Related Experiment Video
Updated: Jun 26, 2025
Author Spotlight: Advancing Research on Candida albicans Biofilm-Associated Prosthetic Joint Infections
Published on: February 2, 2024
A machine learning-based model for "In-time" prediction of periprosthetic joint infection
Weishen Chen1,2, Xuantao Hu1,2, Chen Gu3
1Department of Joint Surgery, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, China.
Background:
Previous criteria had limited value in early diagnosis of periprosthetic joint infection (PJI). Here, we constructed a novel machine learning (ML)-derived, "in-time" diagnostic system for PJI and proved its validity.
Methods:
We filtered "in-time" diagnostic indicators reported in the literature based on our continuous retrospective cohort of PJI and aseptic prosthetic loosening patients. With the indicators, we developed a two-level ML model with six base learners including Elastic Net, Linear Support Vector Machine, Kernel Support Vector Machine, Extra Trees, Light Gradient Boosting Machine and Multilayer Perceptron), and one meta-learner, Ensemble Learning of Weighted Voting. The prediction performance of this model was compared with those of previous diagnostic criteria (International Consensus Meeting in 2018 (ICM 2018), etc.). Another prospective cohort was used for internal validation. Based on our ML model, a user-friendly web tool was developed for swift PJI diagnosis in clinical practice.
Results:
A total of 254 patients (199 for development and 55 for validation cohort) were included in this study with 38.2% of them diagnosed as PJI. We included 21 widely accessible features including imaging indicators (X-ray and CT) in the model. The sensitivity and accuracy of our ML model were significantly higher than ICM 2018 in development cohort (90.6% vs. 76.1%, P = 0.032; 94.5% vs. 86.7%, P = 0.020), which was supported by internal validation cohort (84.2% vs. 78.6%; 94.6% vs. 81.8%).
Conclusions:
Our novel ML-derived PJI "in-time" diagnostic system demonstrated significantly improved diagnostic potency for surgical decision-making compared with the commonly used criteria. Moreover, our web-based tool greatly assisted surgeons in distinguishing PJI patients comprehensively.
Level Of Evidence:
Diagnostic Level III.
Insights
A new machine learning (ML) diagnostic system improves periprosthetic joint infection (PJI) detection. This ML model offers higher accuracy than current criteria, aiding surgical decisions.
Area of Science:
- Orthopedic Surgery
- Medical Diagnostics
- Machine Learning in Healthcare
Background:
- Existing criteria for diagnosing periprosthetic joint infection (PJI) have limitations in early detection.
- There is a need for more accurate and timely diagnostic tools for PJI.
Purpose of the Study:
- To develop and validate a novel machine learning (ML)-derived diagnostic system for the early detection of PJI.
- To compare the performance of the ML system against established diagnostic criteria.
Main Methods:
- A two-level ML model was developed using six base learners and one meta-learner, trained on retrospective PJI patient data.
- Diagnostic indicators were filtered from literature and a retrospective cohort.
- The model incorporated 21 features, including imaging (X-ray, CT), and was validated on a separate prospective cohort.
- A user-friendly web tool was created based on the ML model.
Main Results:
- The ML model demonstrated significantly higher sensitivity (90.6% vs. 76.1%) and accuracy (94.5% vs. 86.7%) compared to the International Consensus Meeting 2018 (ICM 2018) criteria in the development cohort.
- Internal validation confirmed the ML model's superior performance (84.2% vs. 78.6% sensitivity; 94.6% vs. 81.8% accuracy).
Conclusions:
- The novel ML-derived PJI diagnostic system shows improved diagnostic accuracy and potency for surgical decision-making.
- The developed web-based tool effectively assists surgeons in comprehensively diagnosing PJI.
More Related Videos
10:35Novel Diagnostics in Revision Arthroplasty: Implant Sonication and Multiplex Polymerase Chain Reaction
Published on: December 3, 2017
18:40Combined In vivo Optical and µCT Imaging to Monitor Infection, Inflammation, and Bone Anatomy in an Orthopaedic Implant Infection in Mice
Published on: October 16, 2014