Related Experiment Videos
Using artificial intelligence to uncover keywords associated with resident EPA entrustability.
Alexandra Z Agathis1, Joanna Yang2, Damien J Lazar1
1Division of General Surgery, Department of Surgery, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
American Journal of Surgery
|April 26, 2026
Summary
Artificial intelligence and natural language processing analyzed resident evaluations to identify key factors in entrustability. This can help improve feedback and training for surgical residents.
Area of Science:
- Medical Education
- Artificial Intelligence in Medicine
- Surgical Training
Background:
- Entrustable Professional Activity (EPA) evaluations are fundamental for resident feedback and assessing practice readiness.
- Current research lacks studies using AI to compare qualitative feedback with quantitative scoring in EPA evaluations.
Purpose of the Study:
- To utilize artificial intelligence (AI) and natural language processing (NLP) to identify keywords associated with resident entrustability in surgical training.
- To analyze discrepancies between attending and resident-assigned scores in EPA micro-assessments.
Main Methods:
- A retrospective analysis of 1,000 resident EPA micro-assessments from 7/6/2023-12/3/2024 was conducted.
- Natural language processing (NLP) models were applied to extract keywords related to resident entrustability.
- Spearman's correlations were used to identify keywords and score discrepancies.
Main Results:
- Key themes associated with lower entrustability included camera navigation, case progression, and retraction.
- Residents described as "independent" and "safe" were rated with higher entrustability.
- Attendings citing higher scores than resident self-ratings frequently mentioned complex pathologies and emotional aspects of patient care.
Conclusions:
- An AI-based tool can be integrated into residency programs to identify characteristics of highly entrustable residents.
- This approach offers a valuable roadmap for enhancing resident development and feedback systems.
Related Concept Videos
01:53RNA Stability
10.9K
10.9K
01:08The Availability Heuristic
6.1K
A heuristic is a general problem-solving framework (Tversky & Kahneman, 1974). You can think of these as mental shortcuts that are used to solve problems. Different types of heuristics are used in different types of situations, and the impulse to use a heuristic occurs when one of five conditions is met (Pratkanis, 1989):
6.1K
01:16Non-equilibrium in the Cell
3.9K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
3.9K