The utility of machine learning algorithms for the prediction of patient-reported outcome measures following primary hip and knee total joint arthroplasty.

BACKGROUND

Patient-reported outcome measures (PROMs) are increasingly used as quality benchmark in total hip and knee arthroplasty (THA; TKA) due to bundled payment systems that aim to provide a patient-centered, value-based treatment approach. However, there is a paucity of predictive tools for postoperative PROMs. Therefore, this study aimed to develop and validate machine learning models for the prediction of numerous patient-reported outcome measures following primary hip and knee total joint arthroplasty.

METHODS

A total of 4526 consecutive patients (2137 THA; 2389 TKA) who underwent primary hip and knee total joint arthroplasty and completed both pre- and postoperative PROM scores was evaluated in this study. The following PROM scores were included for analysis: HOOS-PS, KOOS-PS, Physical Function SF10A, PROMIS SF Physical and PROMIS SF Mental. Patient charts were manually reviewed to identify patient demographics and surgical variables associated with postoperative PROM scores. Four machine learning algorithms were developed to predict postoperative PROMs following hip and knee total joint arthroplasty. Model assessment was performed through discrimination, calibration and decision curve analysis.

RESULTS

The factors most significantly associated with the prediction of postoperative PROMs include preoperative PROM scores, Charlson Comorbidity Index, American Society of Anaesthesiology score, insurance status, age, length of hospital stay, body mass index and ethnicity. The four machine learning models all achieved excellent performance across discrimination (AUC > 0.83), calibration and decision curve analysis.

CONCLUSION

This study developed machine learning models for the prediction of patient-reported outcome measures at 1-year following primary hip and knee total joint arthroplasty. The study findings show excellent performance on discrimination, calibration and decision curve analysis for all four machine learning models, highlighting the potential of these models in clinical practice to inform patients prior to surgery regarding their expectations of postoperative functional outcomes following primary hip and knee total joint arthroplasty.

LEVEL OF EVIDENCE

Level III, case control retrospective analysis.