Paper 43: Defining and Predicting the “Optimal Observed Outcome” Following Surgical Treatment of Anterior Shoulder Instability: A Machine Learning Clustering Analysis of 200 patients with 11-year mean follow up.

Objectives: Desirable outcomes following surgery for anterior shoulder instability (ASI) include a multitude of functional and clinical functions, yet it remains uncertain if all of these outcomes are simultaneously achievable (i.e. can patients have full motion and no instability; does excellent stability coincide with stiffness?). The purpose of this study was to employ unsupervised machine learning techniques to define the actual "optimal observed outcome” for patients undergoing surgical treatment for ASI and to identify predictors of obtaining this outcome. Methods: Patients <40 years with an initial diagnosis of ASI from 1994 -2016 were included. Four unsupervised machine learning clustering algorithms were evaluated to partition subjects into “optimal observed outcome” or “suboptimal outcome” based on combinations of actually observed outcomes. Demographic, clinical, and treatment variables were compared between groups using descriptive statistics and Kaplan-Meier survival curves; multivariate stepwise logistic regression evaluated variable prognostic value. Results: 200 patients with a mean follow-up of 11 years were included. 146 (64%) obtained the “optimal observed outcome”, characterized by significantly (P <0.001) lower rates of: recurrent postoperative pain (23% vs 52%), recurrent instability (12% vs 41%), revision surgery (10% vs 24%), progression to osteoarthritis (OA) (5% vs. 19%), and mildly restricted motion (161° vs. 168°). Stepwise multivariate logistic regression identified time from initial instability to presentation (OR: 0.96, 95% CI: 0.92-0.98) and habitual instability (OR: 0.17, 95%CI: 0.04-0.77) as negative predictors of “observed optimal outcome”. Increased rate of subluxation over frank dislocation pre-operatively (OR: 1.30, 95% CI: 1.02-1.65) was a positive predictor. Type of surgery performed was not a significant predictor. Conclusions: Following surgical treatment for ASI, an appropriate “optimal observed outcome” can be defined as: minimal postoperative pain, absence of recurrent instability, low rates of revision surgery, absence of OA, and increased ROM. This “optimal observed outcome” was achieved in over 2/3rds of the cohort and this work demonstrated the synergistic relationship of these. The most significant predictors included shorter time to presentation and history of subluxations over frank dislocations pre-operatively. This definition of the “optimal observed outcome” may be more appropriate for surgical decision making and setting appropriate expectations. [Table: see text][Table: see text]