Related Experiment Videos
Development of Machine Learning Algorithms Predicting Psychological Distress After Total Joint Arthroplasty
Michelle M Ramirez1, Maggie E Horn2, Steven Z George3
1Duke University School of Medicine, Department of Population Health Sciences, Durham, NC, USA; Duke University School of Medicine, Department of Orthopaedic Surgery, Durham, NC, USA; University of North Carolina-Chapel Hill, Thurston Arthritis Research Center, Department of Medicine, Chapel Hill, NC, USA.
The Journal of Arthroplasty
|May 28, 2026
Summary
Machine learning models can predict psychological distress after total joint arthroplasty (TJA) using preoperative data. The elastic net model showed the best performance, aiding early patient identification for interventions.
Area of Science:
- Orthopedics
- Data Science
- Psychology
Background:
- Psychological distress negatively impacts outcomes following total joint arthroplasty (TJA).
- Predicting high psychological distress preoperatively is crucial for optimizing patient care.
- Machine learning (ML) offers a promising approach to identify at-risk patients.
Purpose of the Study:
- To develop and evaluate ML models for predicting high psychological distress phenotypes.
- Utilize preoperative data exclusively for model development.
- Identify key predictors of psychological distress in TJA patients.
Main Methods:
- Retrospective analysis of 494 patients undergoing hip or knee arthroplasty.
- Latent class analysis of the Optimal Screening for Prediction of Referral and Outcome Yellow Flag (OSPRO-YF) tool to define phenotypes.
- Trained and compared four ML models: elastic net, XGBoost, random forest, and logistic regression.
Main Results:
- 18% of patients exhibited high postoperative psychological distress.
- High distress was linked to lower physical function and higher pain interference (PROMIS).
- The elastic net model achieved the highest Area Under the Curve (AUC) of 0.75.
Conclusions:
- Preoperative data can effectively predict psychological distress after TJA.
- The elastic net model demonstrates superior performance and interpretability.
- Models can facilitate timely interventions, improving TJA outcomes.