In this section
@article{Alagha:2025,
author = {Alagha, MA and Cobb, J and Liddle, A and Malchau, H and Mohaddes, M and Rolfson, O},
journal = {Bone & Joint Open},
title = {Prediction of quality-of-life improvement after total hip arthroplasty - A simplified and internally validated model based on 82,526 total hip replacements from the Swedish Arthroplasty Register},
year = {2025}
}
TY - JOUR
AB - Introduction: Pain and poor health-related quality of life measures serve as the primary indication for primary elective total hip replacement (THR). It remains challenging to predict whether THR delivers the patient-anticipated improvements. Our study aimed to develop and validate statistical and machine learning prediction models of 1-year clinical improvement in patient-reported outcome measures (PROMs) after elective THR.Methods: We included 82,526 patients with primary elective THRs from the Swedish Arthroplasty Register (SAR) for forecasting one-year improvements in the EQ-5D index, EQ-VAS and combined EQ-5D/EQ-VAS scores. Two Minimal Clinically Important Difference (MCID) thresholds were applied for the EQ-5D index score based on the Standardised Response Mean (SRM = 0.196) and Capacity of Benefit (CoB = 0.428) approaches. MCIDcut off for the EQ-VAS was set to 7.81. Twenty-one features were used to feed the models. To avoid estimates bias we eliminated missing data. Model performance was tested using the area under the receiver operating characteristic curve (AUC), and features importance were identified in the best performing algorithm.Results: Applying the SRM MCID, approximately two-thirds of patients reported one-year improvements in EQ-5D index (66.3%) and EQ-VAS (69.1%). The improvement rate decreased to 51.7% when we combined improvements in both outcomes. A higher CoB cut-off for EQ-5D index yielded lower rates (~40% for the EQ-5D index and 31.3% for the combined measure). The Gradient boosting machine (GBM) consistently outperformed other models by a narrow margin in predicting significant clinical improvements in one-year PROMs and achieved a good to excellent binary discriminative power (AUCs range 0.80 – 0.97%). Pre-operative PROMs, EQ-5D index, EQ-VAS and Charnley classification, along with age, collectively contributed to over 80% of the algorithmic power in the ensemble GBM model.Conclusion: We developed an interpretable machine learning
AU - Alagha,MA
AU - Cobb,J
AU - Liddle,A
AU - Malchau,H
AU - Mohaddes,M
AU - Rolfson,O
PY - 2025///
SN - 2633-1462
TI - Prediction of quality-of-life improvement after total hip arthroplasty - A simplified and internally validated model based on 82,526 total hip replacements from the Swedish Arthroplasty Register
T2 - Bone & Joint Open
ER -