EUVIMEDOpdag EUVIMED
QuerschnittstudieOpen access

ChatGPT versus UpToDate in Preclinical Medical Education: Cross-Sectional Analysis Using Term Frequency–Inverse Document Frequency Cosine Similarity

Shankar S Thiru iD, Nicholas E Aksu iD, Matthew Chiang iD, Daniel O Gallagher iD, Mary Furlong iD, Elizabeth R Prevou iD, Akhil Jay Khanna iD

JMIR Medical Education · 2026

DOI: 10.2196/82885 ↗

At a glance

Querschnittstudie in JMIR Medical Education, 2026. Written by Shankar S Thiru and 6 co-authors. Institution: Georgetown University School of Medicine, 3800 Reservoir Rd, Washington, DC, 20007, United States. Major MEDLINE topics: Education, Medical, Undergraduate. Cited 4 times so far (Crossref); 22 references. The full text is freely available in PubMed Central.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

Generative artificial intelligence tools such as ChatGPT are increasingly used by medical students for self-directed learning. Although these models demonstrate linguistic fluency, their reliability as supplementary resources for preclinical education remains uncertain. In particular, comparisons with evidence-based references such as UpToDate are lacking.

Objective

This study evaluated the similarity between responses generated by ChatGPT (with GPT-4o mini) and those from UpToDate to preclinical medical education questions to assess ChatGPT’s potential as an adjunctive learning tool.

Methods

We conducted a cross-sectional comparison study using 150 first-order questions derived from a preclinical question bank at a single allopathic institution under the oversight of a medical educator with more than 25 years of teaching experience. Each question was entered into ChatGPT 10 times in separate chat sessions, and responses from UpToDate were retrieved from the most relevant articles. The responses were preprocessed through lemmatization, stop-word removal, punctuation removal, and numeric normalization. Similarity between ChatGPT and UpToDate responses was quantified using term frequency–inverse document frequency (TF-IDF) cosine similarity. To determine whether the observed similarities exceeded chance, ChatGPT outputs were compared with a null distribution generated from randomized text.

Results

ChatGPT responses demonstrated statistically significant similarity to UpToDate in 59.3% (89/150) of questions. Across subject areas, pharmacology showed the highest concordance (mean cosine similarity 0.338, SD 0.134), followed by pathology (mean 0.321, SD 0.142), biochemistry (mean 0.296, SD 0.120), microbiology (mean 0.297, SD 0.108), and immunology (mean 0.275, SD 0.102). All subject-level similarity scores exceeded those generated from randomized text, confirming that the observed overlap was nonrandom.

Conclusions

ChatGPT with GPT-4o mini exhibited moderate but meaningful alignment with UpToDate across preclinical topics, performing best in fact-based disciplines such as pharmacology. Although it is not a substitute for evidence-based resources, ChatGPT may serve as an accessible adjunctive tool for medical students. Integration into preclinical learning should be coupled with artificial intelligence literacy training to promote responsible use and critical appraisal.

Subjects

MeSH terms (MEDLINE)

Education, Medical, UndergraduateGenerative Artificial IntelligenceCross-Sectional StudiesHumansEducational MeasurementLarge Language Models

Author keywords

ChatGPTUpToDateartificial intelligencemedical educationpreclinical

Authors and institutions

  • Georgetown University School of Medicine, 3800 Reservoir Rd, Washington, DC, 20007, United States.
  • Department of Orthopaedic Surgery, MedStar Georgetown University Hospital, Washington, DC, United States.
  • DataChat Inc., Madison, WI, United States.
  • Rothman Orthopaedic Institute, Thomas Jefferson University Hospital, Philadelphia, PA, United States.
  • Department of Pathology and Laboratory Medicine, Georgetown University School of Medicine, Washington, DC, United States.
  • The George Washington University School of Medicine and Health Sciences, Washington, DC, United States.

ORCID profiles: Shankar S Thiru, Nicholas E Aksu, Matthew Chiang, Daniel O Gallagher, Mary Furlong, Elizabeth R Prevou, Akhil Jay Khanna

Cite

APA

Thiru, S. S., Aksu, N. E., Chiang, M., Gallagher, D. O., Furlong, M., Prevou, E. R., & Khanna, A. J. (2026). ChatGPT versus UpToDate in Preclinical Medical Education: Cross-Sectional Analysis Using Term Frequency–Inverse Document Frequency Cosine Similarity. JMIR Medical Education. https://doi.org/10.2196/82885

Vancouver

Thiru SS, Aksu NE, Chiang M, Gallagher DO, Furlong M, Prevou ER, et al. ChatGPT versus UpToDate in Preclinical Medical Education: Cross-Sectional Analysis Using Term Frequency–Inverse Document Frequency Cosine Similarity. JMIR Medical Education. 2026. doi:10.2196/82885

BibTeX
@article{Thiru2026,
  author = {Thiru, Shankar S and Aksu, Nicholas E and Chiang, Matthew and Gallagher, Daniel O and Furlong, Mary and Prevou, Elizabeth R and Khanna, Akhil Jay},
  title = {ChatGPT versus UpToDate in Preclinical Medical Education: Cross-Sectional Analysis Using Term Frequency–Inverse Document Frequency Cosine Similarity},
  journal = {JMIR Medical Education},
  year = {2026},
  doi = {10.2196/82885}
}
Start for free →