Skip to content
Open access

Development and validation of machine learning models for predicting rehabilitation non-response after knee arthroplasty

Sep 2026 · Frontiers in Rehabilitation Sciences · Vol 7 · 0 citations · 75 references
Medicine

TL;DR

ML can predict MCID-based non-response after TKA rehabilitation using routinely collected admission data and externally validate ML models to predict MCID-based non-response at discharge.

Abstract

Introduction Structured rehabilitation after total knee arthroplasty (TKA) effectively improves health-related quality of life (HRQoL) and function, yet some patients fail to achieve minimal clinically important differences (MCIDs). Machine-learning (ML) based prediction models offer one way to identify those patients. We aim to develop and externally validate ML models to predict MCID-based non-response at discharge. Methods Registry data from four Austrian rehabilitation centres (N = 5,463; 2018–2024), were used to predict non-response in a global (EQ-5D, n = 4,032), and an indication-specific patient-reported outcome measure (WOMAC, n = 4,213) and a performance test (Timed Up and Go Test - TUG, n = 3,354). Outcomes were dichotomized applying a distribution-based MCID and predicted using automated ML ensemble algorithms. Model performance was assessed in independent test data. Results Models predicted non-response with good discrimination (AUCs: TUG 0.771, WOMAC 0.704, EQ-5D 0.770); and varying calibration (TUG: acceptable, WOMAC: good, EQ-5D: poor). Admission values were the most important predictors, with better values resulting in a higher likelihood of not achieving a MCID. Discussion ML can predict MCID-based non-response after TKA rehabilitation using routinely collected admission data. Baseline status is a dominant driver, highlighting ceiling effects and the potential for bias, as well as the need for more precise outcome definitions and the search for suitable, independent predictors. Clinicians could use ML-based risk estimates to identify likely non-responders early, support personalized expectation management, and tailor therapy intensity or content. Translating these tools to practice will require prospective validation and integration into clinical workflows.

Read PDF

Similar papers

Open access Jan 2026

Development and Validation of a Machine Learning–Based Prediction of Chronic Postsurgical Pain Following Total Hip and Knee Arthroplasty: An Exploratory Study

Introduction Chronic postsurgical pain (CPSP) is a concern following total hip arthroplasty (THA) and total knee arthroplasty (TKA), substantially diminishing surgical benefits. We aimed to develop a machine learning (ML) prediction model for risk of developing CPSP. Methods This cohort study included 383 patients recr...

Yu-Le Cao, Ying-Hua Hu, Tian-Lun Gong et al. · 0 citations
Open access Nov 2026

A preliminary investigation into operationalizing machine learning for hip replacement outcomes: predicting OHS and EQ-5D VAS in Wales

Wales has an extensive program for collecting patient-reported outcome (PRO) measures data, and as a country with a population that generally views artificial intelligence use in healthcare positively, the development of machine learning (ML) models for patient outcome prediction offers an opportunity to advance value-...

Aura Frizzati, M. Pruski, Kathleen L. Withers et al. · 0 citations
Open access Sep 2026

Explainable Gradient Boosting Machine Learning for Predicting Early Functional Recovery and Hospital Discharge After Hip and Knee Arthroplasty

Findings indicate that gradient boosting models based on routinely collected clinical variables can provide interpretable and clinically useful predictions to support individualized rehabilitation planning and discharge management after lower-limb arthroplasty.

Mattia Morri, Monica Guberti, L. Verzellesi et al. · 0 citations
Open access Oct 2026

TP3.1 Moderate Predictive Ability of Machine Learning for Achievement of Minimal Clinically Important Difference for the Pain and Healthy Utility Scores after Hip Arthroscopy: Analysis From the Femoroacetabular Impingement RandomiSed Controlled Trial (FIRST) and Embedded Prospective Cohort

Abstract Background To predict achievement of the minimal clinically important difference (MCID) for the Visual Analogue Scale (VAS) and EuroQol-5D (EQ-5D) score at six and 12 months using both logistic regression and machine learning models. Methods This analysis used data from the Femoroacetabular Impingement Randomi...

Prushoth Vivekanantha, J. Kay, N. Simunovic et al. · 0 citations
Open access Sep 2026

Determination of candidate predictors for chiropractic treatment outcome of spinal pain using a machine learning framework for small datasets.

This explorative study suggests that the current ML framework may identify candidate predictors of chiropractic treatment outcome in spinal pain from a small but phenotypically rich dataset given the performance drop between LOOCV and ensemble CV.

M. Meier, B. Wirth, Martina Wehrli et al. · 0 citations
Oct 2026

Development and internal validation of a conditional failure-to-rescue prediction model after surgery for metastatic spine disease.

OBJECTIVE The aim of this study was to develop and internally validate an optimal patient-level prediction model for conditional failure to rescue (cFTR) after surgery for spinal metastases. METHODS The authors performed a retrospective analysis of the American College of Surgeons National Surgical Quality Improvemen...

Esli Nájera-Samaniego, A. Bangash, V. Cao et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.