Machine Learning–Based prediction of complications and residual pain after total knee arthroplasty
An XGBoost-based ML model incorporating AAHKS-defined risk factors showed moderate effectiveness in predicting postoperative complications following TKA. However, the model was unable to reliably predict residual pain. These findings underscore the need for broader inclusion of joint-specific variables and imaging data in future risk adjustment frameworks to enhance personalized care in knee arthroplasty.
Authors
- Rüdiger von Eisenhart‐Rothe (ORCID: https://orcid.org/0000-0002-2352-1357)
- Heiko Graichen (ORCID: https://orcid.org/0000-0001-6095-3186)
- Igor Lazic (ORCID: https://orcid.org/0000-0002-7403-5535)
- Aqeel Gillani
- Florian Hinterwimmer (ORCID: https://orcid.org/0000-0002-0273-0643)
- Dirk Müller (ORCID: https://orcid.org/0009-0001-5592-5989)
- Anabel Arber
Institutions
- TUM Klinikum (DE)
- Asklepios Orthopädische Klinik Lindenlohe (DE)
- Technical University of Munich (DE)
Publication Details
- Journal
- Journal of Orthopaedics
- Published
- 2025-09-30
- DOI
- https://doi.org/10.1016/j.jor.2025.08.038
- Citations
- 1
- Primary Topic
- Total Knee Arthroplasty Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 2.01