BOSTON — Predictors of failure to achieve a minimally clinically important difference following hip arthroscopy include mental health, symptom duration length, non-intra-articular hip related pain and preoperative intra-articular injections, according to a presentation at the American Orthopaedic Society for Sports Medicine Annual Meeting.

Jourdan M. Cancienne, MD, and colleagues identified 1,194 patients who underwent hip arthroscopy for femoroacetabular impingement. Predictive models were created to achieve a minimally clinically important difference (MCID) with regard to hip outcome score-activity of daily living (HOS-ADL), HOS-sport-specific measures (HOS-SS) and the modified Harris Hip Score (mHHS). The Lasso algorithm was used to decrease data to meaningful features and overfitting. Investigators performed receiver operating characteristic (ROC) analyses on each model. There were 57 independent features used for binary logistic regression analysis. The PatientQ was used to analyze data.