Related Experiment Video
Updated: Jun 12, 2025

Author Spotlight: Evaluating Clinicians' Adoption of Ultrasound-Guided Vascular Cannulation Through Simulation Training
Published on: August 9, 2024
ChatGPT's Performance on Iran's Medical Licensing Exams
Alireza Keshtkar1, Ali-Asghar Hayat2, Farnaz Atighi3
1Research Center of Noncommunicable Diseases, Jahrom University of Medical Sciences, Jahrom, Iran.
ChatGPT demonstrates potential in medical education, scoring above passing thresholds on Iranian medical license exams in basic sciences and pre-internship levels. The AI model also provided reasoning, highlighting its utility for medical training and assessment.
Area of Science:
- Artificial Intelligence in Medicine
- Natural Language Processing Applications
- Medical Education Technology
Background:
- OpenAI's ChatGPT, a 175 billion parameter transformer model, is utilized for natural language processing tasks.
- This study evaluates ChatGPT's knowledge and interpretive capabilities on Iranian medical licensing examinations.
Purpose of the Study:
- To assess the performance of ChatGPT (specifically ChatGPT 3.5) on Iranian medical licensing exams.
- To compare ChatGPT's performance across different exam levels (basic sciences, pre-internship, pre-residency) and languages (Persian and English).
Main Methods:
- Three levels of Iranian medical license exams were administered to ChatGPT 3.5.
- Exams were presented in both Persian and English, with versions reflecting ChatGPT's internet access.
- Accuracy and concordance of responses were evaluated by two blinded adjudicators.
Main Results:
- ChatGPT answered 48.5% of 2210 total questions accurately, with 91% overall concordance.
- English questions yielded higher accuracy (61.4%) and concordance (94.5%) than Persian questions (35.7% accuracy, 88.7% concordance).
- The model exceeded passing scores for basic sciences and pre-internship exams and met the minimum for residency application.
Conclusions:
- ChatGPT demonstrates proficiency exceeding passing standards in certain Iranian medical licensing exams.
- The AI's ability to provide reasoning suggests significant potential for integration into medical education.
- Performance variations between English and Persian indicate language as a critical factor in AI assessment accuracy.
Related Concept Videos
Pulmonary Function Tests
Pulmonary Function Tests are crucial diagnostic tools for assessing respiratory function, particularly in patients with chronic respiratory disorders. They comprehensively evaluate lung volumes, ventilatory function, breathing mechanics, diffusion, and gas exchange. These tests help diagnose pulmonary diseases and play a significant role in monitoring disease progression, evaluating disability, and assessing response to therapy.
PFTs involve using a spirometer, a...
Assessment of the Gastrointestinal System II: Health Perception Pattern
Health Perception Patterns
Health perception patterns offer valuable insights into a patient's lifestyle habits and how they may impact their GI health. These patterns include:
Assessment of the Abdomen II: Percussion
Percussion
Percussion is an essential...
Imaging Studies II: Positron Emission Tomography and Scintigraphy
Fundamental Principles of PET
Radiological Investigation III: Pulmonary Angiogram and PET Scan
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...

