Machine learning prediction for identifying individuals requiring rotator cuff repair: Shoulder muscle strength and questionnaires as the related factors

BackgroundRotator cuff tears, a common cause of shoulder pain, often require surgery when conservative treatment fails. Arthroscopic repair is standard, though re-tear rates remain high.ObjectiveThis study aimed to identify the shoulder function questionnaires and strength tests that are significant factors for determining the necessity of rotator cuff repair and to build an effective machine learning model.MethodsThis study included 183 patients between January 2008 and December 2016. Among them, 89 patients underwent non-surgical treatment for rotator cuff injuries, whereas 94 underwent arthroscopic repair of full-thickness rotator cuff tears. Fifteen features were analyzed in this study. Six machine learning algorithms, including logistic regression, decision tree, random forest, gradient boosting, neural network, and support vector machine, were trained using 5-fold cross-validation.ResultsThe final machine learning model was evaluated in an independent test set (n = 36). The neural network model demonstrated the highest performance (accuracy: 0.824, F1: 0.749). The top six predictive factors for rotator cuff repair were age, Constant-Murley score, American Shoulder and Elbow Surgeons score, University of California-Los Angeles scale score, body mass index, and shoulder abductor strength deficit.ConclusionsThe probability of arthroscopic rotator cuff repair was lower in individuals with a lower abductor strength deficit, higher shoulder questionnaire scores, younger age, and lower body mass index. When patients or clinicians are deciding on arthroscopic rotator cuff repair, shoulder function questionnaires and differences in shoulder abductor strength should be considered. The clinical relevance is that the use of a preoperative shoulder questionnaire alongside objective abductor strength measurements offers practical guidance for shared decision-making on arthroscopic rotator cuff repair.

Authors

Institutions

Publication Details

Journal
Journal of Back and Musculoskeletal Rehabilitation
Published
2026-01-05
DOI
https://doi.org/10.1177/10538127251412325
Primary Topic
Shoulder Injury and Treatment
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Machine learning prediction for identifying individuals requiring rotator cuff repair: Shoulder muscle strength and questionnaires as the related factors

Ula Hwang, Kyu Sung Chung, Obin Kwon, Se-haeng Jo et al.
Journal of Back and Musculoskeletal Rehabilitation
Shoulder Injury and Treatment
article

Machine learning prediction for identifying individuals requiring rotator cuff repair: Shoulder muscle strength and questionnaires as the related factors

Ula Hwang, Kyu Sung Chung, Obin Kwon, Se-haeng Jo, Jin-seong Kim
article en

Abstract

BackgroundRotator cuff tears, a common cause of shoulder pain, often require surgery when conservative treatment fails. Arthroscopic repair is standard, though re-tear rates remain high.ObjectiveThis study aimed to identify the shoulder function questionnaires and strength tests that are significant factors for determining the necessity of rotator cuff repair and to build an effective machine learning model.MethodsThis study included 183 patients between January 2008 and December 2016. Among them, 89 patients underwent non-surgical treatment for rotator cuff injuries, whereas 94 underwent arthroscopic repair of full-thickness rotator cuff tears. Fifteen features were analyzed in this study. Six machine learning algorithms, including logistic regression, decision tree, random forest, gradient boosting, neural network, and support vector machine, were trained using 5-fold cross-validation.ResultsThe final machine learning model was evaluated in an independent test set (n = 36). The neural network model demonstrated the highest performance (accuracy: 0.824, F1: 0.749). The top six predictive factors for rotator cuff repair were age, Constant-Murley score, American Shoulder and Elbow Surgeons score, University of California-Los Angeles scale score, body mass index, and shoulder abductor strength deficit.ConclusionsThe probability of arthroscopic rotator cuff repair was lower in individuals with a lower abductor strength deficit, higher shoulder questionnaire scores, younger age, and lower body mass index. When patients or clinicians are deciding on arthroscopic rotator cuff repair, shoulder function questionnaires and differences in shoulder abductor strength should be considered. The clinical relevance is that the use of a preoperative shoulder questionnaire alongside objective abductor strength measurements offers practical guidance for shared decision-making on arthroscopic rotator cuff repair.

Journal of Back and Musculoskeletal Rehabilitation
Hong Kong Polytechnic University (HK), Yonsei University (KR), Inje University Ilsan Paik Hospital (KR), Hanyang University Guri Hospital (KR)
Openalex Percentile: Top 98%
Shoulder Injury and Treatment
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.