Understanding Anterior Shoulder Instability Through Machine Learning: New Models That Predict Recurrence, Progression to Surgery, and Development of Arthritis

Abstract

Background: Management of anterior shoulder instability (ASI) aims to reduce risk of future recurrence and prevent complications via nonoperative and surgical management. Machine learning may be able to reliably provide predictions to improve decision making for this condition. Purpose: To develop and internally validate a machine-learning model to predict the following outcomes after ASI: (1) recurrent instability, (2) progression to surgery, and (3) the development of symptomatic osteoarthritis (OA) over long-term follow-up. Study Design: Cohort study (prognosis); Level of evidence, 2. Methods: An established geographic database of >500,000 patients was used to identify 654 patients aged <40 years with an initial diagnosis of ASI between 1994 and 2016; the mean follow-up was 11.1 years. Medical records were reviewed to obtain patient information, and models were generated to predict the outcomes of interest. Five candidate algorithms were trained in the development of each of the models, as well as an additional ensemble of the algorithms. Performance of the algorithms was assessed using discrimination, calibration, and decision curve analysis. Results: Of the 654 included patients, 443 (67.7%) experienced multiple instability events, 228 (34.9%) underwent surgery, and 39 (5.9%) developed symptomatic OA. The ensemble gradient-boosted machines achieved the best performances based on discrimination (via area under the receiver operating characteristic curve [AUC]: AUCrecurrence = 0.86), AUCsurgery = 0.76, AUCOA = 0.78), calibration, decision curve analysis, and Brier score (Brierrecurrence = 0.138, Briersurgery = 0.185, BrierOA = 0.05). For demonstration purposes, models were integrated into a single web-based open-access application able to provide predictions and explanations for practitioners and researchers. Conclusion: After identification of key features, including time from initial instability, age at initial instability, sports involvement, and radiographic findings, machine-learning models were developed that effectively and reliably predicted recurrent instability, progression to surgery, and the development of OA in patients with ASI. After careful external validation, these models can be incorporated into open-access digital applications to inform patients, clinicians, and researchers regarding quantifiable risks of relevant outcomes in the clinic.

Risk factors for secondary meniscus tears can be accurately predicted through machine learning, creating a resource for patient education and intervention

“…Several recent investigations have demonstrated the effectiveness and reliability of machine learning in generating individualized prediction models for clinical and patient reported outcomes in orthopedic surgery. These studies highlight improved performance over predictive modeling using linear techniques such as logistic regression [13, 15, 16, 24]. However, machine learning prediction models for meniscus tears have remained primarily diagnostic and imaging focused [4, 27], except for Snoeker et al, who published the development and internal validation of a clinical prediction rule for detection of meniscus tears during primary care encounters [29].…”

Predicting the Risk of Posttraumatic Osteoarthritis After Primary Anterior Cruciate Ligament Reconstruction: A Machine Learning Time-to-Event Analysis

“…The Rochester Epidemiology Database is an established longitudinal geographic database of >500,000 medical records for residents of Olmstead County, Minnesota, as well as neighboring counties in southeast Minnesota and western Wisconsin. 26 Patients were identified using the appropriate International Classification of Diseases, 9th or 10th Revision, diagnosis codes for ACL rupture. After data curation, each individual patient chart was reviewed by study personnel in the following systematic approach: (1) confirm the diagnosis of ACL injury; (2) apply inclusion/exclusion criteria; and (3) extract relevant patient, clinical, and outcome variables from chart review.…”

Early ACLR and Risk and Timing of Secondary Meniscal Injury Compared With Delayed ACLR or Nonoperative Treatment: A Time-to-Event Analysis Using Machine Learning

“…As previously described, the REP is an established longitudinal geographic database of >500,000 medical records for residents of Olmstead County, Minnesota, as well as neighboring counties in southeast Minnesota and western Wisconsin. 30 The REP provides detailed descriptions of every resident health care encounter within the Olmstead County system from 1966 to the present day, independent of the treating institution. Patients were identified using International Classification of Diseases–Ninth Revision and –Tenth Revision diagnosis codes for ACL rupture.…”