Actionable companion · Assessment and evidence of learning

From evidence to district action: Examining the Performance of ChatGPT in Comprehensive Pre‐Internship Exam: The Potential of Artificial Intelligence in Medical Education

AI-assisted editorial implementation guide. The district actions are proposed applications, not findings or recommendations attributed to the original authors. No additional peer review is asserted.

Evidence and context

Health-professions education context: test transfer to K–12 rather than assuming it.

Original authors’ abstract, reproduced under the linked source license:

ABSTRACT Background and Aims ChatGPT is a popular large language model with potential educational applications in medicine. However, its performance in standardized, multi‐disciplinary medical exams has not been comprehensively assessed. This study evaluates ChatGPT's accuracy and quality in Iran's national medical pre‐internship exam. Methods We tested ChatGPT (GPT‐3.5, May 3rd version) on 195 multiple‐choice questions from the March 2022 Iranian pre‐internship exam, covering 23 medical specialties. Questions with visual content were excluded. Each question was asked in a new chat to avoid memory bias. Responses were evaluated by 55 experts using a 5‐point Likert scale and compared against the official answer key. Data were analyzed descriptively using SPSS. Results ChatGPT answered 68.6% of questions correctly. Expert ratings averaged 4.23/5 (SD = 1.21), indicating good to excellent quality. Best‐performing specialties included pharmacology (85.7%), otorhinolaryngology (83.3%), and dermatology (83.3%). Lower performance was observed in pulmonology (42.9%) and epidemiology (50%). Conclusion ChatGPT shows promise as a supplemental educational tool in medical education, but its accuracy varies by specialty. Faculty guidance is essential to ensure responsible integration until further improvements and validations are made.

A 90-day district pilot

1. Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
2. Days 16–30 · Design. Redesign one low-stakes assessment: require a first attempt, an AI-assisted revision, a source-check log and a short oral explanation. Use the same rubric for the comparison task. Name an accountable owner and set the baseline, success threshold and budget before implementation.
3. Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
4. Days 61–90 · Decide. Blind-score reasoning, factual accuracy and unaided transfer on a fresh task. Record suspected misconduct separately from demonstrated evidence. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Michaeel Motaghi Niko; Zahra Karbasi; Maryam Kazemi; Maryam Zahmatkeshan. Examining the Performance of ChatGPT in Comprehensive Pre‐Internship Exam: The Potential of Artificial Intelligence in Medical Education. Health Science Reports (2026-01-08). https://doi.org/10.1002/hsr2.71492

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.