An interpretable knee replacement risk assessment system for osteoarthritis patients.

Objective: Knee osteoarthritis (OA) is a complex disease with heterogeneous representations. Although it is modifiable to prevention and early treatment, there still lacks a reliable and accurate prognostic tool. Hence, we aim to develop a quantitative and self-administrable knee replacement (KR) risk stratification system for knee osteoarthritis (KOA) patients with clinical features. Method: A total of 14 baseline features were extracted from 9592 cases in the Osteoarthritis Initiative (OAI) cohort. A survival model was constructed using the Random Survival Forests algorithm. The prediction performance was evaluated with the concordance index (C-index) and average receiver operating characteristic curve (AUC). A three-class KR risk stratification system was built to differentiate three distinct KR-free survival groups. Thereafter, Shapley Additive Explanations (SHAP) was introduced for model explanation. Results: KR incidence was accurately predicted by the model with a C-index of 0.770 (±0.0215) and an average AUC of 0.807 (±0.0181) with 14 clinical features. Three distinct survival groups were observed from the ten-point KR risk stratification system with a four-year KR rate of 0.79%, 5.78%, and 16.2% from the low, medium, and high-risk groups respectively. KR is mainly caused by pain medication use, age, surgery history, diabetes, and a high body mass index, as revealed by SHAP. Conclusion: A self-administrable and interpretable KR survival model was developed, underscoring a KR risk scoring system to stratify KOA patients. It will encourage regular self-assessments within the community and facilitate personalised healthcare for both primary and secondary prevention of KOA.

A machine learning-based approach to decipher multi-etiology of knee osteoarthritis onset and deterioration.

Objectives: By deploying a novel combination of machine learning approaches, we aim to investigate the contributions of each local and systemic risk factors in multi-etiology of knee osteoarthritis (KOA) to disease onset and deterioration. Methods: A machine-learning-based KOA progression prediction model is developed using the data from the National Institute of Health Osteoarthritis Biomarkers Consortium. According to Kellgren-Lawrence (KL) grade of plain radiographs at baseline, the subjects are divided into either KOA onset or deterioration study groups. The disease progression is defined as the changes in both joint space width (JSW) and WOMAC pain score. In addition to radiographic and symptomatic data, the anthropological particulars, history of the knee injury and surgery, metabolic syndrome and living habits were deployed in a multi-layer perceptron (MLP) to predict disease progression in each study group. The relative contributions of each risk factors were weighted via DeepLIFT gradient. Additionally, statistical interactions among risk factors were identified compared. Results: Our model achieved AUC of 0.843 (95% CI 0.824, 0.862) and 0.765 (95% CI 0.756, 0.774) in prediction of KOA onset and deterioration, respectively. For KOA onset prediction, history of injury has attained the highest DeepLIFT gradient except medial joint space narrowing; while for KOA deterioration prediction, diabetes and habit of smoking obtained second and third highest gradients respectively aside from medial joint space narrowing, surpassing the impact of the injury. Conclusion: We developed a machine learning workflow which effectively dissects the risk factors' contributions and their mutual interactions for onset and deterioration of KOA respectively.