Accessibility settings

This paper is in the following e-collection/theme issue:

Artificial Intelligence (AI) in Medical Education (871) Graduate and Postgraduate Education for Health Professionals (262) Testing and Assessment in Medical Education (244) Evaluation of Medical Education (304) New Methods and Approaches in Medical Education (682) Models and Frameworks in Medical Education (128) Theme Issue: ChatGPT and Generative Language Models in Medical Education (144)

Published on in Vol 11 (2025)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/78320, first published .
Medical team in blue scrubs discussing patient care at a conference table.

Impact of Prompt Engineering on the Performance of ChatGPT Variants Across Different Question Types in Medical Student Examinations: Cross-Sectional Study

Impact of Prompt Engineering on the Performance of ChatGPT Variants Across Different Question Types in Medical Student Examinations: Cross-Sectional Study

Authors of this article:

Ming-Yu Hsieh1, 2 Author Orcid Image ;   Tzu-Ling Wang3 Author Orcid Image ;   Pen-Hua Su2, 4 Author Orcid Image ;   Ming-Chih Chou2, 5 Author Orcid Image
Article Authors Cited by (10) Tweetations Metrics

Journals

  1. Tsuei S. AI Competency: Current State and Challenges. JMIR Medical Education 2026;12:e86686 View
  2. Nogué-Xarau S, Ríos-Guillermo J, Saavedra C, Amigó-Tadín M. Inteligencia artificial y toxicología: conocimientos frente a los de otras especialidades médicas. Medicina Clínica 2026;166(5):107407 View
  3. Nogué-Xarau S, Ríos-Guillermo J, Saavedra C, Amigó-Tadín M. Artificial intelligence and toxicology: Knowledge compared with other medical specialties. Medicina Clínica (English Edition) 2026;166(5):107407 View
  4. Ayhan B, Yoğurt S, Ayhan Z. Evaluation of ChatGPT-5.2 responses to frequently asked questions about benign bone tumors. Frontiers in Oncology 2026;16 View
  5. Genc O, Durgun S, Un B. Can ChatGPT graduate as a civil engineer? Exploring the role of prompt design in model behaviour. Engineering, Construction and Architectural Management 2026:1 View
  6. Llorente de Pedro M, Freire Y, Moneo N, Andreu-Vázquez C, Estévez R, Díaz-Flores García V, Suárez A. Diagnostic accuracy and repeatability of ChatGPT using textual and radiographic data in reversible pulpitis: a retrospective diagnostic study. Frontiers in Bioinformatics 2026;6 View
  7. Maciąg B, Bujak K, Jegierski D, Stolarczyk A. Can ChatGPT pass the polish national medical specialization examination in orthopedics and traumatology?. Archives of Orthopaedic and Trauma Surgery 2026;146(1) View
  8. Al-Haj Ali S, Farah R. NASA TLX workload profiles of multimodal artificial intelligence models and dental students during objective structured practical dental examinations. Discover Education 2026;5(1) View
  9. Siriseth S, Vattanavanit V. Clinicians vs. Artificial Intelligence in Predicting 28-day ICU Mortality: A Vignette Study. Journal of Pain and Symptom Management 2026 View
  10. Zhang L, Liang L, Peng X, Liu S, Zhong L, Li Z. Reliability and readability of five large language models in answering patient-oriented questions about rectal prolapse: a comparative study. Frontiers in Medicine 2026;13 View