EUVIMEDEUVIMED entdecken
Crossref

Large Language Model Predicts Surgeon Recommendations for Imaging and Surgery for Patients Presenting for Knee and Shoulder Complaints With 70% and 81% Accuracy Using Previsit Questionnaire Responses

Ryan T Halvorson iD, Timothy Keeley iD, Kian Niknam, Travis Zack, Sharmila Majumdar, Brian T Feeley, Alan L Zhang iD, Drew A Lansdown iD

Arthroscopy · 2026

DOI: 10.1002/arj.70016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Arthroscopy, 2026. Verfasst von Ryan T Halvorson und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthopaedic Surgery, University of California San Francisco, San Francisco, California, U.S.A. Hauptthemen laut MEDLINE: Large Language Models, Knee Injuries. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 20 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To validate the performance of a pretrained large language model (LLM) in predicting orthopaedic surgeon recommendations for management of newly referred patients, using free‐text previsit questionnaire responses as input.

Methods

This retrospective cross‐sectional study included new patients visiting an orthopaedic sports medicine clinic between 2020 and 2023. Using zero‐shot prompting, the LLM analyzed previsit questionnaire responses (e.g., “When did you start to have pain?”) to predict whether patients required advanced imaging and/or surgical intervention. The LLM was blinded to all other clinical information, including surgeon notes, physical exams, or referral data. Model predictions were evaluated with accuracy, sensitivity, and specificity in comparison to actual surgeon‐generated plans. For a subset of patients who had undergone advanced imaging, the LLM was augmented with free‐text radiology reports and asked to provide updated surgical recommendations.

Results

In the combined cohort of 1141 patients, the LLM predicted surgeon recommendation for advanced imaging with 70% accuracy, 83% sensitivity, and 64% specificity using previsit questionnaire responses alone. Imaging predictions were accurate for common diagnoses, including anterior cruciate ligament (ACL, 94%), meniscus (85%), and rotator cuff (80%) injuries but poor for knee (54%) and shoulder arthritis (66%). When augmented with imaging reports, the LLM predicted recommendations for surgery with 81% accuracy, 88% sensitivity, and 72% specificity. Surgical predictions were highly accurate for ACL (93%), meniscus (78%), rotator cuff (83%), and shoulder instability related pathologies (78%).

Conclusions

Using previsit questionnaire data from new orthopaedic patients with knee and shoulder complaints, the pretrained LLM showed 70% accuracy for imaging recommendations, and the augmented surgical‐decision LLM showed 81% accuracy for surgical recommendations. Level of Evidence Level III, retrospective diagnostic case‐control study.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsKnee InjuriesHumansRetrospective StudiesCross-Sectional StudiesSurveys and QuestionnairesFemaleMaleAdultMiddle AgedSensitivity and Specificity

Autor:innen und Institutionen

  • Department of Orthopaedic Surgery, University of California San Francisco, San Francisco, California, U.S.A.
  • School of Medicine, University of California San Francisco, San Francisco, California, U.S.A.
  • Department of Radiology, University of California San Francisco, San Francisco, California, U.S.A.

ORCID-Profile: Ryan T Halvorson, Timothy Keeley, Alan L Zhang, Drew A Lansdown

Zitieren

APA

Halvorson, R. T., Keeley, T., Niknam, K., Zack, T., Majumdar, S., Feeley, B. T., Zhang, A. L., & Lansdown, D. A. (2026). Large Language Model Predicts Surgeon Recommendations for Imaging and Surgery for Patients Presenting for Knee and Shoulder Complaints With 70% and 81% Accuracy Using Previsit Questionnaire Responses. Arthroscopy. https://doi.org/10.1002/arj.70016

Vancouver

Halvorson RT, Keeley T, Niknam K, Zack T, Majumdar S, Feeley BT, et al. Large Language Model Predicts Surgeon Recommendations for Imaging and Surgery for Patients Presenting for Knee and Shoulder Complaints With 70% and 81% Accuracy Using Previsit Questionnaire Responses. Arthroscopy. 2026. doi:10.1002/arj.70016

BibTeX
@article{Halvorson2026,
  author = {Halvorson, Ryan T and Keeley, Timothy and Niknam, Kian and Zack, Travis and Majumdar, Sharmila and Feeley, Brian T and Zhang, Alan L and Lansdown, Drew A},
  title = {Large Language Model Predicts Surgeon Recommendations for Imaging and Surgery for Patients Presenting for Knee and Shoulder Complaints With 70% and 81% Accuracy Using Previsit Questionnaire Responses},
  journal = {Arthroscopy},
  year = {2026},
  doi = {10.1002/arj.70016}
}
Kostenlos starten →