Machine learning to predict periprosthetic joint infections following primary total hip arthroplasty using a national database

Abstract

Introduction

Periprosthetic joint infection (PJI) following total hip arthroplasty (THA) remains a devastating complication for patients and surgeons. Given the implications of these infections and the current paucity of risk calculators utilizing machine learning (ML), this study aimed to develop an ML algorithm that could accurately identify risk factors for developing a PJI following primary THA using a national database.

Materials and methods

A total of 51,053 patients who underwent primary THA between 2013 and 2020 were identified using the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database. Demographic, preoperative, intraoperative, and immediate postoperative outcomes were collected. Five ML models were created. The receiver operating characteristic curves, the area under the curve (AUC), calibration plots, slopes, intercepts, and Brier scores were evaluated.

Results

The histogram-based gradient boosting (HGB) model demonstrated good PJI discriminatory ability with an AUC of 0.88. The test-specific metrics supported the model’s performance and validation in predicting PJI (calibration curve slope: 0.79; intercept: 0.32; Brier score: 0.007). The top five predictors of PJI were the length of stay (> 3 days), patient weight at the time of surgery (> 94.3 kg), an American Society of Anesthesiologists (ASA) class of 4 or higher, preoperative platelet count (< 249,890/mm3), and preoperative sodium (< 139.5 mEq/L).

Conclusion

This study developed a highly specific ML model that could predict patient-specific PJI development following primary THA. Considering the feature importance of the top predictors of infection, surgeons should counsel at-risk patients to optimize resource utilization and potentially improve surgical outcomes.