Racial and Ethnic Disparities in Predictive Accuracy of Machine Learning Algorithms Developed Using a National Database for 30-Day Complications Following Total Joint Arthroplasty

Abstract

BackgroundWhile predictive capabilities of machine learning (ML) algorithms for hip and knee total joint arthroplasty (TJA) have been demonstrated in previous studies, their performance in racial and ethnic minority patients has not been investigated. This study aimed to assess the performance of ML algorithms in predicting 30-day complications following TJA in racial and ethnic minority patients. MethodsA total of 267,194 patients undergoing primary TJA between 2013 and 2020 were identified from a national outcomes database. The patient cohort was stratified according to race, with further sub-stratification into Hispanic or non-Hispanic ethnicity. There were two ML algorithms, histogram-based gradient boosting (HGB), and random forest (RF), that were modeled to predict 30-day complications following primary TJA in the overall population. They were subsequently assessed in each racial and ethnic subcohort using discrimination, calibration, accuracy, and potential clinical usefulness. ResultsBoth models achieved excellent (Area under the curve (AUC) > 0.8) discrimination (AUCHGB = AUCRF = 0.86), calibration, and accuracy (HGB: slope = 1.00, intercept = -0.03, Brier score = 0.12; RF: slope = 0.97, intercept = 0.02, Brier score = 0.12) in the non-Hispanic White population (N = 224,073). Discrimination decreased in the White Hispanic (N = 10,429; AUC = 0.75 to 0.76), Black (N = 25,116; AUC = 0.77), Black Hispanic (N = 240; AUC = 0.78), Asian non-Hispanic (N = 4,809; AUC = 0.78 to 0.79), and overall (N = 267,194; AUC = 0.75 to 0.76) cohorts, but remained well-calibrated. We noted the poorest model discrimination (N = 1,870; AUC = 0.67 to 0.68) and calibration in the American-Indian cohort. ConclusionThe ML algorithms demonstrate an inferior predictive ability for 30-day complications following primary TJA in racial and ethnic minorities when trained on existing healthcare big data. This may be attributed to the disproportionate underrepresentation of minority groups within these databases, as demonstrated by the smaller sample sizes available to train the machine learning models. The ML models developed using smaller datasets (e.g., in racial and ethnic minorities) may not be as accurate as larger datasets, highlighting the need for equity-conscious model development.