Preoperatively predicting failure to achieve the minimum clinically important difference and substantial clinical benefit for total knee arthroplasty patients using machine learning
Machine-learning models were able to identify patients at risk of failure to achieve the threshold-based metrics and relevant preoperative factors. As such, these models may be used to both improve shared decision-making and help create risk-stratification tools to improve quality assessment of surgical outcomes.
Authors
- Xiang Zhong (ORCID: https://orcid.org/0000-0002-6214-5876)
- Emilie N. Miley (ORCID: https://orcid.org/0000-0001-9286-2115)
- Chancellor F. Gray (ORCID: https://orcid.org/0000-0001-8312-3695)
- Jaeyoung Park (ORCID: https://orcid.org/0000-0002-9586-5570)
Institutions
- Florida State University (US)
- University of Central Florida (US)
- University of Florida (US)
- Tallahassee Orthopedic Clinic (US)
- The Orthopaedic Institute (US)
Publication Details
- Journal
- Knee Surgery and Related Research
- Published
- 2025-09-10
- DOI
- https://doi.org/10.1186/s43019-025-00289-y
- Primary Topic
- Total Knee Arthroplasty Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 0.00