EUVIMEDObjevte EUVIMED
VergleichsstudieQuerschnittstudieOpen access

Comparing AI-Assisted Problem-Solving Ability With Internet Search Engine and e-Books in Medical Students With Variable Prior Subject Knowledge: Cross-Sectional Study

Ajiith Xavier iD, Syed Shariq Naeem iD, Waseem Rizwi iD, Hiramani Rabha iD

JMIR Medical Education · 2026

DOI: 10.2196/81264 ↗

At a glance

Vergleichsstudie in JMIR Medical Education, 2026. Written by Ajiith Xavier and 3 co-authors. Institution: Department of Pharmacology, Jawaharlal Nehru Medical College and Hospital, Aligarh Muslim University, Medical Road, Aligarh, Uttar Pradesh, 202001, I…. Major MEDLINE topics: Students, Medical, Search Engine, Problem Solving, Internet. Cited 7 times so far (Crossref); 23 references. The full text is freely available in PubMed Central.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Artificial intelligence (AI), particularly large language models (LLMs) such as ChatGPT (OpenAI), is rapidly influencing medical education. Its effectiveness for students with varying levels of prior knowledge remains underexplored.

Objective

This study aimed to evaluate the performance of medical students with and without formal pharmacology knowledge when using AI-LLM GPTs, internet search engines, e-books, or self-knowledge to solve multiple-choice questions (MCQs).

Methods

A cross-sectional study was conducted at a tertiary care teaching hospital with 100 medical students, divided into a “naive” group (n=50; no pharmacology training) and a “learned” group (n=50; completed pharmacology training). The study was started after approval from the Institutional Ethics Committee of Jawaharlal Nehru Medical College Hospital, Aligarh Muslim University (1018/IEC/23/8/23). Each participant answered 4 sets of 20 MCQs using self-knowledge, e-books, Google, or ChatGPT-4o. Scores were compared using analysis of covariance with self-knowledge scores as a covariate.

Results

Learned students significantly outperformed naive students across all methods ( P internet search engine > self-knowledge ≈ e-books. Notably, the naive students who used AI scored higher (mean 13.24, SD 3.31) than the learned students who used Google (mean 12.14, SD 2.01; P =.01) or e-books (mean 10.22, SD 3.12; P

Subjects

MeSH terms (MEDLINE)

Students, MedicalSearch EngineProblem SolvingInternetArtificial IntelligencePharmacologyCross-Sectional StudiesHumansMaleFemaleEducational MeasurementEducation, Medical, UndergraduateYoung Adult

Author keywords

AIChatGPTLLMartificial intelligencecognitive performancelarge language modelsmedical educationsubject-naive learners

Authors and institutions

  • Department of Pharmacology, Jawaharlal Nehru Medical College and Hospital, Aligarh Muslim University, Medical Road, Aligarh, Uttar Pradesh, 202001, India, 91 9634912166.

ORCID profiles: Ajiith Xavier, Syed Shariq Naeem, Waseem Rizwi, Hiramani Rabha

Cite

APA

Xavier, A., Naeem, S. S., Rizwi, W., & Rabha, H. (2026). Comparing AI-Assisted Problem-Solving Ability With Internet Search Engine and e-Books in Medical Students With Variable Prior Subject Knowledge: Cross-Sectional Study. JMIR Medical Education. https://doi.org/10.2196/81264

Vancouver

Xavier A, Naeem SS, Rizwi W, Rabha H. Comparing AI-Assisted Problem-Solving Ability With Internet Search Engine and e-Books in Medical Students With Variable Prior Subject Knowledge: Cross-Sectional Study. JMIR Medical Education. 2026. doi:10.2196/81264

BibTeX
@article{Xavier2026,
  author = {Xavier, Ajiith and Naeem, Syed Shariq and Rizwi, Waseem and Rabha, Hiramani},
  title = {Comparing AI-Assisted Problem-Solving Ability With Internet Search Engine and e-Books in Medical Students With Variable Prior Subject Knowledge: Cross-Sectional Study},
  journal = {JMIR Medical Education},
  year = {2026},
  doi = {10.2196/81264}
}
Start for free →