Related Experiment Video
Updated: Jun 1, 2025
Novel Diagnostics in Revision Arthroplasty: Implant Sonication and Multiplex Polymerase Chain Reaction
Published on: December 3, 2017
Machine learning to predict periprosthetic joint infections following primary total hip arthroplasty using a national
Mehdi S Salimy1, Anirudh Buddhiraju1, Tony L-W Chen1
1Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, 55 Fruit Street, Boston, MA, 02114, USA.
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.
Insights
Machine learning accurately predicts periprosthetic joint infection (PJI) after hip replacement. Key risk factors include longer hospital stays, higher patient weight, and specific pre-operative lab values, aiding in better patient counseling and outcomes.
Area of Science:
- Orthopedic surgery
- Medical informatics
- Machine learning in healthcare
Background:
- Periprosthetic joint infection (PJI) is a significant complication after total hip arthroplasty (THA).
- Existing risk calculators for PJI lack machine learning (ML) integration.
- There is a need for accurate ML-driven tools to identify PJI risk factors.
Purpose of the Study:
- To develop and validate an ML algorithm for predicting PJI risk after primary THA.
- To identify key risk factors contributing to PJI development.
- To utilize a national surgical database for robust model development.
Main Methods:
- Analysis of 51,053 primary THA patients from the ACS-NSQIP database (2013-2020).
- Collection and evaluation of demographic, preoperative, intraoperative, and postoperative data.
- Development and assessment of five ML models, including performance metrics like AUC and Brier score.
Main Results:
- The histogram-based gradient boosting (HGB) model showed strong predictive ability for PJI (AUC=0.88).
- Key predictors identified include: prolonged length of stay (>3 days), high patient weight (>94.3 kg), ASA class 4+, low preoperative platelet count (<249,890/mm3), and low preoperative sodium (<139.5 mEq/L).
- The model demonstrated good calibration and discrimination.
Conclusions:
- A highly specific ML model was developed to predict patient-specific PJI risk post-THA.
- Identified risk factors can guide surgeons in counseling high-risk patients.
- Optimizing resource use and improving surgical outcomes are potential benefits.
