Sign in Subscribe
Artificial intelligence

Artificial Intelligence in Graduate Medical Education: A Scoping Review of Attitudes, Applications & Practice

Strategic Insights

— 1 min read

A recent study from Johns Hopkins University published in BMC Medical Education has shed light on the transformative potential of artificial intelligence (AI) in graduate medical education (GME). The study, conducted by an international team of researchers, aimed to map the current literature on AI in GME, identifying prevailing perceptions, applications, and research gaps. The comprehensive review of 102 studies across 16 countries, predominantly from North America, Asia, and Europe, found that AI has the potential to differentiate between skill levels, offer meaningful feedback, and evaluate narrative comments to assess resident performance.

Key Takeaways:

  • The study found that perceptions of AI in GME were initially mixed but have increasingly shifted toward a more favorable outlook as the benefits of AI integration in education become more apparent.
  • AI demonstrated the ability to differentiate between skill levels and offer meaningful feedback, making it a valuable tool in resident assessment.
  • Large language models consistently outperformed average candidates on board certification and in-training examinations, indicating their potential utility in standardized assessments.
  • AI tools showed promise in enhancing clinical decision-making by supporting trainees with improved diagnostic accuracy and efficiency.
  • The study found that AI tools have been applied to analyze letters of recommendation, applications, and personal statements to identify potential biases and improve equity in candidate selection.
  • Radiology had the highest number of publications (21), followed by general surgery (11) and emergency medicine (8).
  • The majority of studies were published in 2023, indicating a growing interest in the application of AI in GME.
  • Several key thematic areas emerged from the literature, including the potential of AI in education, assessment, recruitment, and clinical decision-making.

Statistics:

  • 102 studies met the inclusion criteria, conducted across 16 countries, predominantly from North America (72), Asia (14), and Europe (6).
  • As of February 2024, a comprehensive search of multiple databases included up to 1734 citations.
  • The majority of studies were published in 2023 (58 studies).
  • Radiology had the highest number of publications (21), followed by general surgery (11) and emergency medicine (8).
  • Large language models consistently outperformed average candidates on board certification and in-training examinations by 10-15%.

Sources:

  • Modern artificial intelligence and large language models in graduate medical education: a scoping review of attitudes, applications & practice (2025,25(1):1-28). BMC Medical Education. Available at: https://doi-org.sdpl.idm.oclc.org/10.1186/s12909-025-07321-5.
  • Johns Hopkins University. Researchers Publish New Study on Artificial Intelligence (NewsRx, 2025).

Read more