case study on multiple intelligence

How Teachers use Gardner’s Multiple Intelligences Theory

• July 8, 2019

Gone are the days when teachers could rely on an IQ test to measure a student’s intelligence. A recent study involving over 100,000 participants found that no one test can measure how well a person would perform cognitive tasks.[8] Because most intelligence tests give only a two-dimensional picture of a person’s mental abilities, they don’t always capture a student’s full potential. If you want to help students develop cognitive skills in a way that meets them at their strengths and shores up their weaknesses, one of the best ways to do so is through Gardner’s multiple intelligences theory.

What are Gardner’s Multiple Intelligences?

In the past, many held up the IQ test as the “golden standard” for measuring intelligence; however, it does not fully capture all of the ways a child can succeed. Just because a child has poor mathematical skills, for example, doesn’t mean that they have impaired artistic or social skills.[5] For this reason, it’s long been important for educational researchers to find better ways to measure a person’s potential beyond the reading and logical skills that IQ tests measure.[9]

The multiple intelligences theory was created by Dr. Howard Gardner, a professor of education at Harvard University, in 1983. It challenges the then-dominant (and still sometimes prevalent) belief that only linguistic and mathematical skills can define a person’s intelligence.[2] Instead, Dr. Gardner proposed eight different skill sets that better grasp the full scope of a child’s abilities.[2]

It’s important to note, however, that Gardner’s multiple intelligences constitute an educational theory and not scientific fact. While many teachers find the theory to be a helpful framework for their curriculum, few studies have been done on whether it is the most accurate model of human intelligence or on its success rate in schools.[15] But from a professional development standpoint, the theory of multiple intelligences is a great reminder for teachers that all students have different strengths and the potential for academic achievement.

The list of Gardner’s multiple intelligences includes:

• Linguistic intelligence
• Logical-mathematical intelligence
• Spatial intelligence
• Musical intelligence
• Bodily-kinesthetic intelligence
• Naturalistic intelligence
• Interpersonal intelligence
• Intrapersonal intelligence

Each of these intelligences are relatively independent of one another.[1] This means that a child can be highly proficient in one intelligence and struggle with another. An athlete, for example, could have strong bodily-kinesthetic and spatial intelligence but poor musical intelligence. That’s why it’s so important to use instructional strategies that involve a variety of these multiple intelligences so every child has the opportunity to learn in a way that works best for them.

Linguistic Intelligence

Linguistic intelligence involves the ability to comprehend words while reading, writing, or speaking. This can include reading and writing in a person’s native tongue, but it also involves the ability to learn new languages.

A few activities and skills related to linguistic intelligence include:

• Reading books aloud or independently
• Learning new vocabulary words
• Writing stories, sentences, or essays

Logical-Mathematical Intelligence

Logical-mathematical intelligence refers to the ability to use reason and analysis to solve problems. Children with strong logical-mathematical skills are also often skilled at identifying patterns to develop answers to a question.

A few logical-mathematical intelligence skills and activities include:

• Learning addition, subtraction, and other math concepts
• Using the scientific method to test hypotheses
• Using logical abilities to create compelling debates

Spatial Intelligence

Spatial intelligence involves the ability to visualize and manipulate environments. Children with strong spatial intelligence are aware of the space around them and skilled at manipulating it in creative or innovative ways.

Spatial intelligence skills or activities you could use in class include:

• Putting together puzzles
• Painting, sculpting, or other artistic activities
• Performing tasks that involve hand-eye coordination

Musical Intelligence

Musical intelligence is defined as the ability to appreciate, create, and perform music. It involves not only does sensory musical activities, but also the theoretical side of music, such as composition.

A few musical intelligence skills or activities can include:

• Practicing pitch or a sense of rhythm
• Learning to sing or play an instrument
• Recognizing musical notes or patterns

Bodily-Kinesthetic Intelligence

Bodily-kinesthetic intelligence involves skillfully moving and controlling your body. Children with a strong sense of bodily-kinesthetic intelligence often succeed in hands-on activities rather than theoretical assignments.

If you want to try bodily-kinesthetic intelligence activities in class, a few ideas can include:

• Participating on a sports team
• Doing relay-races or outdoor games
• Learning the choreography to a dance

Interpersonal Intelligence

Interpersonal intelligence refers to the ability to interact with others in a healthy and meaningful way. Students skilled in interpersonal intelligence can be introverted or extroverted, but they are often good at making and maintaining friendships.

Activities and skills related to interpersonal intelligence include:

• Making positive relationships with peers
• Using effective communication skills
• Comforting a friend when they’re feeling down

Intrapersonal Intelligence

Coinciding in some ways with interpersonal intelligence, intrapersonal intelligence is defined as the ability to understand and analyze your own emotions, actions, and beliefs. It is closely linked to the social-emotional skill of self-awareness, or developing an understanding of yourself and how others perceive you.

Skills and activities that involve interpersonal intelligence include:

• Creating a reflection journal
• Nurturing a strong sense of introspection
• Practicing mindfulness activities like meditation

Naturalistic Intelligence

The eighth type of intelligence, naturalistic intelligence, refers to a person’s sensitivity to and appreciation for the natural world. Students with naturalistic intelligence often have an affinity for recognizing and interacting with plants and animals.

A few activities or skills related to naturalistic intelligence include:

• Hiking, camping, or other outdoor activities
• Taking care of animals
• Recognizing different types of plants

In addition to these eight types of intelligences, Dr. Gardner considered adding existential intelligence. This would involve a person’s ability to understand themselves and the world around them with a philosophical mindset.[10] At this time, however, it is not one of the official intelligences in his theory.

How the Multiple Intelligences Theory Can Help You Reach Struggling Learners

Using multiple intelligences in the classroom, on the other hand, is proven to help students with dyslexia and other learning disabilities.[11] Not all students’ strengths are within traditionally valued types of intelligence like reading or math skills. By discovering the intellectual gifts a child already possesses, you can find ways to work with their existing strengths and help slow learners in the classroom.

Additionally, multiple intelligences theory can help teachers see cognitive abilities in a way that better aligns with science than traditional intelligence tests. Even four- and five-year-olds display strengths and weaknesses within different types of intelligence that function independently.[1] When a student struggles with one skill, keeping the multiple intelligences theory in mind can help teachers see a student’s potential instead of just their weaknesses.

5 Multiple Intelligence Activities and Tips for Reaching Different Types of Learners

When you use multiple intelligences theory in your school, you can provide every student with differentiated instruction strategies that work with their strengths and weaknesses.[4] Not only can this approach help students improve, but it can also help teachers change their perspective towards slow learners or students with disabilities.

Use these five multiple intelligence activities and strategies to help all children in your class reach their potential:

• Try to link all instructional objectives to at least two types of intelligences. If you’re teaching students about multiplication tables, for example, you could add visual references or teach children a song about multiplying.[3]
• The multiple intelligences theory is connected to multisensory learning , which teaches that children learn better with activities that involve more than one sense.[14] Engage your students’ visual, tactile, auditory, and other senses to reach more students.
• Incorporate all of the different multiple intelligences at least once a week. Create a weekly checklist with all eight intelligences so you make sure you’re using a comprehensive multiple intelligence strategy in class.
• When planning interventions for struggling students, discover what their strengths are as connected to the multiple intelligences theory. If a child has strong spatial intelligence but poor linguistic skills, for example, you may be able to use their strengths to teach difficult concepts.
• Use multiple intelligence strategies with ELL students , as this can be particularly helpful for teaching concepts in a language other than their native tongue.[13]
• Gardner, H., and Hatch, T. Multiple Intelligences Go to School: Educational Implications of the Theory of Multiple Intelligences . Educational Researcher, November 1989, 18(8), pp. 4-10.
• Silver, H., Strong, R., and Perini, M. Integrating Learning Styles and Multiple Intelligences . Educational Leadership, September 1997, 55(1), pp. 22-27.
• Armstrong, T. Multiple Intelligences: Seven Ways to Approach Curriculum . Educational Leadership, November 1994, 52(3), pp. 26-28.
• Gardner, H. Multiple Intelligences as a Partner in School Improvement. Educational Leadership, September 1997, 55(1), pp. 20-21.
• Davis, K., Christodoulou, J., Seider, S., and Gardner, H. The Theory of Multiple Intelligences . Cambridge Handbook of Intelligence, 2011, New York: Cambridge University Press.
• Huntsmann, P.R., and O’Loughlin, V.D. Another Nail in the Coffin for Learning Styles? Disparities among Undergraduate Anatomy Students’ Study Strategies, Class Performance, and Reported VARK Learning Styles. Anatomical Sciences Education, 2019, 12(1), pp. 6-19.
• Oostdam, R., and Meijer, J. Influence of test anxiety on measurement of intelligence . Psychology Rep, February 2003, 92(1), pp. 3-20.
• Hampshire, A., Highfield, R.R., Parkin, B.L., and Owen, A.M. Fractionating Human Intelligence. Neuron, December 2012, 76(6), pp. 1225-1237.
• Harvard Graduate School of Education. Multiple Intelligences: Challenging the Standard View of Intelligence . Retrieved from harvard.edu: http://www.pz.harvard.edu/projects/multiple-intelligences.
• Smith, M. Howard Gardner and Multiple Intelligences . Retrieved from smcdsb.on.ca: https://sts.schools.smcdsb.on.ca/UserFiles/Servers/Server_97729/File/St.Thomas%20Aquinas%20Catholic%20Secondary%20School/Staff%20Links/Ms.Whelton/Gardners%20MI%20by%20Smith.pdf.
• Gardner, H. The theory of multiple intelligences. Annals of Dyslexia, January 1987, 37(1), pp. 19-35.
• Denig, S.J. Multiple Intelligences and Learning Styles: Two Complementary Dimensions . Retrieved from cbe.ab.ca: http://projects.cbe.ab.ca/central/altudl/FILES/Multiple_Intellegences_Learning_styles.pdf.
• Beare, K. Multiple Intelligence Activities . Retrieved from thoughtco.com: https://www.thoughtco.com/multiple-intelligence-activities-1211779.
• Kallenbach, S., and Viens, S. Multiple Intelligences in Practice: Teacher Research Reports from the Adult Multiple Intelligences Study. Retrieved from worlded.org: https://www.worlded.org/WEIInternet/inc/common/_download_pub.cfm?id=16687&lid=3.
• Waterhouse, L. Multiple Intelligences, the Mozart Effect, and Emotional Intelligence: A Critical Review. Educational Psychologist, 2006, 41(4), pp. 207-225.

More education articles

National Poetry Month: Elementary Classroom Activities & Picture Books

Every April, the literary world comes alive with rhythm and rhyme as we celebrate National Poetry Month. For elementary school teachers, this month is an

Bridging the Trust Gap in AI: Ethical Design and Product Innovation to Revolutionize Classroom Experiences

Written by Leah Dozier Walker Executive Vice President of Equity & Inclusion at Waterford.org The integration of Artificial Intelligence (AI) holds tremendous promise across the

24 Activities, Teaching Strategies, and Resources for Teaching Students with Autism

Autism spectrum disorder (ASD) is a neurodivergent condition that affects communication, behavior, and learning. Psychologists use the term spectrum disorder because symptoms and support needs

50 Ways to Celebrate Teacher Appreciation Week

MacKenzie Scott’s Yield Giving Awards Waterford.org a $10 Million Grant

End Bullying: October is National Bullying Prevention Month

Science Education in Theory and Practice pp 405–418 Cite as

Multiple Intelligences Theory—Howard Gardner

• Bulent Cavas 3 &
• Pinar Cavas 4  
• First Online: 09 September 2020

19k Accesses

8 Citations

Part of the book series: Springer Texts in Education ((SPTE))

Multiple intelligences theory (MI) developed by Howard Gardner, an American psychologist, in late 1970s and early 1980s, asserts that each individual has different learning areas. In his book, Frames of Mind: The Theory of Multiple Intelligences published in 1983, Gardner argued that individuals have eight different intelligence areas and added one more intelligence area in the later years. Howard Gardner named these nine intelligence areas as “musical–rhythmic”, “visual–spatial”, “verbal–linguistic”, “logical–mathematical”, “bodily–kinesthetic”, “interpersonal”, “intrapersonal”, “naturalistic”, and “existential intelligence. Gardner indicates that these intelligences are constructed through the participation of individuals in culturally valued activities, and these activities help individuals to develop unique patterns in their mind. Multiple intelligences theory states that there are many ways to be intelligent not only just two ways measured by IQ tests. Appearance of multiple intelligences theory has provided significant practices and studies particularly in the field of education to be carried out and has changed educators’ views toward the concepts of learning and intelligence. This chapter discusses the historical and theoretical dimensions of multiple intelligences as well as the research conducted on the theory. We have also provided the advantages and disadvantages of MI implementation in science education.

An intelligence is the ability to solve problems, or to create products, that are valued within one or more cultural settings. Howard Gardner — Frames of Mind ( 1983 ).

This is a preview of subscription content, log in via an institution .

Buying options

• Available as PDF
• Read on any device
• Instant download
• Own it forever
• Available as EPUB and PDF
• Compact, lightweight edition
• Dispatched in 3 to 5 business days
• Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Abdi, A., Laei, S., & Ahmadyan, H. (2013). The effect of teaching strategy based on multiple intelligences on students’ academic achievement in science course. Universal Journal of Educational Research, 1 (4), 281–284.

Google Scholar  

Blumenfield-Jones, D. (2009). Bodily-kinesthetic intelligence and dance education: Critique, revision, and potentials for the democratic idea. Journal of Aesthetic Education, 43 (1), 59–76.

Article   Google Scholar  

Campbell, L., & Campbell, B. (1999). Multiple intelligences and student achievement: Success stories from six schools . Alexandria, VA: Association for Supervision and Curriculum Development. Retrieved from https://goo.gl/Y7Cz3w .

Crowther, G. J., Williamson, J. L., Buckland, H. T., & Cunningham, S. L. (2013). Making material more memorable with music. American Biology Teacher, 75, 713–714. https://doi.org/10.1525/abt.2013.75.9.16 .

Davis, K., Christodoulou, J. A., Seider, S., & Gardner, H. (2011). The theory of multiple intelligences. In R. J. Sternberg & S. B. Kaufman (Eds.), Cambridge handbook of intelligence (pp. 485–503). New York: Cambridge University Press.

Chapter   Google Scholar  

Gardner, H. (1983). Frames of mind: The theory of multiple intelligences . New York: Basic Books.

Gardner, H. (1991). The unschooled mind: How children think and how schools should teach. New York, NY: Basic Books.

Gardner, H. (1993). Multiple intelligences: The theory in practice . New York, NY: Basic Books.

Gardner, H. (1999a). Intelligence reframed: Multiple intelligences for the 21st century . New York, NY: Basic Books.

Gardner, H. (1999b). The disciplined mind: What all students should understand . New York: Simon & Schuster.

Gardner, H. (2006). Multiple intelligences: New horizon . New York, NY: Basic Books.

Gardner, H. (2011). The unschooled mind: How children think and how schools should teach . United Kingdom: Hachette.

Gardner, H., & Walters, J. (1993). Questions and answers about multiple intelligences theory. Multiple intelligences: The theory in practice (pp. 35–48). New York: Basic Books.

Goodnough, K. (2001). Multiple intelligences theory: A framework for personalizing science curricula. School Science and Mathematics., 101 (4), 180–193.

Hoerr, R. T. (2000). Becoming a multiple intelligences school. Retrieved from http://www.ascd.org/publications/books/100006.aspx .

Hom, E. (2014). What is STEM education? Retrieved from https://www.livescience.com/43296-what-is-stem-education.html .

Junchun, W. (2015). To explore the relationship of temporal spatial reasoning between music and mathematics by an inventory based on the multiple intelligence theory. Education and Psychological Research, 38 (3). https://doi.org/10.3966/102498852015093803002 .

Klein, P. (1997). Multiplying the problems of intelligence by eight: A critique of Gardner’s theory. Canadian Journal of Education, 22, 377–394.

Lai, H. Y., & Yap, S. L. (2016). Application of multiple intelligence theory in the assessment for learning. In S. Tang & L. Logonnathan (Eds.), Assessment for learning within and beyond the classroom (pp. 427–436). Singapore: Springer.

Martin, M. R., Bishop, J., Ciotto, C., & Gagnon, A. (2014). Teaching the whole child: Using the multiple intelligence theory and interdisciplinary teaching in physical education. In The chronicle of kinesiology in higher education ( Special Edition , pp. 25–29).

Martín, J. S., Gragera, G. J. A., Dávila-Acedo, M., & Mellado, V. (2017). What do K-12 students feel when dealing with technology and engineering issues? Gardner’s multiple intelligence theory implications in technology lessons for motivating engineering vocations at Spanish secondary school. European Journal of Engineering Education, 42 (6), 1330–1343.

Martin, M., & McKenzie, M. (2013). Sport education and multiple intelligences: A path to student success. Strategies, 26 (4), 31–34.

Morgan, H. (1996). An analysis of Gardner’s theory of multiple intelligence. Roeper Review, 18, 263–269.

Ozdermir, P., Güneysu, S., & Tekkaya, C. (2006). Enhancing learning through multiple intelligences. Journal of Biological Education, 40 (2), 74–78.

Richards, D. (2016). The integration of the multiple intelligence theory into the early childhood curriculum. American Journal of Educational Research, 4 (15), 1096–1099. Retrieved from http://pubs.sciepub.com/education/4/15/7 .

Schulkind, M. D. (2009). Is memory for music special? Annals of the New York Academy of Sciences, 1169, 216–224. https://doi.org/10.1111/j.1749-6632.2009.04546.x .

Schwert, A. (2004). Using the theory of multiple intelligences to enhance science education . Unpublished Master’s Thesis. The University of Toledo, USA. Retrieved from http://utdr.utoledo.edu/cgi/viewcontent.cgi?article=1487&context=graduate-projects .

Suprapto, N., Liu, W. Y., & Ku, C. K. (2017). The implementation of multiple intelligence in (science) classroom: From empirical into critical. Pedagogika, 126 (2), 214–227.

Viadero, D. (2003). Staying power. Education Week, 22 (39), 24.

Download references

Author information

Authors and affiliations.

Buca Faculty of Education, Dokuz Eylül University, Izmir, Turkey

Bulent Cavas

Faculty of Education, Ege University, Izmir, Turkey

Pinar Cavas

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Bulent Cavas .

Editor information

Editors and affiliations.

Science Teachers Association of Nigeria, Abuja, Nigeria

University of Texas at Tyler, Tyler, TX, USA

Teresa J. Kennedy

Recommended Resources

Gardner, H. (1999a). Intelligence reframed: Multiple intelligences for the 21st century . New York: Basic Books.

Gardner, H. (2004). Frequently asked questions—Multiple intelligences and related educational topics. Retrieved March 9, 2018, from http://multipleintelligencesoasis.org/wp-content/uploads/2013/06/faq.pdf .

Gardner, H. (2006). Multiple intelligences: New Horizon . New York: Basic Books.

Gardner, H. (2011). The unschooled mind: How children think and how schools should teach . UK: Hachette.

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this chapter

Cite this chapter.

Cavas, B., Cavas, P. (2020). Multiple Intelligences Theory—Howard Gardner. In: Akpan, B., Kennedy, T.J. (eds) Science Education in Theory and Practice. Springer Texts in Education. Springer, Cham. https://doi.org/10.1007/978-3-030-43620-9_27

Download citation

DOI : https://doi.org/10.1007/978-3-030-43620-9_27

Published : 09 September 2020

Publisher Name : Springer, Cham

Print ISBN : 978-3-030-43619-3

Online ISBN : 978-3-030-43620-9

eBook Packages : Education Education (R0)

Share this chapter

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Publish with us

Policies and ethics

• Find a journal
• Track your research

Howard Gardner’s Theory of Multiple Intelligences

Michele Marenus

Research Scientist

B.A., Psychology, Ed.M., Harvard Graduate School of Education

Michele Marenus is a Ph.D. candidate at the University of Michigan with over seven years of experience in psychology research.

Learn about our Editorial Process

Saul Mcleod, PhD

Editor-in-Chief for Simply Psychology

BSc (Hons) Psychology, MRes, PhD, University of Manchester

Saul Mcleod, PhD., is a qualified psychology teacher with over 18 years of experience in further and higher education. He has been published in peer-reviewed journals, including the Journal of Clinical Psychology.

Olivia Guy-Evans, MSc

Associate Editor for Simply Psychology

BSc (Hons) Psychology, MSc Psychology of Education

Olivia Guy-Evans is a writer and associate editor for Simply Psychology. She has previously worked in healthcare and educational sectors.

On This Page:

Howard Gardner first proposed the theory of multiple intelligences in his 1983 book “Frames of Mind”, where he broadens the definition of intelligence and outlines several distinct types of intellectual competencies.

Gardner developed a series of eight inclusion criteria while evaluating each “candidate” intelligence that was based on a variety of scientific disciplines.

He writes that we may all have these intelligences, but our profile of these intelligences may differ individually based on genetics or experience.

Gardner defines intelligence as a “biopsychological potential to process information that can be activated in a cultural setting to solve problems or create products that are of value in a culture” (Gardner, 2000, p.28).

What is Multiple Intelligences Theory?

• Howard Gardner’s theory of multiple intelligences proposes that people are not born with all of the intelligence they will ever have.
• This theory challenged the traditional notion that there is one single type of intelligence, sometimes known as “g” for general intelligence, that only focuses on cognitive abilities.
• To broaden this notion of intelligence, Gardner introduced eight different types of intelligences consisting of: Linguistic, Logical/Mathematical, Spatial, Bodily-Kinesthetic, Musical, Interpersonal, Intrapersonal, and Naturalist.
• Gardner notes that the linguistic and logical-mathematical modalities are most typed valued in school and society.
• Gardner also suggests that there may other “candidate” intelligences—such as spiritual intelligence, existential intelligence, and moral intelligence—but does not believe these meet his original inclusion criteria. (Gardner, 2011).

Linguistic Intelligence (word smart)

Linguistic Intelligence is a part of Howard Gardner’s multiple intelligence theory that deals with sensitivity to the spoken and written language, ability to learn languages, and capacity to use language to accomplish certain goals.

Linguistic intelligence involves the ability to use language masterfully to express oneself rhetorically or poetically. It includes the ability to manipulate syntax, structure, semantics, and phonology of language.

People with linguistic intelligence, such as William Shakespeare and Oprah Winfrey, have the ability to analyze information and create products involving oral and written language, such as speeches, books, and memos.

Potential Career Choices

Careers you could dominate with your linguistic intelligence:

Lawyer Speaker / Host Author Journalist Curator

Logical-Mathematical Intelligence (number/reasoning smart)

Logical-mathematical intelligence refers to the capacity to analyze problems logically, carry out mathematical operations, and investigate issues scientifically.

Logical-mathematical intelligence involves the ability to use logic, abstractions, reasoning, and critical thinking to solve problems. It includes the capacity to understand the underlying principles of some kind of causal system.

People with logical-mathematical intelligence, such as Albert Einstein and Bill Gates, have an ability to develop equations and proofs, make calculations, and solve abstract problems.

Careers you could dominate with your logical-mathematical intelligence:

Mathematician Accountant Statistician Scientist Computer Analyst

Spatial Intelligence (picture smart)

Spatial intelligence involves the ability to perceive the visual-spatial world accurately. It includes the ability to transform, modify, or manipulate visual information. People with high spatial intelligence are good at visualization, drawing, sense of direction, puzzle building, and reading maps.

Spatial intelligence features the potential to recognize and manipulate the patterns of wide space (those used, for instance, by navigators and pilots) as well as the patterns of more confined areas, such as those of importance to sculptors, surgeons, chess players, graphic artists, or architects.

People with spatial intelligence, such as Frank Lloyd Wright and Amelia Earhart, have the ability to recognize and manipulate large-scale and fine-grained spatial images.

Careers you could dominate with your spatial intelligence:

Pilot Surgeon Architect Graphic Artist Interior Decorator

Bodily-Kinesthetic Intelligence (body smart)

Bodily-kinesthetic intelligence is the potential of using one’s whole body or parts of the body (like the hand or the mouth) to solve problems or to fashion products.

Bodily-kinesthetic intelligence involves using the body with finesse, grace, and skill. It includes physical coordination, balance, dexterity, strength, and flexibility. People with high bodily-kinesthetic intelligence are good at sports, dance, acting, and physical crafts.

People with bodily-kinesthetic intelligence, such as Michael Jordan and Simone Biles, can use one’s own body to create products, perform skills, or solve problems through mind–body union.

Careers you could dominate with your bodily-kinesthetic intelligence:

Dancer Athlete Surgeon Mechanic Carpenter Physical Therapist

Musical Intelligence (music smart)

Musical intelligence refers to the skill in the performance, composition, and appreciation of musical patterns.

Musical intelligence involves the ability to perceive, discriminate, create, and express musical forms. It includes sensitivity to rhythm, pitch, melody, and tone color. People with high musical intelligence are good at singing, playing instruments, and composing music.

People with musical intelligence, such as Beethoven and Ed Sheeran, have the ability to recognize and create musical pitch, rhythm, timbre, and tone.

Careers you could dominate with your musical intelligence:

Singer Composer DJ Musician

Interpersonal Intelligence (people smart)

Interpersonal intelligence is the capacity to understand the intentions, motivations, and desires of other people and, consequently, to work effectively with others.

Interpersonal intelligence involves the ability to understand and interact effectively with others. It includes sensitivity to other people’s moods, temperaments, motivations, and desires. People with high interpersonal intelligence communicate well and can build rapport.

People with interpersonal intelligence, such as Mahatma Gandhi and Mother Teresa, have the ability to recognize and understand other people’s moods, desires, motivations, and intentions.

Careers you could dominate with your interpersonal intelligence:

Teacher Psychologist Manager Salespeople Public Relations

Intrapersonal Intelligence (self-smart)

Intrapersonal intelligence is the capacity to understand oneself, to have an effective working model of oneself, including one’s desires, fears, and capacities—and to use such information effectively in regulating one’s own life.

It includes self-awareness, personal cognizance, and the ability to refine, analyze, and articulate one’s emotional life.

People with intrapersonal intelligence, such as Aristotle and Maya Angelou, have the ability to recognize and understand his or her own moods, desires, motivations, and intentions.

This type of intelligence can help a person understand which life goals are important and how to achieve them.

Careers you could dominate with your intrapersonal intelligence:

Therapist Psychologist Counselor Entrepreneur Clergy

Naturalist intelligence (nature smart)

Naturalist intelligence involves the ability to recognize, categorize, and draw upon patterns in the natural environment. It includes sensitivity to the flora, fauna, and phenomena in nature. People with high naturalist intelligence are good at classifying natural forms.

Naturalistic intelligence involves expertise in recognizing and classifying the numerous species—the flora and fauna—of his or her environment.

People with naturalistic intelligence, such as Charles Darwin and Jane Goddall, have the ability to identify and distinguish among different types of plants, animals, and weather formations that are found in the natural world.

Careers you could dominate with your naturalist intelligence:

Botanist Biologist Astronomer Meteorologist Geologist

Critical Evaluation

Most resistance to multiple intelligences theory has come from cognitive psychologists and psychometricians. Cognitive psychologists such as Waterhouse (2006) claimed that there is no empirical evidence to the validity of the theory of multiple intelligences.

Psychometricians, or psychologists involved in testing, argue that intelligence tests support the concept for a single general intelligence, “g”, rather than the eight distinct competencies (Gottfredson, 2004). Other researchers argue that Gardner’s intelligences comes second or third to the “g” factor (Visser, Ashton, & Vernon, 2006).

Some responses to this criticism include that the multiple intelligences theory doesn’t dispute the existence of the “g” factor; it proposes that it is equal along with the other intelligences. Many critics overlook the inclusion criteria Gardner set forth.

These criteria are strongly supported by empirical evidence in psychology, biology, neuroscience, among others. Gardner admits that traditional psychologists were valid in criticizing the lack of operational definitions for the intelligences, that is, to figure out how to measure and test the various competencies (Davis et al., 2011).

Gardner was surprised to find that Multiple Intelligences theory has been used most widely in educational contexts. He developed this theory to challenge academic psychologists, and therefore, he did not present many educational suggestions. For this reason, teachers and educators were able to take the theory and apply it as they saw fit.

As it gained popularity in this field, Gardner has maintained that practitioners should determine the theory’s best use in classrooms. He has often declined opportunities to aid in curriculum development that uses multiple intelligences theory, opting to only provide feedback at most (Gardner, 2011).

Most of the criticism has come from those removed from the classroom, such as journalists and academics. Educators are not typically tied to the same standard of evidence and are less concerned with abstract inconsistencies, which has given them the freedom to apply it with their students and let the results speak for itself (Armstrong, 2019).

Shearer (2020) provides extensive empirical evidence from neuroscience research supporting MI theory.

Shearer reviewed evidence from over 500 functional neuroimaging studies that associate patterns of brain activation with the cognitive components of each intelligence.

The visual network was associated with the visual-spatial intelligence, somatomotor networks with kinesthetic intelligence, fronto-parietal networks with logical and general intelligence, auditory networks with musical intelligence, and default mode networks with intra- and interpersonal intelligences. The coherence and distinctiveness of these networks provides robust support for the neural validity of MI theory

He concludes that human intelligence is best characterized as being multiple rather than singular, with each person possessing unique neural potentials aligned with specific intelligences.

Implications for Learning

The most important educational implications of the theory of multiple intelligences can be summed up through individuation and pluralization. Individuation posits that because each person differs from other another there is no logical reason to teach and assess students identically.

Individualized education has typically been reserved for the wealthy and others who could afford to hire tutors to address individual student’s needs.

Technology has now made it possible for more people to access a variety of teachings and assessments depending on their needs. Pluralization, the idea that topics and skills should be taught in more than one way, activates an individual’s multiple intelligences.

Presenting a variety of activities and approaches to learning helps reach all students and encourages them to be able to think about the subjects from various perspectives, deepening their knowledge of that topic (Gardner, 2011b).

A common misconception about the theory of multiple intelligences is that it is synonymous with learning styles. Gardner states that learning styles refer to the way an individual is most comfortable approaching a range of tasks and materials.

Multiple intelligences theory states that everyone has all eight intelligences at varying degrees of proficiency and an individual’s learning style is unrelated to the areas in which they are the most intelligent.

For example, someone with linguistic intelligence may not necessarily learn best through writing and reading. Classifying students by their learning styles or intelligences alone may limit their potential for learning.

Research shows that students are more engaged and learn best when they are given various ways to demonstrate their knowledge and skills, which also helps teachers more accurately assess student learning (Darling-Hammond, 2010).

Therapeutic Benefits of Incorporating Multiple Intelligences Within Therapy

Pearson et al. (2015) investigated the experiences of 8 counselors who introduced multiple intelligences (MI) theory and activities into therapy sessions with adult clients. The counselors participated in a 1-day MI training intervention and were interviewed 3 months later about their experiences using MI in practice.

The major themes that emerged from qualitative analysis of the interviews were:

• MI helped enhance therapeutic alliances. Counselors felt incorporating MI strengthened their connections with clients, increased counselor and client comfort, and reduced client suspicion/resistance.
• MI led to more effective professional work. Counselors felt MI provided more tools and flexibility in responding to clients. This matches findings from education research on the benefits of MI.
• Clients responded positively to identifying strengths through MI. The MI survey helped clients recognize talents/abilities, which counselors saw as identity-building. This aligns with the literature on strength-based approaches.
• Clients appreciated the MI preference survey. It provided conversation starters, increased self-reflection, and was sometimes a catalyst for using music therapeutically.
• Counselors felt comfortable with MI. They experienced increased confidence and professional comfort. Counselor confidence contributes to alliance building (Ackerman & Hilsenroth, 2003).
• Music use stood out as impactful. In-session and extratherapeutic music use improved client well-being after identifying musicality through the MI survey. This matches the established benefits of music therapy (Koelsch, 2009).
• MI training opened up therapeutic possibilities. Counselors valued the experiential MI training. MI appeared to expand their skills and activities.

The authors conclude that MI may enhance alliances, effectiveness, and counselor confidence. They recommend further research on long-term impacts and optimal training approaches. Counselor education could teach MI theory, assessment, and tailored interventions.

Frequently Asked Questions

How can understanding the theory of multiple intelligences contribute to self-awareness and personal growth.

Understanding the theory of multiple intelligences can contribute to self-awareness and personal growth by providing a framework for recognizing and valuing different strengths and abilities.

By identifying their own unique mix of intelligences, individuals can gain a greater understanding of their own strengths and limitations and develop a more well-rounded sense of self.

Additionally, recognizing and valuing the diverse strengths and abilities of others can promote empathy , respect, and cooperation in personal and professional relationships.

Why is multiple intelligence theory important?

Understanding multiple intelligences is important because it helps individuals recognize that intelligence is not just about academic achievement or IQ scores, but also includes a range of different abilities and strengths.

By identifying their own unique mix of intelligences, individuals can develop a greater sense of self-awareness and self-esteem, as well as pursue career paths that align with their strengths and interests.

Additionally, understanding multiple intelligences can promote more inclusive and personalized approaches to education and learning that recognize and value the diverse strengths and abilities of all students.

Are certain types of intelligence more valued or prioritized in society than others?

Yes, certain types of intelligence, such as linguistic and logical-mathematical intelligence, are often prioritized in traditional education and assessment methods.

However, the theory of multiple intelligences challenges this narrow definition of intelligence and recognizes the value of a diverse range of strengths and abilities.

By promoting a more inclusive and personalized approach to education and learning, the theory of multiple intelligences can help individuals recognize and develop their unique mix of intelligences, regardless of whether they align with traditional societal expectations.

What is the difference between multiple intelligences and learning styles?

The theory of multiple intelligences proposes that individuals possess a range of different types of intelligence. In contrast, learning styles refer to an individual’s preferred way of processing information, such as visual, auditory, or kinesthetic.

While both theories emphasize the importance of recognizing and valuing individual differences in learning and development, multiple intelligence theory proposes a broader and more diverse range of intelligences beyond traditional academic abilities, while learning styles are focused on preferences for processing information.

Armstrong, T. (2009). Multiple intelligences in the classroom . Ascd.

Darling-Hammond, L. (2010). Performance Counts: Assessment Systems That Support High-Quality Learning . Council of Chief State School Officers .

Davis, K., Christodoulou, J., Seider, S., & Gardner, H. E. (2011). The theory of multiple intelligences.  Davis, K., Christodoulou, J., Seider, S., & Gardner, H.(2011). The theory of multiple intelligences . In RJ Sternberg & SB Kaufman (Eds.), Cambridge Handbook of Intelligence , 485-503.

Edutopia. (2013, March 8). Multiple Intelligences: What Does the Research Say? https://www.edutopia.org/multiple-intelligences-research

Gardner, H. E. (2000). Intelligence reframed: Multiple intelligences for the 21st century . Hachette UK.

Gardner, H. (2011a). Frames of mind: The theory of multiple intelligences . Hachette Uk.

Gardner, H. (2011b). The theory of multiple intelligences: As psychology, as education, as social science. Address delivered at José Cela University on October, 29, 2011.

Gottfredson, L. S. (2004). Schools and the g factor . The Wilson Quarterly (1976-), 28 (3), 35-45.

Pearson, M., O’Brien, P., & Bulsara, C. (2015). A multiple intelligences approach to counseling: Enhancing alliances with a focus on strengths.  Journal of Psychotherapy Integration, 25 (2), 128–142

Shearer, C. B. (2020). A resting state functional connectivity analysis of human intelligence: Broad theoretical and practical implications for multiple intelligences theory.  Psychology & Neuroscience, 13 (2), 127–148.

Visser, B. A., Ashton, M. C., & Vernon, P. A. (2006). Beyond g: Putting multiple intelligences theory to the test . Intelligence, 34 (5), 487-502.

Waterhouse, L. (2006). Inadequate evidence for multiple intelligences, Mozart effect, and emotional intelligence theories . Educational Psychologist, 41 (4), 247-255.

Further Information

• Multiple Intelligences Criticisms
• The Theory of Multiple Intelligences
• Multiple Intelligences FAQ
• “In a Nutshell,” the first chapter of Multiple Intelligences: New Horizons
• Multiple Intelligences After Twenty Years”
• Intelligence: Definition, Theories and Testing
• Fluid vs Crystallized Intelligence

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List
• Front Psychol

A Conceptual Analysis of the Semantic Use of Multiple Intelligences Theory and Implications for Teacher Education

Gardner’s theory of multiple intelligences (MI) has been at the center of a long-running debate in educational psychology in terms of its generalizable validity. In this article, MI theory is discussed for a review of why and how MI theory may be contextually discussed for preservice teachers to learn about in their teacher education program. The semantic conceptual basis of intelligence in MI theory is discussed in comparison to learning styles theory with implications for the importance of the teaching of Universal Design for Learning and related frameworks in teacher education curriculum.

Introduction

Gardner’s (1983 , 2006) theory of multiple intelligences [hereafter referred to as multiple intelligences (MI) theory] has had substantial influence on K-12 curriculum design and implementation. This influence has been promoted, at times, through professional development for in-service teachers and in teacher education programs for preservice teachers (see, for example, “Project Zero” from the Harvard Graduate School of Education; Multiple Intelligence Schools, 2022 ). The seven and then eight intelligences that comprise the theory that Gardner (1983 , 2006) posited have influenced teachers, students, and teacher educators across the world ( Brualdi Timmins, 1996 ; Rousseau, 2021 ). This influence has generated a long-standing debate among educational psychologists about the efficacy and validity of MI theory. While there has been substantial discussion of the varying points of view of educational psychologists and teachers on MI theory, there is not nearly as much discussion of this issue for teacher educators who address MI theory in what may be the only educational psychology course that preservice teachers take during their teacher education program. There should be more literature specifically on the teacher educator perspective on how to teach MI theory to preservice teachers in comparison to Understanding by Design (UbD) and Universal Design for Learning (UDL). This paper reevaluates the debate about the efficacy and validity of MI theory, and makes recommendations for how this debate can be introduced and discussed in a survey course on educational psychology for preservice teachers.

Most preservice teachers seem to have a favorable opinion of Gardner’s MI theory ( Rousseau, 2021 ). This is despite the long-standing critical debate on the theory’s efficacy and validity from the technical perspectives of educational psychologists ( Schulte et al., 2004 ; Bordelon and Banbury, 2005 ; Visser et al., 2006 ; Waterhouse, 2006 ; McGreal, 2013 ; Rogowsky et al., 2015 ; Willingham et al., 2015 ; Rousseau, 2021 ). Additionally, a study by Luo and Huang (2019) of English as a second language (ESL) teachers’ self-perception of MI theory and the uses of the defined multiple intelligences found either ambiguity or no significant correlation between MI theory and its instructional strategies, further supporting the critics of MI theory based on it not having statistical validity. These findings prompt the question of why? Why do preservice teachers tend to have an overall positive opinion of MI theory? This paper addresses these questions as a conceptual issue in semantics.

Part of the answer for preservice teacher perception of MI theory may be in the perspectives they developed in either their teacher education program or in their school placement ( Rousseau, 2021 ). This may present as having heard about anecdotal success in applying MI theory, and then assuming it is beneficial in and of itself without critical evaluation of whether theories such as MI theory are supported in psychological science. The other part of the answer is in the educational psychological research that supports MI theory in qualitative principle but not in the technical aspects of statistical validity. These can become conflated when preservice teachers go into their field placements and hear the words differentiation and learning styles and semantically linking these to preferences in an unquestioning assumption because of perceived popularity despite technical differences among these concepts in psychological science, especially in reference to the word intelligence in context of MI theory. This second reason reinforces the first because preservice teachers’ perception of the effectiveness of learning styles and related theories, especially MI theory, tends to be influenced by anecdotal experience ( Menz et al., 2021 ).

Comparative Literature Review

Interpreting the research links and conceptual overlap of mi theory and learning styles theory.

While most of the critique of MI theory is in the technical use of the word “intelligences” and the testing of MI theory’s validity in correlating the intelligences to teaching and learning that have found no correlation between MI theory and its instructional strategies (e.g., Schulte et al., 2004 ; Visser et al., 2006 ; Waterhouse, 2006 ; Rogowsky et al., 2015 ; Willingham et al., 2015 ; Luo and Huang, 2019 ), there are a number of studies that demonstrated favorable findings that partially validate MI theory, though there are qualifying limitations (e.g., Mokhtar et al., 2008 ; Furnham, 2009 ; Wu and Alrabah, 2009 ; Dolati and Tahriri, 2017 ; Prast et al., 2018 ; Yidana et al., 2022 ). However, Pashler et al. (2008) suggested that some studies that suggest favorable findings of learning styles theories there might be ambiguity in the study design leading to inconclusive findings. The issue, again, seems to be predicated on the semantics of MI theory in its use of the word intelligences. Other studies have emphasized contextual interpretation with statistical data analysis involving in-service teachers or preservice teachers to provide evidence of MI theory’s qualitative effectiveness in the multiple-subject curriculum of elementary school to secondary school science and mathematics (e.g., Baş and Beyhan, 2010 ; Modirkhamene and Azhiri, 2012 ; Milić and Simeunović, 2017 ; Koçak Altundağ, 2018 ; Ghaznavi et al., 2021 ; Shahzada et al., 2021 ). These case studies further support the efficacy of MI theory in classroom practice.

Armstrong’s (2018) textbook Multiple Intelligences in the Classroom (in its fourth edition in 2018) demonstrates what seems to continue to be perennial interest—and, perhaps it could be said, popularity among teachers—of MI theory for inspiring engagement with ways in which to differentiate instruction and link with the related learning styles theories. Multiple intelligences theory and learning styles theory, while different, do interface with each other in that the theory of learning styles could be viewed as the conceptual framework while MI theory is an operationalization of that framework. According to Silver et al. (1997) :

“Though both theories claim that dominant ideologies of intelligence inhibit our understanding of human differences, learning styles are concerned with differences in the process of learning, whereas multiple intelligences center on the content and products of learning. Until now, neither theory has had much to do with the other” (para. 2).

With MI theory’s continued place in popular discussion, it should be contextualized in educational psychology courses for preservice teachers with an emphasis on additional evidence-based frameworks. These evidence-based frameworks include “Understanding by Design” (UbD; see Wiggins and McTighe, 2005 ) and UDL (see Hall et al., 2012 ).

Role of Anecdotal Evidence

Psychology is sometimes viewed as a helping profession as it is often applied across human services fields ( Sternberg and Dennis, 1997 ). Teacher education is historically rooted in the field of psychology. As a social science, psychology’s use of validity tests of pedagogical strategies is important. That being stated, teaching—as a helping profession—is also as much about the teacher’s intuition informed by their teaching experience and their anecdotal observations of a lesson’s effects historically and in the present on student learning. Anecdotes matter because teaching can differ from textbook theories, even if those psychological theories have validity. As such, historical study and psychological study are linked, and this can often include individual stories ( Vaughn-Blount et al., 2009 ). Anecdote should not replace psychological science, but neither should quantitative studies be used to the exclusion of all anecdotal experience as an important source of information about teaching practice. These are different constructs that each hold a place in educational psychology. The stories of anecdotal observation by Stock (1993) and Weber (1993) , for example, are examples of the importance of anecdotes in assessing teaching and learning. Similarly, the importance of the anecdote and anecdotal method has been established for its helpful role in teacher professional knowledge construction ( Doecke et al., 2000 ; Attwood, 2021 ).

Although the effect of anecdotal evidence can be substantially influential, the quality of anecdotes can be difficult for individuals to discern. Hornikx (2018) noted in their study testing the effect on participants’ opinions using “high-quality” and “low-quality” anecdotal evidence that “contrary to theoretical expectations, readers were not found to be sensitive to the quality of anecdotal evidence: The similar and dissimilar variants were equally persuasive” (p. 333). Such a finding might offer further basis for why MI theory has been found to be popular with preservice teachers when considering the findings of Rousseau (2021) . It also might underscore some of the concerns of critics of MI theory who suggest that MI theory lacks sufficient scientific basis for its claims regarding multiple intelligences ( Waterhouse, 2006 ; Willingham et al., 2015 ). The critique of validity in strategies such as MI theory is important and should be emphasized in educational psychology, but the qualitative and anecdotal observations of teachers who are daily in their classrooms seeing favorable results from differentiated practice is at least as important and should likewise have a place in educational psychology curriculum. Sometimes, the semantics of the framework becomes an obstacle and, instead, the observed results in the classroom might matter more. It is in that perspective, then, that MI theory continues to influence some educators in presenting MI theory with what appears to be an overall favorable impression of the theory’s possibilities.

Although there has been a substantial phase of popularity in the critique of “neuromyths” prompted, in part, by critical studies of MI theory during the 2000s and 2010s, this appears to be waning and perhaps partially reversing, at least temporarily ( Gardner, 2020 ; Rousseau, 2021 ). An example of the popularity of critique has been in the widely assigned textbook Educational Psychology: Developing Learners by Ormrod et al. (2020) , which by 2020 was in its tenth edition. This textbook for undergraduate preservice K-12 teachers and psychology students features a critique of “neuromyths” in the first chapter. Among the critiques is one focused on learning styles theories and Gardner’s (1983 , 2006) MI theory. There was some ambivalence in the critique, but it was more in the negative.

Considering how widely used this textbook is in survey courses in educational psychology in the United States, this raises the earlier question, again: Why do preservice teachers still seem to have an overall positive opinion of MI theory, as Rousseau (2021) discussed in a review of several international studies. Part of the reason is what may be an emphasis on qualitative interpretation rather than quantitative inquiry in educational psychology courses for preservice K-12 teachers because they will be teaching in one school and informed by their own individual teaching experience and the experience of their supervising teacher to adapt to the conditions of their local classrooms in consultation with colleagues. In this scenario, the individual experience in full-time student teaching might take precedence, at least in the near term, over the studies that critiqued MI theory that they may have read previously.

Connecting Concepts in Learning Styles Theory Across Contexts of Language

It is important for teacher educators to make the connection between studies in psychological science and the daily routines of K-12 schools evident for preservice teachers. Achieving this connection in their educational psychology course is important for encouraging preservice teachers to emphasize evidence-based pedagogical frameworks (e.g., UbD and UDL) in their lesson planning and practice as classroom teachers. This connection should be established so preservice teachers may contextualize anecdotal experience with studies in psychological science to foster understanding of evidence-based frameworks, they might be less likely to continue to have misconceptions about MI theory and learning styles theory ( Menz et al., 2021 ; Rousseau, 2021 ).

When teacher educators teach the importance of both qualitative and quantitative inquiry in educational psychology, preservice teachers can decide what will work for them in the classroom. Contextualizing technical scientific validity matters for how to translate those studies to what seems to work and can most efficiently be communicated for and in the K-12 classroom. Preservice teachers should be taught frameworks for implementing effective instruction and classroom management, and this can involve teaching about MI theory to get preservice teachers thinking about intentional, inclusive curriculum design. Thus, teacher educators should probably emphasize what MI theory has to offer practically to encourage effective differentiation of instruction.

There are increasingly more examples of demonstrating connections between research that tests MI theory and presents favorable findings of MI theory. A study of secondary school economics teachers found that there was a statistically significant difference using a multiple analysis of variance in teachers’ use of a bodily-kinesthetic approach to teaching economics in secondary school based on the teacher’s teaching experience ( Yidana et al., 2022 ). In a study of English as a foreign language (EFL) teachers, the researchers found that “only teachers of logical-mathematical type were influenced by their dominant intelligence type and other intelligence types did not exert a significant influence on the types of activities being implemented in the classes” ( Dolati and Tahriri, 2017 , p. 1). It was also notable that the majority of the teachers in that study “did not have any education at the university level about the MI theory” ( Dolati and Tahriri, 2017 , p. 7). This indicates further support for the logical-mathematical intelligence construct in MI theory because the teachers in that study were not taught about MI theory in their teacher education program suggesting little to no prior influence on their opinion of the theory. In a study comparing EFL students internationally and applying MI theory in a cross-cultural analysis, Wu and Alrabah (2009) applied MI theory to identify students’ learning preferences to develop a differentiated teaching approach. These studies further suggest the popularity of MI theory for its pedagogical potential in successfully implementing a differentiated curriculum. The question, then, is prompted again to what the extent of overlap between MI theory’s concept of plural intelligences is and whether it is being used in practice as nearly synonymous with preferences . This is especially relevant when considering MI theory’s relationship to—and operationalization of—learning styles theory ( Silver et al., 1997 ).

Precision in Word Choice of Intelligences or Preferences at Center of MI Theory Debate

If the word intelligences were replaced with the word preferences in MI theory, there might be a shift in the debate of MI theory’s efficacy. The semantics of MI theory’s context in teacher education may be part of the reason why many preservice teachers may tend to have a favorable perception of MI theory because the concept of intelligences seems to be used synonymously with preferences. Nevertheless, a student’s preference in modality (i.e., auditory) may still not necessarily be the best approach for their learning depending on the topic, skill, and activity being taught, though there is some conflicting evidence ( Rogowsky et al., 2015 ). Approaching MI theory from a classroom practitioner perspective is generally how preservice teachers will interact with the concept of MI theory. With this understanding, it makes sense that technical validity studies would be of less importance if the classroom observations of MI theory’s implementation appear to support its use for K-12 classroom instruction.

Differentiation is, in part, about aligning instruction to student preferences as much as anything else for the purpose of maintaining or increasing student engagement. This has been one of the benefits of MI theory in teacher education. The debate about MI theory has perhaps, ultimately, been more about the semantics of the word intelligences and observations of anecdotal benefits of its implementation. The technical aspects of quantitative validity are important, but not always to a level that supersedes the qualitative effectiveness of the theory’s application if the discussion is focused on preservice teachers’ observations of its use in classrooms. If students appear engaged in the content when using MI theory, then perhaps that makes more of a positive difference for in-service teachers. Even when validation tests do not meet or exceed the 95 percent confidence interval, there will still be anecdotal cases of apparent success in the theory’s implementation (e.g., Furnham, 2009 ).

Semantics of MI Theory Affect Assessment Conceptualization

Student engagement is often part of formative assessment in K-12 classrooms, hence part of the reason that MI theory became popular in the late twentieth century as a potential way to address differentiated engagement. This is where more recent discussion in the MI theory debate has trended. When teachers assess students based on MI theory or related, though different, learning styles theory in their classroom, Papadatou-Pastou et al. (2018) observed that there can be a dissonance in the preferences being assessed by the teacher and the students’ self-assessment of their own preferences on the given task. If using the MI theory as a lens, preferences can become conflated with the definition of intelligence used in MI theory. In a broader discussion of self-assessment, Coutinho et al. (2021) addressed the related issue of the Dunning-Kruger effect in the debate on learning styles theories when student preferences are emphasized to the point that they could potentially over-rely on self-assessment.

If the word intelligence is changed to preference, it seems that the issue of validity may not be as relevant, and self-assessments could be checked against the teacher’s assessment of the given task or assignment so that the unit grade is not based on the student’s self-assessment. The word change would also likely address Willingham et al. (2015) in their critique of learning styles theories and the inferred influence of Gardner’s (1983 , 2006) MI theory. To avoid this semantic issue, preservice teachers would benefit more from being taught UDL which addresses student preferences within an evidence-based framework so that their learning is personalized to what will more likely generate effective learning instead of relying solely on a student’s self-reported preference which may not be accurate or best for their achievement of the learning goals.

When testing MI theory to ascertain if it holds validity in assessing instructional strategies aligned to its concept of multiple intelligences, many studies have found no widespread statistical correlation or validity in MI theory’s concepts of multiple intelligences and instructional strategies aligned to those purported intelligences (e.g., Waterhouse, 2006 ; Willingham et al., 2015 ; Luo and Huang, 2019 ). However, some case studies have found statistical significance for some of the MI domains (e.g., Dolati and Tahriri, 2017 ; Yidana et al., 2022 ), or partial significance for one but not the other domains (e.g., Rogowsky et al., 2015 ). While divergent findings further the debate of MI theory, this again seems to suggest the issue of the semantics of this theory and its overlap with learning styles theory, as the use of the word “intelligence” in MI theory can cause confusion from a technical standpoint in psychological science where the word preferences may be a better fit for Gardner’s theory, especially in context of its overlapping application with learning styles theory.

Some studies that emphasized qualitative observation in assessment practices and semantically infer that the use of the word intelligences is practically synonymous with preferences suggest more positive results, though not generalizable (e.g., Mokhtar et al., 2008 ; Baş and Beyhan, 2010 ). However, when testing MI theory’s application in how assessment of student learning is conducted in an MI theory-based curriculum, findings from studies suggest ambiguity or little scientific foundation for MI theory ( Luo and Huang, 2019 ). This, taken together with other studies that raise questions of MI theory’s generalizable significance or lack of correlation between it and assessment strategies based upon it ( Waterhouse, 2006 ; Willingham et al., 2015 ), provide additional support for explicit direct instruction (EDI) in the teaching of English as a second language, as well as in the teaching of several other content areas. EDI, itself, overlays with UDL as part of the highly structured and scaffolded approach in direct instruction ( Hollingsworth and Ybarra, 2018 ).

Semantics of General Intelligence ( g ) or Intelligences Affect Student Engagement Conceptualization

The importance of teaching about MI theory from a student engagement perspective has been debated with some scholars suggesting that granular technicalities of quantitative validity studies in the learning styles theories are not always more important than the qualitative influence of such theories in improving instruction ( Shearer, 2004 ). As suggested by some scholars, MI theory has benefits when implemented intentionally and systematically across learner groups from those below grade level to those above grade level ( Milić and Simeunović, 2017 ; Shearer, 2020 ). Gardner (1983) essentially changed the meaning of the word intelligence in the way it was used in his book. According to Shearer (2004) , “It is fundamentally important to recognize that MI [multiple intelligences theory] is a new kind of construct based on a unique definition of intelligence” (p. 3). Shearer (2004) criticized some of the earlier critics of MI theory for a “distorted understanding of the theory itself” (p. 2) and that some critics were misapplying the general intelligence (known as g ) construct by using a different definition than the one Gardner (1983) was using.

The semantics are important as there should be clear definitions so that discussants are speaking from the same understanding of the words used. As Shearer (2004) argued, Gardner was not basing MI theory on the older, extant concept of a singular general intelligence ( g ) but, instead, Gardner was positing a new construct in which a singular general intelligence was deemphasized while positing the concept of MI when using the construct for K-12 teaching and learning. Nevertheless, there need not be a dichotomy between using MI theory and not using it. Instead, in teacher education, there should be nuance in its use in keeping with the complex context of schools with students below, at, and above grade level in the same classroom.

Fostering learning for all students to achieve the learning targets is central to lesson planning, and if MI theory’s implementation achieves that goal, then it is useful for preservice teachers to learn. This was inferred in a study that showed some positive findings of the intelligence domains outside of g , thus providing some tentative support for MI theory ( Visser et al., 2006 ). Even small associations or even inconclusive associations of MI theory can still have qualitatively important outcomes for students. As such, the intelligence quotient (IQ)—influenced by the research on g —has been revised several times with subsequent research, suggesting that the IQ is important but not a static concept ( Kaufman, 2018 ). One view is that transcending dichotomies of using or not using MI theory is necessary, and instead use what works from MI theory on a classroom-by-classroom basis which is part of what MI theory is focused on: choice based on preferences. This still becomes semantically complicated because of what definition of “intelligences” is being used. However, UbD and UDL offer more useful frameworks without the semantic debate. UbD and UDL should be emphasized in educational psychology courses as they will serve as evidence-based frameworks for preservice teachers to learn about lesson planning that is more likely to be effective. UDL has been substantiated in research studies, including a study using an item-level content validity index (I-CVI) that demonstrated how a UDL-based approach in grades 6–12 supported “personalized learning” ( Zhang et al., 2022 ).

Discussion of Teaching Implications

MI theory provides an entry point for discussion of differentiation. However, UbD and UDL should be emphasized and taught in educational psychology for preservice teachers so that these strategies are accessible to demonstrate their usefulness across school contexts in successfully implementing differentiated strategies across content areas and grade levels. Providing preservice teachers with examples is essential. Assigning a lesson plan project in which preservice teachers apply UDL, for example, will help establish understanding and confidence to use this evidence-based approach. In a study of preservice teachers who were taught the UDL framework for lesson planning, Spooner et al. (2007) found that preservice teachers in both special education and general education benefited substantially from just one lesson on UDL. With instruction in UDL with practice, preservice teachers could gain even more benefit in this evidence-based instructional design and likely rely on MI theory.

Multiple studies have provided evidence of MI theory’s semantic effectiveness in inspiring differentiated teaching and learning in the classroom (e.g., Modirkhamene and Azhiri, 2012 ; Milić and Simeunović, 2017 ; Koçak Altundağ, 2018 ; Ghaznavi et al., 2021 ; Shahzada et al., 2021 ). Semantic effectiveness here means that MI theory’s use of the word intelligences seemed to be interpreted as nearly synonymous or at least overlapping with preferences; therefore, its conceptual framing interfaced readily with learning styles theory. As such, qualitative observations tended to provide positive interpretations balancing somewhat ambivalent quantitative findings, depending on the study’s research design. Part of the issue in discussion of findings depends in part on how the word intelligences is used when considering the historically technical term of general intelligence ( g ) with the way in which it is pluralized and adapted in MI theory. Armstrong’s (2018) textbook on MI theory in the classroom further highlights its popularity and, as such, it might be noted in educational psychology courses to preservice teachers from a perspective of a way to think about differentiation. However, UbD and UDL should be taught throughout to emphasize these frameworks’ importance.

Teacher educators should refer to Gardner’s (1983 , 2006) MI theory focusing on its qualitative value for curriculum design to foster student engagement in the content area. This could be a three-step process for the teacher educator: (1) emphasize that MI theory is a way to envision differentiation in designing projects that give students options, while noting the problem of validity when calling preferences “intelligences”; (2) implement activities in which preservice teachers practice project design in their content areas to address preferences when practicable through UbD or UDL; and (3) ask preservice teachers to think of MI theory through the lens of preferences in which each of the eight intelligences are preferences. It should also be noted that just because a student indicates that they prefer to learn a certain way, does not necessarily mean the student learns best that way ( Papadatou-Pastou et al., 2018 ). This process should occur after teaching about the concept of general intelligence ( g ) and validity in psychological science since those concepts relate to standardized tests ( Kane and Brand, 2006 ). Standardized tests are important for determining general intelligence historically as well as for establishing what services may be needed in special education, but are rarely part of the daily instructional side of student engagement as standardized tests tend to rely on the older concept of g . The increasing trend of colleges and universities discontinuing requirements of standardized tests such as the SAT and ACT for admission is an indication of changing perceptions or pressures on the role of a singular, general intelligence measure ( g ) when student eligibility for admission to universities or academic programs is under consideration ( Sternberg, 2020 ; Vigdor and Diaz, 2020 ). Given this trend, MI theory may continue to be relevant in the broader discussion of the role in personalized learning and assessment.

Preservice teachers should be encouraged to learn about student engagement strategies which MI theory provides. MI theory can establish the foundation for engagement with the think-pair-share format of learning and differentiated curriculum design so that students think about the concept of general intelligence and then MI theory’s different approach to intelligence as preferences. In this way, preservice teachers are introduced to the technical aspects of how educational psychologists have defined intelligence while also engaging with MI theory in ways that are practicable for differentiation in the K-12 classroom.

In a unit on learning styles theories in preservice teachers’ educational psychology course, include a lesson on the precision of language and semantics as it relates to MI theory and disciplinary vocabulary. While MI theory is separate from learning styles theory, as it does differ, there is some thematic overlap in conceptual goals between the two ( Silver et al., 1997 ). Engaging preservice teachers in an intentional discussion about the history of MI theory, its influence, and its promising concepts for fostering differentiation can be an integral part of having an informed opinion and understanding of MI theory. Explain the benefits of explicit direct instruction (see Hollingsworth and Ybarra, 2018 ) and its uses in teaching skills and content within UDL and UbD frameworks. Then, assign a project design assignment in which preservice teachers design a UDL or UbD lesson plan. Concurrently assign a lesson plan in which students are tasked with applying eight of the intelligences from MI theory to a differentiated project in their content area. Assign students into groups based on content area and grade level and have them discuss their completed project designs to compare across the frameworks.

This review of the literature on the perceptions of MI theory and the related concept of learning styles theory suggests a continued divergence in observations of MI theory’s efficacy in relation to generalizable validity. Nevertheless, there are studies discussed in in this conceptual analysis that have showed favorable outcomes. Various studies discussed in this conceptual analysis align with findings from Shearer (2020) in the benefits of MI theory observed in those case studies. Some scholars in the literature reviewed also posited questions and points of view in this debate whose discussions should be included in courses on educational psychology for preservice teachers so that they have an informed view of the conceptual background of the theory throughout time. They may likely encounter MI theory or learning styles theory in their schools, so an informed view is important. A discussion of the semantics of the word intelligence with the concept of general intelligence ( g ) and its relationship to IQ should be included for context. The studies critical of MI theory as well as those that have had favorable observations should perhaps both be presented and discussed with preservice teachers, while UbD (see Wiggins and McTighe, 2005 ) and UDL (see Hall et al., 2012 ) should be emphasized as evidence-based frameworks for their K-12 classroom contexts.

Author Contributions

The author confirms being the sole contributor of this work and has approved it for publication.

Conflict of Interest

The author declares that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Publisher’s Note

All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.

• Armstrong T. (2018). Multiple Intelligences in the Classroom (4th Edn). Alexandria, VA: ASCD. [ Google Scholar ]
• Attwood A. I. (2021). An anecdotal case study in psychological anthropology of two retired middle school teachers’ perceptions of classroom life in the United States . Front. Educ. 6 , 1–9. doi: 10.3389/feduc.2021.655457 [ CrossRef ] [ Google Scholar ]
• Baş G., Beyhan Ö. (2010). Effects of multiple intelligences supported project-based learning on students’ achievement levels and attitudes towards English lessons . Int. Electron. J. Elem. Educ. 2 , 366–385. [ Google Scholar ]
• Bordelon D. E., Banbury M. M. (2005). Pursuing the parameters: validating the multiple intelligences inventory for teachers . Assess. Eff. Interv. 30 , 33–51. doi: 10.1177/073724770503000303 [ CrossRef ] [ Google Scholar ]
• Brualdi Timmins A. C. (1996). Multiple intelligences: Gardner’s theory . Pract. Assess. Res. Eval. 5 , 1–3. doi: 10.7275/7251-ea02 [ CrossRef ] [ Google Scholar ]
• Coutinho M. V. C., Thomas J., Alsuwaidi A. S. M., Couchman J. J. (2021). Dunning-Kruger effect: intuitive errors predict overconfidence on the cognitive reflection test . Front. Psychol. 12 :603225. doi: 10.3389/fpsyg.2021.603225, PMID: [ PMC free article ] [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Doecke B., Brown J., Loughran J. (2000). Teacher talk: The role of story and anecdote in constructing professional knowledge for beginning teachers . Teach. Teach. Educ. 16 , 335–348. doi: 10.1016/S0742-051X(99)00065-7 [ CrossRef ] [ Google Scholar ]
• Dolati Z., Tahriri A. (2017). EFL teachers’ multiple intelligences and their classroom practice . SAGE Open 7 , 1–12. doi: 10.1177/2158244017722582 [ CrossRef ] [ Google Scholar ]
• Furnham A. (2009). The validity of a new, self-report measure of multiple intelligence . Curr. Psychol. 28 , 225–239. doi: 10.1007/s12144-009-9064-z [ CrossRef ] [ Google Scholar ]
• Gardner H. (1983). Frames of Mind: The Theory of Multiple Intelligences . New York, NY: Basic Books. [ Google Scholar ]
• Gardner H. (2006). Multiple Intelligences: New Horizons . New York, NY: Basic Books. [ Google Scholar ]
• Gardner H. (2020). “Neuromyths”: a critical consideration . Mind Brain Educ. 14 , 2–4. doi: 10.1111/mbe.12229 [ CrossRef ] [ Google Scholar ]
• Ghaznavi N., Haddad Narafshan M., Tajadini M. (2021). The implementation of a multiple intelligences teaching approach: classroom engagement and physically disabled learners . Cogent Psychol. 8 , 1–20. doi: 10.1080/23311908.2021.1880258 [ CrossRef ] [ Google Scholar ]
• Hall T. E., Meyer A., Rose D. H. (eds.) (2012). Universal design for Learning in the Classroom: Practical Applications . New York, NY: The Guilford Press. [ Google Scholar ]
• Hollingsworth J. R., Ybarra S. E. (2018). Explicit Direct Instruction: The Power of the Well-Crafted, Well-Taught Lesson (2nd Edn). New York, NY: Sage. [ Google Scholar ]
• Hornikx J. (2018). Combining anecdotal and statistical evidence in real-life discourse: comprehension and persuasiveness . Discourse Process. 55 , 324–336. doi: 10.1080/0163853X.2017.1312195 [ CrossRef ] [ Google Scholar ]
• Kane H. D., Brand C. R. (2006). The variable importance of general intelligence (g) in the cognitive abilities of children and adolescents . Educ. Psychol. 26 , 751–767. doi: 10.1080/01443410500390897 [ CrossRef ] [ Google Scholar ]
• Kaufman A. S. (2018). “ Many pathways, one destination: IQ tests, intelligent testing, and the continual push for more equitable assessments ,” in The Nature of Human Intelligence . ed. Sternberg R. J. (Cambridge: Cambridge University Press; ), 197–214. [ Google Scholar ]
• Koçak Altundağ C. (2018). Context-based chemistry teaching within the 4Ex2 model: its impacts on metacognition, multiple intelligence, and achievement . J. Turk. Sci. Educ. 15 , 1–12. doi: 10.12973/tused.10226a [ CrossRef ] [ Google Scholar ]
• Luo M. N., Huang M. (2019). ESL teachers’ multiple intelligences and teaching strategies: is there a linkage? TESOL J. 10 :e00379. doi: 10.1002/tesj.379 [ CrossRef ] [ Google Scholar ]
• McGreal S. A. (2013). The illusory theory of multiple intelligences. Psychology Today . Available at: https://www.psychologytoday.com/us/blog/unique-everybody-else/201311/the-illusory-theory-multiple-intelligences (Accessed February 28, 2022).
• Menz C., Spinath B., Seifried E. (2021). Where do pre-service teachers’ educational psychological misconceptions come from? The roles of anecdotal versus scientific evidence . Zeitschrift für Pädagogische Psychol. [German J. Educ. Psychol.] 35 , 143–156. doi: 10.1024/1010-0652/a000299 [ CrossRef ] [ Google Scholar ]
• Milić S., Simeunović V. (2017). Possibility of identifying the logical-mathematical giftedness with students of lower primary school grades through evaluations . J. Educ. e-Learn. Res. 4 , 154–162. doi: 10.20448/journal.509.2017.44.154.162 [ CrossRef ] [ Google Scholar ]
• Modirkhamene S., Azhiri M. H. B. (2012). The effect of multiple intelligences-based reading tasks on EFL learners reading comprehension . Theory Pract. Lang. Stud. 2 , 1013–1021. doi: 10.4304/tpls.2.5.1013-1021 [ CrossRef ] [ Google Scholar ]
• Mokhtar I. A., Majid S., Foo S. (2008). Teaching information literacy through learning styles: The application of Gardner’s multiple intelligences . J. Librariansh. Inf. Sci. 40 , 93–109. doi: 10.1177/0961000608089345 [ CrossRef ] [ Google Scholar ]
• Multiple Intelligence Schools (2022). Project Zero. Harvard Graduate School of Education. Available at: http://www.pz.harvard.edu/projects/multiple-intelligence-schools (Accessed April 12, 2022).
• Ormrod J. E., Anderman E. M., Anderman L. H. (2020). Educational Psychology: Developing Learners (10th Edn). London: Pearson. [ Google Scholar ]
• Papadatou-Pastou M., Gritzali M., Barrable A. (2018). The learning styles educational neuromyth: lack of agreement between teachers’ judgments, self-assessment, and students’ intelligence . Front. Educ. 3 :105. doi: 10.3389/feduc.2018.00105 [ CrossRef ] [ Google Scholar ]
• Pashler H., McDaniel M., Rohrer D., Bjork R. (2008). Learning styles: concepts and evidence . Psychol. Sci. Public Interest 9 , 105–119. doi: 10.1111/j.1539-6053.2009.01038.x [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Prast E. J., de Weijer-Bergsma E. V., Miočević M., Kroesbergen E. H., Van Luit J. E. H. (2018). Relations between mathematics achievement and motivation in students of diverse achievement levels . Contemp. Educ. Psychol. 55 , 84–96. doi: 10.1016/j.cedpsych.2018.08.002 [ CrossRef ] [ Google Scholar ]
• Rogowsky B. A., Calhoun B. M., Tallal P. (2015). Matching learning style to instructional method: effects on comprehension . J. Educ. Psychol. 107 , 64–78. doi: 10.1037/a0037478 [ CrossRef ] [ Google Scholar ]
• Rousseau L. (2021). “Neuromyths” and multiple intelligences (MI) theory: a comment on Gardner, 2020 . Front. Psychol. 12 :720706. doi: 10.3389/fpsyg.2021.720706, PMID: [ PMC free article ] [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Schulte M. J., Ree M. J., Carretta T. R. (2004). Emotional intelligence: not much more than g and personality . Personal. Individ. Differ. 37 , 1059–1068. doi: 10.1016/j.paid.2003.11.014 [ CrossRef ] [ Google Scholar ]
• Shahzada G., Khan H. N., Muhammad Khan A., Ullah H. (2021). Are students of secondary schools of seven districts different on their self-estimates of multiple intelligences? A case study of southern districts of Khyber Pakhtunkhwa . Front. Educ. 6 :679289. doi: 10.3389/feduc.2021.679289 [ CrossRef ] [ Google Scholar ]
• Shearer B. (2004). Multiple intelligences theory after 20 years . Teach. Coll. Rec. 106 , 2–16. doi: 10.1111/j.1467-9620.2004.00312.x [ CrossRef ] [ Google Scholar ]
• Shearer C. B. (2020). Multiple intelligences in gifted and talented education: lessons learned from neuroscience after 35 years . Roeper Rev. 42 , 49–63. doi: 10.1080/02783193.2019.1690079 [ CrossRef ] [ Google Scholar ]
• Silver H. F., Strong R., Perini M. J. (1997). Integrating learning styles and multiple intelligences . Educational Leadership , 55 , 22–27. [ Google Scholar ]
• Spooner F., Baker J. N., Harris A. A., Ahlgrim-Delzell L., Browder D. M. (2007). Effects of training in universal design for learning on lesson plan development . Remedial Spec. Educ. 28 , 108–116. doi: 10.1177/07419325070280020101 [ CrossRef ] [ Google Scholar ]
• Sternberg R. J. (2020). Rethinking what we mean by intelligence . Phi Delta Kappan 102 , 36–41. doi: 10.1177/0031721720970700 [ CrossRef ] [ Google Scholar ]
• Sternberg R. J., Dennis M. J. (1997). Elaborating cognitive psychology through linkages to psychology as a helping profession . Teach. Psychol. 24 , 246–249. doi: 10.1207/s15328023top2404_3 [ CrossRef ] [ Google Scholar ]
• Stock P. L. (1993). The function of anecdote in teacher research . Engl. Educ. 25 , 173–187. [ Google Scholar ]
• Vaughn-Blount K., Rutherford A., Baker D., Johnson D. (2009). History’s mysteries demystified: Becoming a psychologist–historian . Am. J. Psychol. 122 , 117–129. [ PubMed ] [ Google Scholar ]
• Vigdor N., Diaz J. (2020). More colleges are waiving SAT and ACT requirements. New York Times . Available at: https://www.nytimes.com/article/sat-act-test-optional-colleges-coronavirus.html?smid=url-share (Accessed February 28, 2022).
• Visser B. A., Ashton M. C., Vernon P. A. (2006). Beyond g: putting multiple intelligences theory to the test . Intelligence 34 , 487–502. doi: 10.1016/j.intell.2006.02.004 [ CrossRef ] [ Google Scholar ]
• Waterhouse L. (2006). Multiple intelligences, the Mozart effect, and emotional intelligence: a critical review . Educ. Psychol. 41 , 207–225. doi: 10.1207/s15326985ep4104_1 [ CrossRef ] [ Google Scholar ]
• Weber S. (1993). The narrative anecdote in teacher education . J. Educat. Teach. Int. Res. Pedag. 19 , 71–82. doi: 10.1080/0260747930190107 [ CrossRef ] [ Google Scholar ]
• Wiggins G. P., McTighe J. (2005). Understanding by Design (2nd Edn.). Alexandria, VA: ASCD. [ Google Scholar ]
• Willingham D. T., Hughes E. M., Dobolyi D. G. (2015). The scientific status of learning styles theories . Teach. Psychol. 42 , 266–271. doi: 10.1177/0098628315589505 [ CrossRef ] [ Google Scholar ]
• Wu S., Alrabah S. (2009). A cross-cultural study of Taiwanese and Kuwaiti EFL students’ learning styles and multiple intelligences . Innov. Educ. Teach. Int. 46 , 393–403. doi: 10.1080/14703290903301826 [ CrossRef ] [ Google Scholar ]
• Yidana M. B., Arthur F., Ababio B. T. (2022). Teachers’ application of multiple intelligences approach in teaching economics . Educ. Res. Int. 2022 , 1–16. doi: 10.1155/2022/2875555 [ CrossRef ] [ Google Scholar ]
• Zhang L., Basham J. D., Carter R. A., Jr. (2022). Measuring personalized learning through the Lens of UDL: development and content validation of a student self-report instrument . Stud. Educ. Eval. 72 :101121. doi: 10.1016/j.stueduc.2021.101121 [ CrossRef ] [ Google Scholar ]

How to Use Multiple Intelligences to Study for a Test

• Study Skills
• Test Prep Strategies
• SAT Test Prep
• ACT Test Prep
• GRE Test Prep
• LSAT Test Prep
• Certifications
• Homework Help
• Private School
• College Admissions
• College Life
• Graduate School
• Business School
• Distance Learning

• B.A., English, University of Michigan

Are you one of those people who have a difficult time sitting down to study for a test? Perhaps you get distracted and lose focus easily, or maybe you are just not the type of person who likes learning new information from a book, a lecture, or a presentation. Maybe the reason you dislike studying the way you've been taught to study—sitting in a chair with an open book, reviewing your notes —is because your predominant intelligence has nothing to do with words. The theory of multiple intelligences may just be your best friend when you go to study for a test if traditional study methods aren't quite suiting you. 

The Theory of Multiple Intelligences

The theory of multiple intelligences was developed by Dr. Howard Gardner in 1983. He was a professor of education at Harvard University, and believed that traditional intelligence, where a person's I.Q. or intelligence quotient, did not account for the many brilliant ways in which people are smart. Albert Einstein once said, “Everybody is a genius. But if you judge a fish by its ability to climb a tree, it will live its whole life believing that it is stupid.” 

Instead of a the traditional "one-size-fits-all" approach to intelligence, Dr. Gardner stated that he believed there were eight different intelligences that covered the scope of the brilliance possible in men, women, and children. He believed that people have different intellectual abilities and are more adept in some areas than others. In general, people are able to process information in different ways, using different methods for different things. Here are the eight multiple intelligences according to his theory:

• Verbal-Linguistic Intelligence: "Word Smart"  This type of intelligence refers to a person's ability to analyze information and produce work that involves spoken and written language like speeches, books, and emails. 
• Logical-Mathematical Intelligence:   "Number & Reasoning Smart"  This type of intelligence refers to a person's ability to develop equations and proofs, make calculations, and solve abstract problems that may or may not be related to numbers.
• Visual-Spatial Intelligence: "Picture Smart"  This type of intelligence refers to a person's ability to understand maps and other types of graphical information like charts, tables, diagrams, and pictures. 
• Bodily-Kinesthetic Intelligence: "Body Smart"  This type of intelligence refers to a person's ability to use his or her own body to solve problems, find solutions or create products.
• Musical Intelligence: "Music Smart"  This type of intelligence refers to a person's ability to create and make meaning of different types of sound.
• Interpersonal Intelligence: "People Smart"  This type of intelligence refers to a person's ability to recognize and understand other people's moods, desires, motivations, and intentions.
• Intrapersonal Intelligence: "Self Smart"  This type of intelligence refers to a person's ability to recognize and understand their own moods, desires, motivations, and intentions.
• Naturalistic Intelligence: "Nature Smart" This type of intelligence refers to a person's ability to identify and distinguish among different types of plants, animals, and weather formations found in the natural world.

lt is important to note that you do not have one specific type of intelligence. Everyone has all eight types of intelligences although some types may show up stronger than others. For example, some people approach numbers warily, while others relish the idea of solving complex mathematical problems. Or, one person may quickly and easily learn lyrics and musical notes, but does not excel visually or spatially. Our aptitudes at each of the multiple intelligences can vary widely, but they are all present in each of us. It's important not to label ourselves, or students, as one type of learner with one predominant intelligence because  everyone  can benefit from learning in various ways. 

Using the Theory of Multiple Intelligences to Study 

When you prepare to study, whether that be for a midterm, a final exam , a chapter test or a standardized test like the ACT, SAT, GRE or even the MCAT , it's important to tap into your  many  different intelligences as you take out your notes, study guide or test prep book. Why? Using a variety of methods to take information from the page to your brain can help you remember the info better and longer. Here are a few ways to use several of your multiple intelligences to do just that

Tap Into Your Verbal-Linguistic Intelligence With These Study Tricks

• Write a letter to another person, explaining the mathematical theory you've just learned.
• Read your notes aloud while studying for your science chapter test.
• Ask someone to quiz you after you've read through the study guide for your English literature quiz.
• Quiz via text: text a question to your study partner and read his or her response.
• Download a SAT app that quizzes you daily. 
• Record yourself reading your Spanish notes and then listen to your recording in the car on the way to school. 

Tap Into Your Logical-Mathematical Intelligence With These Study Tricks

• Reorganize your notes from Calculus class using an outline method like the Cornell note-taking system. 
• Compare and contrast different ideas (North vs.South in the Civil War) with one another. 
• List information into particular categories as you read through your notes. For instance, if you're studying grammar, all parts of speech go in one category while all punctuation rules go in another. 
• Predict outcomes that could have happened based on the material you've learned. (What would have happened had Hitler never risen to power?)
• Figure out what was happening in a different part of the world at the same time as what you're studying. (What was happening in Europe during the rise of Genghis Khan?)
• Prove or disprove a theory based on information you've learned throughout the chapter or semester.

Tap Into Your Visual-Spatial Intelligence With These Study Tricks

• Break down information from the text into tables, charts, or graphs.
• Draw a small picture next to each item in a list you need to remember. This is helpful when you have to remember lists of names, because you can draw a likeness next to each person.
• Use highlighters or special symbols related to similar ideas in the text. For instance, anything related to Plains Native Americans gets highlighted yellow, and anything related to Northeast Woodlands Native Americans gets highlighted blue, etc.
• Rewrite your notes using an app that allows you to add pictures. 
• Ask your teacher if you can take pictures of the science experiment as you go so you remember what happened. 

Tap Into Your Bodily-Kinesthetic Intelligence With These Study Tricks

• Act out a scene from a play or do the "extra" science experiment in the back of the chapter.
• Rewrite your lecture notes with pencil instead of typing them out. The physical act of writing will help you remember more.
• As you study, do a physical activity. Shoot hoops while someone quizzes you. Or, jump rope. 
• Use manipulatives to solve math problems whenever possible. 
• Build or craft models of items you need to remember or visit physical spaces to cement the idea in your head. You'll remember the bones of the body much better if you touch each part of your body as you learn them, for instance. 

Tap Into Your Musical Intelligence With These   Study Tricks

• Set a long list or chart to a favorite tune. For example, if you have to learn the periodic table of elements, try setting the names of the elements to "The Wheels on the Bus" or "Twinkle, Twinkle Little Star."
• If you have particularly tough words to remember, try saying their names with different pitches and volumes. 
• Have a long list of poets to remember? Assign a noise (a clap, a wrinkled paper, a stomp) to each. 
• Play lyric-free music when you study so the lyrics don't compete for brain space. 

Multiple Intelligences Vs. Learning Style

The theory that you have many ways of being intelligent is different from Neil Fleming's VAK theory of learning styles. Fleming states that there were three (or four, depending on which theory is used) dominant learning styles: Visual, Auditory and Kinesthetic. Check out this learning styles quiz to see which one of those learning styles you tend to use most!

• What's Your Learning Language?
• Smart Study Strategies for Different Intelligence Types
• Multiple Intelligences in the ESL Classroom
• Understanding Howard Gardner's Theory of Multiple Intelligence
• Multiple Intelligence Activities
• Understanding the Meaning of Bodily-Kinesthetic Intelligence
• Teaching Students Who Have Musical Intelligence
• Teaching Students Who Have a Naturalist Intelligence
• How to Analyze Problems Using Logical Mathematical Intelligence
• Linguistic Intelligence
• Spatial Intelligence
• The 6 Most Important Theories of Teaching
• Collection of Learning Styles Tests and Inventories
• 6 Study Tips for Visual Learners
• How to Study for a Multiple Choice Exam
• The Visual Learning Style

Academia.edu no longer supports Internet Explorer.

To browse Academia.edu and the wider internet faster and more securely, please take a few seconds to  upgrade your browser .

Enter the email address you signed up with and we'll email you a reset link.

• We're Hiring!
• Help Center

Case Study: Multiple Intelligences in Leadership

2019, ProQuest

Multiple intelligence theory presents an overlap of trait and behavioral theory in the discussion of leadership. Gardner pioneered the multiple intelligence theory, including linguistic intelligence, musical intelligence, logic-mathematical intelligence, spatial intelligence, bodily-kinesthetic intelligence, interpersonal intelligence, and intrapersonal intelligence. Although scholars have focused on the differing categories of intelligence, little work has been conducted on using the categories of intelligence in leadership. To address this gap in the literature, a qualitative instrumental case study was conducted to answer the following research question: How and why are leaders using multiple intelligences in leadership? Based on the literature, the categories of intelligence for the study included linguistic intelligence, logic-mathematical intelligence, emotional intelligence, knowledge intelligence, temporal intelligence, cultural intelligence, and spiritual intelligence. The sample included 3 highly influential leaders of megachurch and para-church ministries who influenced over 2,000 individuals utilizing purposeful sampling. Interviews included 1 for the leader, 1 for the follower, and 1 for the leader and follower. The literature determined the in-depth questions and follow-up questions, which explored the “how” and “why” behind respondent answers. To ensure validation and credibility, the analysis employed data saturation through triangulation. The study resulted in all 3 leaders using all 7 intelligences. Multiple coding in data analysis revealed 3 themes under “how” and 3 themes under “why” leaders utilized multiple intelligences in their leadership.

Related Papers

Paola Bortini , Irene Rojnik , Daria Marani Toro , Deirdre quinlan

The paper explores the process and finding of a 2 years project aiming at looking at how the use of the Multiple Intelligences as defined by Gardner and other researchers can support Leadership Development. Leadership is seen as process of authenticity and the Multiple Intelligences support the process of Leaders of "getting rid” of predefined techniques to use in order to be successful for exploring what is inherent to the person, her/his talents and resources and how this can be used in Leadership, thus becoming more authentic and effective. The paper provides a series of experiences/activities and the results of a year long testing phase where the experiences/activities suggested have been tested. It targets leaders as well as adult education providers.

Journal of Cooperative Education

Anna Dåderman

A new Swedish leadership theory of "leadership intelligence" (Ronthy, 2006; 2013) is characterized by a work integrated learning approach. This theory arose from analysis of the experiences of managers trained in performance appraisals, and describes the balance between being a leader and being a manager. A leader develops and uses, in an integrative good balance, leadership intelligence, which comprises emotional intelligence, rational intelligence and spiritual intelligence. The aim of this study was to further develop the Leadership Intelligence Questionnaire (LIQ) created by Ronthy (which has been developed to measure leadership intelligence), and to examine its reliability. Over 400 leaders, aged 21 to 69 years completed the 71-item LIQ. A shorter, 32-item version of the LIQ was developed by confirmatory factor analysis thorough excluding psychometrically "poor" items. The internal consistency measured by Cronbach’s alpha was high (> .80), and we conclude...

Journal of Public Affairs

Boshra A Arnout

Spiritual intelligence has received increasing quantitative research interest, while there is still no attention regarding to investigate spiritual intelligence with applying qualitative methods, especially grounded theory design. This study aimed to detect the skills, affecting factors, and the effects of spiritual intelligence and religiousness on performance. The qualitative analysis of the data collected through the in-depth interview of the participants after encoding and classification, and the continuous comparison of the data by encoding and data by axes, resulted in these data can be coded in three axes: leader's spiritual intelligence skills, factors that affect leader's spiritual intelligence, and the effects of leader's spiritual intelligence on performance. The results revealed that there are five skills of leader's spiritual intelligence: work-life balance skill, consists of (5) sub-skills, leadership transcendence skill includes (6) sub-skills, leadership meaning and purpose production skill includes (4) sub-skills, leadership mindfulness skill consists of (9) sub-skills, and the fifth skill is leadership virtue behavior includes (8) sub-skills. And also, the results indicated that there are many factors that impact the leader's spiritual intelligence, were classified into three objects: personal (three factors), social and family (two factors), and work factors (4 factors). All participants were agreed unanimously that the leader's spiritual intelligence and religiousness are determined and affect the performance of the leader and his subordinates, these were classified into two objects: The first object is a leader's work-performance, consisting of (16) indicators, and the second object is a workers performance includes (12) indicators. In light of these results, the study recommended the necessity of developing leaders' awareness of the importance of passion of spiritual intelligence skill and their impacts on performance. Thus, these findings shed new light on the importance of developing leaders' spiritual intelligence skills to resolve leadership problems, and increasing productivity, creativity, and well-being among leaders and workers in Arab World.

Leader To Leader

Atina Bilqis

PEOPLE: International Journal of Social Sciences

Dr Christa Bonnet

Zanna Zhang

Meta-analysis was used to aggregate results from studies examining the relationship between intelligence and leadership. One hundred fifty-one independent samples in 96 sources met the criteria for inclusion in the meta-analysis. Results indicated that the corrected correlation between intelligence and leadership is .21 (uncorrected for range restriction) and .27 (corrected for range restriction). Perceptual measures of intelligence showed stronger correlations with leadership than did paper-and-pencil measures of intelligence. Intelligence correlated equally well with objective and perceptual measures of leadership. Additionally, the leader's stress level and the leader's directiveness moderated the intelligence– leadership relationship. Overall, results suggest that the relationship between intelligence and leadership is considerably lower than previously thought. The results also provide meta-analytic support for both implicit leadership theory and cognitive resource theory.

Journal of School Leadership

Wanda Green

George Kunnath

The homocentric nature of our developmental paradigms alienates us from self and others. Over-emphasis on cognitive dimensions of life has resulted in skewed development focus. Restoring the equilibrium calls for the integration of multiple intelligences. In the cosmos centric paradigm, the key to transformation is in the inner journey of the leader. Attributes of a spiritually intelligent leader are outlined as the Warrior’s Way. The transformation of the leader stems from the convergence of the analytical, emotional and spiritual intelligences.

Leader to Leader

Clint Sidle

RELATED TOPICS

•   We're Hiring!
•   Help Center
• Find new research papers in:
• Health Sciences
• Earth Sciences
• Cognitive Science
• Mathematics
• Computer Science
• Academia ©2024

• Open access
• Published: 22 April 2024

Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study

• Kannan Sridharan 1 &
• Reginald P. Sequeira 1  

BMC Medical Education volume  24 , Article number:  431 ( 2024 ) Cite this article

2 Altmetric

Metrics details

Artificial intelligence (AI) tools are designed to create or generate content from their trained parameters using an online conversational interface. AI has opened new avenues in redefining the role boundaries of teachers and learners and has the potential to impact the teaching-learning process.

In this descriptive proof-of- concept cross-sectional study we have explored the application of three generative AI tools on drug treatment of hypertension theme to generate: (1) specific learning outcomes (SLOs); (2) test items (MCQs- A type and case cluster; SAQs; OSPE); (3) test standard-setting parameters for medical students.

Analysis of AI-generated output showed profound homology but divergence in quality and responsiveness to refining search queries. The SLOs identified key domains of antihypertensive pharmacology and therapeutics relevant to stages of the medical program, stated with appropriate action verbs as per Bloom’s taxonomy. Test items often had clinical vignettes aligned with the key domain stated in search queries. Some test items related to A-type MCQs had construction defects, multiple correct answers, and dubious appropriateness to the learner’s stage. ChatGPT generated explanations for test items, this enhancing usefulness to support self-study by learners. Integrated case-cluster items had focused clinical case description vignettes, integration across disciplines, and targeted higher levels of competencies. The response of AI tools on standard-setting varied. Individual questions for each SAQ clinical scenario were mostly open-ended. The AI-generated OSPE test items were appropriate for the learner’s stage and identified relevant pharmacotherapeutic issues. The model answers supplied for both SAQs and OSPEs can aid course instructors in planning classroom lessons, identifying suitable instructional methods, establishing rubrics for grading, and for learners as a study guide. Key lessons learnt for improving AI-generated test item quality are outlined.

Conclusions

AI tools are useful adjuncts to plan instructional methods, identify themes for test blueprinting, generate test items, and guide test standard-setting appropriate to learners’ stage in the medical program. However, experts need to review the content validity of AI-generated output. We expect AIs to influence the medical education landscape to empower learners, and to align competencies with curriculum implementation. AI literacy is an essential competency for health professionals.

Peer Review reports

Artificial intelligence (AI) has great potential to revolutionize the field of medical education from curricular conception to assessment [ 1 ]. AIs used in medical education are mostly generative AI large language models that were developed and validated based on billions to trillions of parameters [ 2 ]. AIs hold promise in the incorporation of history-taking, assessment, diagnosis, and management of various disorders [ 3 ]. While applications of AIs in undergraduate medical training are being explored, huge ethical challenges remain in terms of data collection, maintaining anonymity, consent, and ownership of the provided data [ 4 ]. AIs hold a promising role amongst learners because they can deliver a personalized learning experience by tracking their progress and providing real-time feedback, thereby enhancing their understanding in the areas they are finding difficult [ 5 ]. Consequently, a recent survey has shown that medical students have expressed their interest in acquiring competencies related to the use of AIs in healthcare during their undergraduate medical training [ 6 ].

Pharmacology and Therapeutics (P & T) is a core discipline embedded in the undergraduate medical curriculum, mostly in the pre-clerkship phase. However, the application of therapeutic principles forms one of the key learning objectives during the clerkship phase of the undergraduate medical career. Student assessment in pharmacology & therapeutics (P&T) is with test items such as multiple-choice questions (MCQs), integrated case cluster questions, short answer questions (SAQs), and objective structured practical examination (OSPE) in the undergraduate medical curriculum. It has been argued that AIs possess the ability to communicate an idea more creatively than humans [ 7 ]. It is imperative that with access to billions of trillions of datasets the AI platforms hold promise in playing a crucial role in the conception of various test items related to any of the disciplines in the undergraduate medical curriculum. Additionally, AIs provide an optimized curriculum for a program/course/topic addressing multidimensional problems [ 8 ], although robust evidence for this claim is lacking.

The existing literature has evaluated the knowledge, attitude, and perceptions of adopting AI in medical education. Integration of AIs in medical education is the need of the hour in all health professional education. However, the academic medical fraternity facing challenges in the incorporation of AIs in the medical curriculum due to factors such as inadequate grounding in data analytics, lack of high-quality firm evidence favoring the utility of AIs in medical education, and lack of funding [ 9 ]. Open-access AI platforms are available free to users without any restrictions. Hence, as a proof-of-concept, we chose to explore the utility of three AI platforms to identify specific learning objectives (SLOs) related to pharmacology discipline in the management of hypertension for medical students at different stages of their medical training.

Study design and ethics

The present study is observational, cross-sectional in design, conducted in the Department of Pharmacology & Therapeutics, College of Medicine and Medical Sciences, Arabian Gulf University, Kingdom of Bahrain, between April and August 2023. Ethical Committee approval was not sought given the nature of this study that neither had any interaction with humans, nor collection of any personal data was involved.

Study procedure

We conducted the present study in May-June 2023 with the Poe© chatbot interface created by Quora© that provides access to the following three AI platforms:

Sage Poe [ 10 ]: A generative AI search engine developed by Anthropic © that conceives a response based on the written input provided. Quora has renamed Sage Poe as Assistant © from July 2023 onwards.

Claude-Instant [ 11 ]: A retrieval-based AI search engine developed by Anthropic © that collates a response based on pre-written responses amongst the existing databases.

ChatGPT version 3.5 [ 12 ]: A generative architecture-based AI search engine developed by OpenAI © trained on large and diverse datasets.

We queried the chatbots to generate SLOs, A-type MCQs, integrated case cluster MCQs, integrated SAQs, and OSPE test items in the domain of systemic hypertension related to the P&T discipline. Separate prompts were used to generate outputs for pre-clerkship (preclinical) phase students, and at the time of graduation (before starting residency programs). Additionally, we have also evaluated the ability of these AI platforms to estimate the proportion of students correctly answering these test items. We used the following queries for each of these objectives:

Specific learning objectives

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

A-type MCQs

In the initial query used for A-type of item, we specified the domains (such as the mechanism of action, pharmacokinetics, adverse reactions, and indications) so that a sample of test items generated without any theme-related clutter, shown below:

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase of which 5 MCQs should be related to mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

The MCQs generated with the above search query were not based on clinical vignettes. We queried again to generate MCQs using clinical vignettes specifically because most medical schools have adopted problem-based learning (PBL) in their medical curriculum.

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase using a clinical vignette for each MCQ of which 5 MCQs should be related to the mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

We attempted to explore whether AI platforms can provide useful guidance on standard-setting. Hence, we used the following search query.

Can you do a simulation with 100 undergraduate medical students to take the above questions and let me know what percentage of students got each MCQ correct?

Integrated case cluster MCQs

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette. Please do not include ‘none of the above’ as the choice. (This modified search query was used because test items with ‘None of the above’ option were generated with the previous search query).

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students at the time of graduation integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Integrated short answer questions

Write a short answer question scenario with difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with moderately difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students at the time of graduation with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Both authors independently evaluated the AI-generated outputs, and a consensus was reached. We cross-checked the veracity of answers suggested by AIs as per the Joint National Commission Guidelines (JNC-8) and Goodman and Gilman’s The Pharmacological Basis of Therapeutics (2023), a reference textbook [ 13 , 14 ]. Errors in the A-type MCQs were categorized as item construction defects, multiple correct answers, and uncertain appropriateness to the learner’s level. Test items in the integrated case cluster MCQs, SAQs and OSPEs were evaluated with the Preliminary Conceptual Framework for Establishing Content Validity of AI-Generated Test Items based on the following domains: technical accuracy, comprehensiveness, education level, and lack of construction defects (Table  1 ). The responses were categorized as complete and deficient for each domain.

The pre-clerkship phase SLOs identified by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials 1 – 3 , respectively. In general, a broad homology in SLOs generated by the three AI platforms was observed. All AI platforms identified appropriate action verbs as per Bloom’s taxonomy to state the SLO; action verbs such as describe, explain, recognize, discuss, identify, recommend, and interpret are used to state the learning outcome. The specific, measurable, achievable, relevant, time-bound (SMART) SLOs generated by each AI platform slightly varied. All key domains of antihypertensive pharmacology to be achieved during the pre-clerkship (pre-clinical) years were relevant for graduating doctors. The SLOs addressed current JNC Treatment Guidelines recommended classes of antihypertensive drugs, the mechanism of action, pharmacokinetics, adverse effects, indications/contraindications, dosage adjustments, monitoring therapy, and principles of monotherapy and combination therapy.

The SLOs to be achieved by undergraduate medical students at the time of graduation identified by Sage Poe, Claude-Instant, and ChatGPT listed in electronic supplementary materials 4 – 6 , respectively. The identified SLOs emphasize the application of pharmacology knowledge within a clinical context, focusing on competencies needed to function independently in early residency stages. These SLOs go beyond knowledge recall and mechanisms of action to encompass competencies related to clinical problem-solving, rational prescribing, and holistic patient management. The SLOs generated require higher cognitive ability of the learner: action verbs such as demonstrate, apply, evaluate, analyze, develop, justify, recommend, interpret, manage, adjust, educate, refer, design, initiate & titrate were frequently used.

The MCQs for the pre-clerkship phase identified by Sage Poe, Claude-Instant, and ChatGPT listed in the electronic supplementary materials 7 – 9 , respectively, and those identified with the search query based on the clinical vignette in electronic supplementary materials ( 10 – 12 ).

All MCQs generated by the AIs in each of the four domains specified [mechanism of action (MOA); pharmacokinetics; adverse drug reactions (ADRs), and indications for antihypertensive drugs] are quality test items with potential content validity. The test items on MOA generated by Sage Poe included themes such as renin-angiotensin-aldosterone (RAAS) system, beta-adrenergic blockers (BB), calcium channel blockers (CCB), potassium channel openers, and centrally acting antihypertensives; on pharmacokinetics included high oral bioavailability/metabolism in liver [angiotensin receptor blocker (ARB)-losartan], long half-life and renal elimination [angiotensin converting enzyme inhibitors (ACEI)-lisinopril], metabolism by both liver and kidney (beta-blocker (BB)-metoprolol], rapid onset- short duration of action (direct vasodilator-hydralazine), and long-acting transdermal drug delivery (centrally acting-clonidine). Regarding the ADR theme, dry cough, angioedema, and hyperkalemia by ACEIs in susceptible patients, reflex tachycardia by CCB/amlodipine, and orthostatic hypotension by CCB/verapamil addressed. Clinical indications included the drug of choice for hypertensive patients with concomitant comorbidity such as diabetics (ACEI-lisinopril), heart failure and low ejection fraction (BB-carvedilol), hypertensive urgency/emergency (alpha cum beta receptor blocker-labetalol), stroke in patients with history recurrent stroke or transient ischemic attack (ARB-losartan), and preeclampsia (methyldopa).

Almost similar themes under each domain were identified by the Claude-Instant AI platform with few notable exceptions: hydrochlorothiazide (instead of clonidine) in MOA and pharmacokinetics domains, respectively; under the ADR domain ankle edema/ amlodipine, sexual dysfunction and fatigue in male due to alpha-1 receptor blocker; under clinical indications the best initial monotherapy for clinical scenarios such as a 55-year old male with Stage-2 hypertension; a 75-year-old man Stage 1 hypertension; a 35-year-old man with Stage I hypertension working on night shifts; and a 40-year-old man with stage 1 hypertension and hyperlipidemia.

As with Claude-Instant AI, ChatGPT-generated test items on MOA were mostly similar. However, under the pharmacokinetic domain, immediate- and extended-release metoprolol, the effect of food to enhance the oral bioavailability of ramipril, and the highest oral bioavailability of amlodipine compared to other commonly used antihypertensives were the themes identified. Whereas the other ADR themes remained similar, constipation due to verapamil was a new theme addressed. Notably, in this test item, amlodipine was an option that increased the difficulty of this test item because amlodipine therapy is also associated with constipation, albeit to a lesser extent, compared to verapamil. In the clinical indication domain, the case description asking “most commonly used in the treatment of hypertension and heart failure” is controversial because the options listed included losartan, ramipril, and hydrochlorothiazide but the suggested correct answer was ramipril. This is a good example to stress the importance of vetting the AI-generated MCQ by experts for content validity and to assure robust psychometrics. The MCQ on the most used drug in the treatment of “hypertension and diabetic nephropathy” is more explicit as opposed to “hypertension and diabetes” by Claude-Instant because the therapeutic concept of reducing or delaying nephropathy must be distinguished from prevention of nephropathy, although either an ACEI or ARB is the drug of choice for both indications.

It is important to align student assessment to the curriculum; in the PBL curriculum, MCQs with a clinical vignette are preferred. The modification of the query specifying the search to generate MCQs with a clinical vignette on domains specified previously gave appropriate output by all three AI platforms evaluated (Sage Poe; Claude- Instant; Chat GPT). The scenarios generated had a good clinical fidelity and educational fit for the pre-clerkship student perspective.

The errors observed with AI outputs on the A-type MCQs are summarized in Table  2 . No significant pattern was observed except that Claude-Instant© generated test items in a stereotyped format such as the same choices for all test items related to pharmacokinetics and indications, and all the test items in the ADR domain are linked to the mechanisms of action of drugs. This illustrates the importance of reviewing AI-generated test items by content experts for content validity to ensure alignment with evidence-based medicine and up-to-date treatment guidelines.

The test items generated by ChatGPT had the advantage of explanations supplied rendering these more useful for learners to support self-study. The following examples illustrate this assertion: “ A patient with hypertension is started on a medication that works by blocking beta-1 receptors in the heart (metoprolol)”. Metoprolol is a beta blocker that works by blocking beta-1 receptors in the heart, which reduces heart rate and cardiac output, resulting in a decrease in blood pressure. However, this explanation is incomplete because there is no mention of other less important mechanisms, of beta receptor blockers on renin release. Also, these MCQs were mostly recall type: Which of the following medications is known to have a significant first-pass effect? The explanation reads: propranolol is known to have a significant first pass-effect, meaning that a large portion of the drug is metabolized by the liver before it reaches systemic circulation. Losartan, amlodipine, ramipril, and hydrochlorothiazide do not have significant first-pass effect. However, it is also important to extend the explanation further by stating that the first-pass effect of propranolol does not lead to total loss of pharmacological activity because the metabolite hydroxy propranolol also has potent beta-blocking activity. Another MCQ test item had a construction defect: “A patient with hypertension is started on a medication that can cause photosensitivity. Which of the following medications is most likely responsible?” Options included: losartan, amlodipine, ramipril, hydrochlorothiazide, hydrochlorothiazide/triamterene. The explanation states that hydrochlorothiazide (HCTZ) can cause photosensitivity, which is increased sensitivity to sunlight that can cause skin rashes and sunburns. Losartan, amlodipine, ramipril, and HCTZ/triamterene are less likely to cause photosensitivity. However, it is irrational to claim that HCTZ/triamterene, one of the wrong options, is less likely to cause photosensitivity. The difficulty index of such test items is likely unacceptable in high-stake tests to make equitable psychometric decisions.

The responses from Sage Poe, Claude-Instant, and ChatGPT on guidance for standard-setting methods are listed in the electronic supplementary materials 13 – 15 . Sage Poe offered this information with the caveat that “the results of this simulation were purely hypothetical and do not reflect the actual performance of any real students”. The simulation estimates of examinees correctly answering test items ranged from 60 to 90% for the mechanism of action, 65–85% for pharmacokinetics, 60–80% for adverse reactions, and 75–90% for clinical indications of antihypertensives.

In contrast, Claude-Instant admitted that “Performing a full simulation with 100 medical students is beyond the scope of what I can do as an AI assistant. I can generate sample MCQ questions and answers, but I do not have access to a population of medical students to administer the questions. A true simulation that administers questions to real students and analyzes the results would require access to a database of medical students, a platform to deliver the questions, and code to analyze the responses. As an AI assistant, I lack these capabilities. While I cannot perform a full simulation, here are some considerations for administering MCQ questions to medical students: provide details on the purpose and instructions for the test to ensure students understand what is expected out of them; consider including some easier questions in addition to more challenging ones to boost students’ confidence and motivation; avoid ambiguous wording and ensure each question has only one unambiguously correct answer option; when analyzing results, look for questions factors that may have impacted performance, like unclear wording or answer options that are too similar. Focusing on weak questions can help improve future tests; compare performance across different student groups to identify areas where more teaching may be needed; provide detailed answer explanations and review sessions after the test to help students learn from any errors and reinforce correct concepts”. However, ChatGPT offered the simulation result estimates for the 20 MCQ on antihypertensive drugs: mechanism of action ranged from 67 to 92%, pharmacokinetics 63–86%, adverse effects 65–82%, and clinical indications 64–89%. Furthermore, it also stated that “Overall, the performance of the students was quite good, with most questions having a response rate of over 70%. However, there were some questions where the projected correct response rate was rather low, such as Question #5 (Mechanism of Action of Hydrochlorothiazide; see Electronic Supplementary Material 12 ) and Question 18 (Indications for Verapamil; see Electronic Supplementary Material 10 ). This may suggest areas where students need more focused education or review.”

We asked AI assistants to generate 20 integrated case cluster MCQs with 2 test items in each cluster with five options for undergraduate medical students in the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette and the responses by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials ( 16 – 18 ). In all instances, the test items generated had focused case descriptions in the form of a clinical vignette, and horizontal integration across the pathophysiology of hypertension and pharmacology of antihypertensive drugs. These test items mostly targeted the ‘knows (knowledge)’ or ‘knows how (competence)’ level on Miller’s pyramid and are suitable for assessing the clinical competence of pre-clerkship medical students, especially in an integrated PBL curriculum. Both the AI assistants generated excellent clinical vignettes and themes; however, most of the cluster MCQs by ChatGPT had “None of the above” as an option, which is often considered a test item construction flaw. Notwithstanding these limitations, case cluster integrated test items are valuable for learners to integrate their knowledge of different basic medical sciences and their application to clinical sciences. This integrated approach can be used for both instructional and student assessment purposes to make the course more meaningful. Indeed, one of the basic tenets of PBL is curriculum integration.

In the next query, we asked AI assistants to write integrated case cluster MCQs with 2 test items in each cluster with 5 options for undergraduate medical students at the time of graduation integrating pharmacology and physiology of hypertension with a case vignette. The responses are listed in the electronic supplementary materials 19 – 21 . Claude-Instant has provided only partial responses to both the queries. Overall, the information provided in case vignettes requires the learner to interpret the clinical information and make therapeutic decisions. Such test items are appropriate for assessing the minimum competency of medical school graduates to start internship or residency programs; these MCQs are generally comparable to test items used in USMLE Part 2. The evaluation of the integrated case cluster test items provided by all the AI platforms is summarized in Table  3 . In general, the AI outputs had at least one construction defect, and did not include all the core sub-topics to a sufficient degree.

When asked to simulate the above-generated test items to 100 undergraduate medical students at the time of graduation and provide a percentage of students who are likely to correctly answer each item, the AI assistant responded:

“ As an AI language model, I cannot simulate the responses of 100 undergraduate medical students likely to obtain the correct answer for each question. However, I can provide some general information about the difficulty level of each question based on the complexity of the concepts being tested and the level of integration between pharmacology and physiology ”.

AI assistant went on to clarify that questions that require knowledge of basic pharmacology principles, such as the mechanism of action of specific drugs, are likely to be easier for students to answer correctly. Test items that require an understanding of the physiological mechanisms underlying hypertension and correlating with symptoms are likely to be more challenging for students. The AI assistant sorted these test items into two categories accordingly. Overall, the difficulty level of the test item is based on the level of integration between pharmacology and pathophysiology. Test items that require an understanding of both pharmacological and physiological mechanisms are likely to be more challenging for students requiring a strong foundation in both pharmacology and physiology concepts to be able to correctly answer integrated case-cluster MCQs.

Short answer questions

The responses to a search query on generating SAQs appropriate to the pre-clerkship phase Sage Poe, Claude-Instant, and ChatGPT generated items are listed in the electronic supplementary materials 22 – 24 for difficult questions and 25–27 for moderately difficult questions.

It is apparent from these case vignette descriptions that the short answer question format varied. Accordingly, the scope for asking individual questions for each scenario is open-ended. In all instances, model answers are supplied which are helpful for the course instructor to plan classroom lessons, identify appropriate instructional methods, and establish rubrics for grading the answer scripts, and as a study guide for students.

We then wanted to see to what extent AI can differentiate the difficulty of the SAQ by replacing the search term “difficult” with “moderately difficult” in the above search prompt: the changes in the revised case scenarios are substantial. Perhaps the context of learning and practice (and the level of the student in the MD/medical program) may determine the difficulty level of SAQ generated. It is worth noting that on changing the search from cardiology to internal medicine rotation in Sage Poe the case description also changed. Thus, it is essential to select an appropriate AI assistant, perhaps by trial and error, to generate quality SAQs. Most of the individual questions tested stand-alone knowledge and did not require students to demonstrate integration.

The responses of Sage Poe, Claude-Instant, and ChatGPT for the search query to generate SAQs at the time of graduation are listed in the electronic supplementary materials 28 – 30 . It is interesting to note how AI assistants considered the stage of the learner while generating the SAQ. The response by Sage Poe is illustrative for comparison. “You are a newly graduated medical student who is working in a hospital” versus “You are a medical student in your pre-clerkship.”

Some questions were retained, deleted, or modified to align with competency appropriate to the context (Electronic Supplementary Materials 28 – 30 ). Overall, the test items at both levels from all AI platforms were technically accurate and thorough addressing the topics related to different disciplines (Table  3 ). The differences in learning objective transition are summarized in Table  4 . A comparison of learning objectives revealed that almost all objectives remained the same except for a few (Table  5 ).

A similar trend was apparent with test items generated by other AI assistants, such as ChatGPT. The contrasting differences in questions are illustrated by the vertical integration of basic sciences and clinical sciences (Table  6 ).

Taken together, these in-depth qualitative comparisons suggest that AI assistants such as Sage Poe and ChatGPT consider the learner’s stage of training in designing test items, learning outcomes, and answers expected from the examinee. It is critical to state the search query explicitly to generate quality output by AI assistants.

The OSPE test items generated by Claude-Instant and ChatGPT appropriate to the pre-clerkship phase (without mentioning “appropriate instructions for the patients”) are listed in the electronic supplementary materials 31 and 32 and with patient instructions on the electronic supplementary materials 33 and 34 . For reasons unknown, Sage Poe did not provide any response to this search query.

The five OSPE items generated were suitable to assess the prescription writing competency of pre-clerkship medical students. The clinical scenarios identified by the three AI platforms were comparable; these scenarios include patients with hypertension and impaired glucose tolerance in a 65-year-old male, hypertension with chronic kidney disease (CKD) in a 55-year-old woman, resistant hypertension with obstructive sleep apnea in a 45-year-old man, and gestational hypertension at 32 weeks in a 35-year-old (Claude-Instant AI). Incorporating appropriate instructions facilitates the learner’s ability to educate patients and maximize safe and effective therapy. The OSPE item required students to write a prescription with guidance to start conservatively, choose an appropriate antihypertensive drug class (drug) based on the patients’ profile, specifying drug name, dose, dosing frequency, drug quantity to be dispensed, patient name, date, refill, and caution as appropriate, in addition to prescribers’ name, signature, and license number. In contrast, ChatGPT identified clinical scenarios to include patients with hypertension and CKD, hypertension and bronchial asthma, gestational diabetes, hypertension and heart failure, and hypertension and gout (ChatGPT). Guidance for dosage titration, warnings to be aware, safety monitoring, and frequency of follow-up and dose adjustment. These test items are designed to assess learners’ knowledge of P & T of antihypertensives, as well as their ability to provide appropriate instructions to patients. These clinical scenarios for writing prescriptions assess students’ ability to choose an appropriate drug class, write prescriptions with proper labeling and dosing, reflect drug safety profiles, and risk factors, and make modifications to meet the requirements of special populations. The prescription is required to state the drug name, dose, dosing frequency, patient name, date, refills, and cautions or instructions as needed. A conservative starting dose, once or twice daily dosing frequency based on the drug, and instructions to titrate the dose slowly if required.

The responses from Claude-Instant and ChatGPT for the search query related to generating OSPE test items at the time of graduation are listed in electronic supplementary materials 35 and 36 . In contrast to the pre-clerkship phase, OSPEs generated for graduating doctors’ competence assessed more advanced drug therapy comprehension. For example, writing a prescription for:

(1) A 65-year- old male with resistant hypertension and CKD stage 3 to optimize antihypertensive regimen required the answer to include starting ACEI and diuretic, titrating the dosage over two weeks, considering adding spironolactone or substituting ACEI with an ARB, and need to closely monitor serum electrolytes and kidney function closely.

(2) A 55-year-old woman with hypertension and paroxysmal arrhythmia required the answer to include switching ACEI to ARB due to cough, adding a CCB or beta blocker for rate control needs, and adjusting the dosage slowly and monitoring for side effects.

(3) A 45-year-old man with masked hypertension and obstructive sleep apnea require adding a centrally acting antihypertensive at bedtime and increasing dosage as needed based on home blood pressure monitoring and refer to CPAP if not already using one.

(4) A 75-year-old woman with isolated systolic hypertension and autonomic dysfunction to require stopping diuretic and switching to an alpha blocker, upward dosage adjustment and combining with other antihypertensives as needed based on postural blood pressure changes and symptoms.

(5) A 35-year-old pregnant woman with preeclampsia at 29 weeks require doubling methyldopa dose and consider adding labetalol or nifedipine based on severity and educate on signs of worsening and to follow-up immediately for any concerning symptoms.

These case scenarios are designed to assess the ability of the learner to comprehend the complexity of antihypertensive regimens, make evidence-based regimen adjustments, prescribe multidrug combinations based on therapeutic response and tolerability, monitor complex patients for complications, and educate patients about warning signs and follow-up.

A similar output was provided by ChatGPT, with clinical scenarios such as prescribing for patients with hypertension and myocardial infarction; hypertension and chronic obstructive pulmonary airway disease (COPD); hypertension and a history of angina; hypertension and a history of stroke, and hypertension and advanced renal failure. In these cases, wherever appropriate, pharmacotherapeutic issues like taking ramipril after food to reduce side effects such as giddiness; selection of the most appropriate beta-blocker such as nebivolol in patients with COPD comorbidity; the importance of taking amlodipine at the same time every day with or without food; preference for telmisartan among other ARBs in stroke; choosing furosemide in patients with hypertension and edema and taking the medication with food to reduce the risk of gastrointestinal adverse effect are stressed.

The AI outputs on OSPE test times were observed to be technically accurate, thorough in addressing core sub-topics suitable for the learner’s level and did not have any construction defects (Table  3 ). Both AIs provided the model answers with explanatory notes. This facilitates the use of such OSPEs for self-assessment by learners for formative assessment purposes. The detailed instructions are helpful in creating optimized therapy regimens, and designing evidence-based regimens, to provide appropriate instructions to patients with complex medical histories. One can rely on multiple AI sources to identify, shortlist required case scenarios, and OSPE items, and seek guidance on expected model answers with explanations. The model answer guidance for antihypertensive drug classes is more appropriate (rather than a specific drug of a given class) from a teaching/learning perspective. We believe that these scenarios can be refined further by providing a focused case history along with relevant clinical and laboratory data to enhance clinical fidelity and bring a closer fit to the competency framework.

In the present study, AI tools have generated SLOs that comply with the current principles of medical education [ 15 ]. AI tools are valuable in constructing SLOs and so are especially useful for medical fraternities where training in medical education is perceived as inadequate, more so in the early stages of their academic career. Data suggests that only a third of academics in medical schools have formal training in medical education [ 16 ] which is a limitation. Thus, the credibility of alternatives, such as the AIs, is evaluated to generate appropriate course learning outcomes.

We observed that the AI platforms in the present study generated quality test items suitable for different types of assessment purposes. The AI-generated outputs were similar with minor variation. We have used generative AIs in the present study that could generate new content from their training dataset [ 17 ]. Problem-based and interactive learning approaches are referred to as “bottom-up” where learners obtain first-hand experience in solving the cases first and then indulge in discussion with the educators to refine their understanding and critical thinking skills [ 18 ]. We suggest that AI tools can be useful for this approach for imparting the core knowledge and skills related to Pharmacology and Therapeutics to undergraduate medical students. A recent scoping review evaluating the barriers to writing quality test items based on 13 studies has concluded that motivation, time constraints, and scheduling were the most common [ 19 ]. AI tools can be valuable considering the quick generation of quality test items and time management. However, as observed in the present study, the AI-generated test items nevertheless require scrutiny by faculty members for content validity. Moreover, it is important to train faculty in AI technology-assisted teaching and learning. The General Medical Council recommends taking every opportunity to raise the profile of teaching in medical schools [ 20 ]. Hence, both the academic faculty and the institution must consider investing resources in AI training to ensure appropriate use of the technology [ 21 ].

The AI outputs assessed in the present study had errors, particularly with A-type MCQs. One notable observation was that often the AI tools were unable to differentiate the differences between ACEIs and ARBs. AI platforms access several structured and unstructured data, in addition to images, audio, and videos. Hence, the AI platforms can commit errors due to extracting details from unauthenticated sources [ 22 ] created a framework identifying 28 factors for reconstructing the path of AI failures and for determining corrective actions. This is an area of interest for AI technical experts to explore. Also, this further iterates the need for human examination of test items before using them for assessment purposes.

There are concerns that AIs can memorize and provide answers from their training dataset, which they are not supposed to do [ 23 ]. Hence, the use of AIs-generated test items for summative examinations is debatable. It is essential to ensure and enhance the security features of AI tools to reduce or eliminate cross-contamination of test items. Researchers have emphasized that AI tools will only reach their potential if developers and users can access full-text non-PDF formats that help machines comprehend research papers and generate the output [ 24 ].

AI platforms may not always have access to all standard treatment guidelines. However, in the present study, it was observed that all three AI platforms generally provided appropriate test items regarding the choice of medications, aligning with recommendations from contemporary guidelines and standard textbooks in pharmacology and therapeutics. The prompts used in the study were specifically focused on the pre-clerkship phase of the undergraduate medical curriculum (and at the time of their graduation) and assessed fundamental core concepts, which were also reflected in the AI outputs. Additionally, the recommended first-line antihypertensive drug classes have been established for several decades, and information regarding their pharmacokinetics, ADRs, and indications is well-documented in the literature.

Different paradigms and learning theories have been proposed to support AI in education. These paradigms include AI- directed (learner as recipient), AI-supported (learner as collaborator), and AI-empowered (learner as leader) that are based on Behaviorism, Cognitive-Social constructivism, and Connectivism-Complex adaptive systems, respectively [ 25 ]. AI techniques have potential to stimulate and advance instructional and learning sciences. More recently a three- level model that synthesizes and unifies existing learning theories to model the roles of AIs in promoting learning process has been proposed [ 26 ]. The different components of our study rely upon these paradigms and learning theories as the theoretical underpinning.

Strengths and limitations

To the best of our knowledge, this is the first study evaluating the utility of AI platforms in generating test items related to a discipline in the undergraduate medical curriculum. We have evaluated the AI’s ability to generate outputs related to most types of assessment in the undergraduate medical curriculum. The key lessons learnt for improving the AI-generated test item quality from the present study are outlined in Table  7 . We used a structured framework for assessing the content validity of the test items. However, we have demonstrated using a single case study (hypertension) as a pilot experiment. We chose to evaluate anti-hypertensive drugs as it is a core learning objective and one of the most common disorders relevant to undergraduate medical curricula worldwide. It would be interesting to explore the output from AI platforms for other common (and uncommon/region-specific) disorders, non-/semi-core objectives, and disciplines other than Pharmacology and Therapeutics. An area of interest would be to look at the content validity of the test items generated for different curricula (such as problem-based, integrated, case-based, and competency-based) during different stages of the learning process. Also, we did not attempt to evaluate the generation of flowcharts, algorithms, or figures for generating test items. Another potential area for exploring the utility of AIs in medical education would be repeated procedural practices such as the administration of drugs through different routes by trainee residents [ 27 ]. Several AI tools have been identified for potential application in enhancing classroom instructions and assessment purposes pending validation in prospective studies [ 28 ]. Lastly, we did not administer the AI-generated test items to students and assessed their performance and so could not comment on the validity of test item discrimination and difficulty indices. Additionally, there is a need to confirm the generalizability of the findings to other complex areas in the same discipline as well as in other disciplines that pave way for future studies. The conceptual framework used in the present study for evaluating the AI-generated test items needs to be validated in a larger population. Future studies may also try to evaluate the variations in the AI outputs with repetition of the same queries.

Notwithstanding ongoing discussions and controversies, AI tools are potentially useful adjuncts to optimize instructional methods, test blueprinting, test item generation, and guidance for test standard-setting appropriate to learners’ stage in the medical program. However, experts need to critically review the content validity of AI-generated output. These challenges and caveats are to be addressed before the use of widespread use of AIs in medical education can be advocated.

Data availability

All the data included in this study are provided as Electronic Supplementary Materials.

Tolsgaard MG, Pusic MV, Sebok-Syer SS, Gin B, Svendsen MB, Syer MD, Brydges R, Cuddy MM, Boscardin CK. The fundamentals of Artificial Intelligence in medical education research: AMEE Guide 156. Med Teach. 2023;45(6):565–73.

Article   Google Scholar  

Sriwastwa A, Ravi P, Emmert A, Chokshi S, Kondor S, Dhal K, Patel P, Chepelev LL, Rybicki FJ, Gupta R. Generative AI for medical 3D printing: a comparison of ChatGPT outputs to reference standard education. 3D Print Med. 2023;9(1):21.

Azer SA, Guerrero APS. The challenges imposed by artificial intelligence: are we ready in medical education? BMC Med Educ. 2023;23(1):680.

Masters K. Ethical use of Artificial Intelligence in Health Professions Education: AMEE Guide 158. Med Teach. 2023;45(6):574–84.

Nagi F, Salih R, Alzubaidi M, Shah H, Alam T, Shah Z, Househ M. Applications of Artificial Intelligence (AI) in Medical Education: a scoping review. Stud Health Technol Inf. 2023;305:648–51.

Google Scholar  

Mehta N, Harish V, Bilimoria K, et al. Knowledge and attitudes on artificial intelligence in healthcare: a provincial survey study of medical students. MedEdPublish. 2021;10(1):75.

Mir MM, Mir GM, Raina NT, Mir SM, Mir SM, Miskeen E, Alharthi MH, Alamri MMS. Application of Artificial Intelligence in Medical Education: current scenario and future perspectives. J Adv Med Educ Prof. 2023;11(3):133–40.

Garg T. Artificial Intelligence in Medical Education. Am J Med. 2020;133(2):e68.

Matheny ME, Whicher D, Thadaney IS. Artificial intelligence in health care: a report from the National Academy of Medicine. JAMA. 2020;323(6):509–10.

Sage Poe. Available at: https://poe.com/Assistant (Accessed on. 3rd June 2023).

Claude-Instant: Available at: https://poe.com/Claude-instant (Accessed on 3rd. June 2023).

ChatGPT: Available at: https://poe.com/ChatGPT (Accessed on 3rd. June 2023).

James PA, Oparil S, Carter BL, Cushman WC, Dennison-Himmelfarb C, Handler J, Lackland DT, LeFevre ML, MacKenzie TD, Ogedegbe O, Smith SC Jr, Svetkey LP, Taler SJ, Townsend RR, Wright JT Jr, Narva AS, Ortiz E. 2014 evidence-based guideline for the management of high blood pressure in adults: report from the panel members appointed to the Eighth Joint National Committee (JNC 8). JAMA. 2014;311(5):507–20.

Eschenhagen T. Treatment of hypertension. In: Brunton LL, Knollmann BC, editors. Goodman & Gilman’s the pharmacological basis of therapeutics. 14th ed. New York: McGraw Hill; 2023.

Shabatura J. September. Using Bloom’s taxonomy to write effective learning outcomes. https://tips.uark.edu/using-blooms-taxonomy/ (Accessed on 19th 2023).

Trainor A, Richards JB. Training medical educators to teach: bridging the gap between perception and reality. Isr J Health Policy Res. 2021;10(1):75.

Boscardin C, Gin B, Golde PB, Hauer KE. ChatGPT and generative artificial intelligence for medical education: potential and opportunity. Acad Med. 2023. https://doi.org/10.1097/ACM.0000000000005439 . (Published ahead of print).

Duong MT, Rauschecker AM, Rudie JD, Chen PH, Cook TS, Bryan RN, Mohan S. Artificial intelligence for precision education in radiology. Br J Radiol. 2019;92(1103):20190389.

Karthikeyan S, O’Connor E, Hu W. Barriers and facilitators to writing quality items for medical school assessments - a scoping review. BMC Med Educ. 2019;19(1):123.

Developing teachers and trainers in undergraduate medical education. Advice supplementary to Tomorrow’s Doctors. (2009). https://www.gmc-uk.org/-/media/documents/Developing_teachers_and_trainers_in_undergraduate_medical_education___guidance_0815.pdf_56440721.pdf (Accessed on 19th September 2023).

Cooper A, Rodman A. AI and Medical Education - A 21st-Century Pandora’s Box. N Engl J Med. 2023;389(5):385–7.

Chanda SS, Banerjee DN. Omission and commission errors underlying AI failures. AI Soc. 2022;17:1–24.

Narayanan A, Kapoor S. ‘GPT-4 and Professional Benchmarks: The Wrong Answer to the Wrong Question’. Substack newsletter. AI Snake Oil (blog). https://aisnakeoil.substack.com/p/gpt-4-and-professional-benchmarks (Accessed on 19th September 2023).

Brainard J. November. As scientists face a flood of papers, AI developers aim to help. Science, 21 2023. doi.10.1126/science.adn0669.

Ouyang F, Jiao P. Artificial intelligence in education: the three paradigms. Computers Education: Artif Intell. 2021;2:100020.

Gibson D, Kovanovic V, Ifenthaler D, Dexter S, Feng S. Learning theories for artificial intelligence promoting learning processes. Br J Edu Technol. 2023;54(5):1125–46.

Guerrero DT, Asaad M, Rajesh A, Hassan A, Butler CE. Advancing Surgical Education: the Use of Artificial Intelligence in Surgical Training. Am Surg. 2023;89(1):49–54.

Lee S. AI tools for educators. EIT InnoEnergy Master School Teachers Conference. 2023. https://www.slideshare.net/ignatia/ai-toolkit-for-educators?from_action=save (Accessed on 24th September 2023).

Download references

Author information

Authors and affiliations.

Department of Pharmacology & Therapeutics, College of Medicine & Medical Sciences, Arabian Gulf University, Manama, Kingdom of Bahrain

Kannan Sridharan & Reginald P. Sequeira

You can also search for this author in PubMed   Google Scholar

Contributions

RPS– Conceived the idea; KS– Data collection and curation; RPS and KS– Data analysis; RPS and KS– wrote the first draft and were involved in all the revisions.

Corresponding author

Correspondence to Kannan Sridharan .

Ethics declarations

Ethics approval and consent to participate.

Not applicable as neither there was any interaction with humans, nor any personal data was collected in this research study.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Material 1

Rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Sridharan, K., Sequeira, R.P. Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study. BMC Med Educ 24 , 431 (2024). https://doi.org/10.1186/s12909-024-05365-7

Download citation

Received : 26 September 2023

Accepted : 28 March 2024

Published : 22 April 2024

DOI : https://doi.org/10.1186/s12909-024-05365-7

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Medical education
• Pharmacology
• Therapeutics

BMC Medical Education

ISSN: 1472-6920

• Submission enquiries: [email protected]
• General enquiries: [email protected]