Related Experiment Video
Updated: Jan 18, 2026
05:33
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
Published on: July 11, 2025
811
Preparing for AI in Resident Selection: A Scoping Review of Current Applications and Limitations
Gillian Michaelson1,2, Daniel Karasik2,3, Eleanor Polen4
1Case Western Reserve University School of Medicine, Cleveland, Ohio, USA.
The Laryngoscope
|June 7, 2025
Summary
Artificial intelligence (AI) can help streamline medical residency applications by assessing bias and predicting outcomes. However, careful development is needed to ensure AI tools are equitable and interpretable in resident selection.
Area of Science:
- Medical Education
- Health Informatics
- Artificial Intelligence
Background:
- Medical residency programs receive numerous applications, necessitating efficient review processes.
- Artificial intelligence (AI) offers potential solutions for optimizing resident selection.
- This review explores AI applications in evaluating medical residency applicants.
Purpose of the Study:
- To conduct a scoping review of AI applications in medical resident selection.
- To identify the impacts and limitations of using AI in this process.
Main Methods:
- Searched six databases (PubMed, OVID, Cochrane, EMBASE, Google Scholar, Web of Science) for English articles from the last 10 years.
- Used keywords related to AI, natural language processing, machine learning, medical residency, and personnel selection.
- Included studies involving real or simulated residency applicants/applications and AI in selection; screened independently by two reviewers.
Main Results:
- 11 of 115 articles met inclusion criteria, focusing on AI for bias assessment, outcome prediction, and comparison with human reviewers.
- AI models included natural language processing, machine learning, and large language models.
- AI showed potential for bias detection, improved consistency, and identifying overlooked applicants, but concerns exist regarding bias replication, generalizability, and interpretability.
Conclusions:
- AI demonstrates promise for enhancing efficiency and equity in resident selection.
- Further research is crucial for responsible AI development, validation, and oversight in medical education.
