Evaluating Resident Feedback Using a Large Language Model: Are We Missing Core Competencies?
The Laryngoscope · 2025-11 · 135 (11) · 4119-4124
DOI: 10.1002/lary.32368 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Laryngoscope, online erschienen am 27.06.2025. Verfasst von Syed Ameen Ahmad und 4 weiteren Autor:innen. Beteiligte Einrichtung: Johns Hopkins University School of Medicine, Baltimore, Maryland, USA. Hauptthemen laut MEDLINE: Internship and Residency, Clinical Competence, Education, Medical, Graduate, Formative Feedback. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 17 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIDCD NIH HHS.
Abstract (Originalsprache)
Objectives
Use a large language model (LLM) to examine the content and quality of narrative feedback provided to residents through: (1) an app collecting workplace‐based assessments of surgical performance (SIMPL‐OR), (2)
Objective
Structured Assessment of Technical Skills (OSATS), and (3) end‐of‐rotation (EOR) evaluations.
Methods
Narrative feedback provided to residents at a single institution from 2017 to 2021 was examined. Sixty entries (20 of each format) were evaluated by two faculty members on whether they were encouraging, corrective, or specific, and whether they addressed the Core Competencies outlined by the Accreditation Council for Graduate Medical Education. ChatGPT4o was tested on these 60 entries before evaluating the remaining 776 entries.
Results
ChatGPT evaluated entries with 90% concordance with faculty ( κ = 0.94). Within the 776 feedback entries evaluated by ChatGPT, competencies addressed included: patient care ( n = 491, 97% vs. 77% vs. 36% for SIMPL‐OR, OSATS, EOR respectively, p < 0.001), practice‐based learning ( n = 175, 32% vs. 23% vs. 16%, p < 0.001), professionalism ( n = 168, 1% vs. 6% vs. 40%, p < 0.001), medical knowledge ( n = 95, 7% vs. 8% vs. 17%, p < 0.001), interpersonal and communication skills ( n = 59, 3% vs. 3% vs. 12%, p < 0.001), and systems‐based practice ( n = 31, 4% vs. 2% vs. 5%, p = 0.387). Feedback was “encouraging” in 93% of both SIMPL‐OR and OSATS, as compared to 84% of EOR ( p < 0.001). Feedback was “corrective” in 71% of SIMPL‐OR versus 44% of OSATS versus 24% of EOR ( p < 0.001), and “specific” in 97% versus 53% versus 15%, respectively ( p < 0.001).
Conclusion
Different instruments provided feedback of differing content and quality and a multimodal feedback approach is important. Level of Evidence N/A
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
- Department of Otolaryngology-Head and Neck Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
ORCID-Profile: Syed Ameen Ahmad, Jenny X Chen, Deepa Galaiya
Förderung
- NIDCD NIH HHS
Zitieren
APA
Ahmad, S. A., Armache, M., Trakimas, D. R., Chen, J. X., & Galaiya, D. (2025). Evaluating Resident Feedback Using a Large Language Model: Are We Missing Core Competencies?. The Laryngoscope, 135(11), 4119-4124. https://doi.org/10.1002/lary.32368
Vancouver
Ahmad SA, Armache M, Trakimas DR, Chen JX, Galaiya D. Evaluating Resident Feedback Using a Large Language Model: Are We Missing Core Competencies?. The Laryngoscope. 2025;135(11):4119-4124. doi:10.1002/lary.32368
BibTeX
@article{Ahmad2025,
author = {Ahmad, Syed Ameen and Armache, Maria and Trakimas, Danielle R and Chen, Jenny X and Galaiya, Deepa},
title = {Evaluating Resident Feedback Using a Large Language Model: Are We Missing Core Competencies?},
journal = {The Laryngoscope},
year = {2025},
volume = {135},
number = {11},
pages = {4119--4124},
doi = {10.1002/lary.32368}
}
EUVIMED