Nair Abhinav, Alagha M Abdulhadi, Cobb Justin, Jones Gareth
MSk Lab, Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UK.
Data Science Institute, London School of Economics and Political Science, London, UK.
Bioengineering (Basel). 2024 Aug 12;11(8):824. doi: 10.3390/bioengineering11080824.
Knee osteoarthritis (OA) affects over 650 million patients worldwide. Total knee replacement is aimed at end-stage OA to relieve symptoms of pain, stiffness and reduced mobility. However, the role of imaging modalities in monitoring symptomatic disease progression remains unclear. This study aimed to compare machine learning (ML) models, with and without imaging features, in predicting the two-year Western Ontario and McMaster Universities Arthritis Index (WOMAC) score for knee OA patients. We included 2408 patients from the Osteoarthritis Initiative (OAI) database, with 629 patients from the Multicenter Osteoarthritis Study (MOST) database. The clinical dataset included 18 clinical features, while the imaging dataset contained an additional 10 imaging features. Minimal Clinically Important Difference (MCID) was set to 24, reflecting meaningful physical impairment. Clinical and imaging dataset models produced similar area under curve (AUC) scores, highlighting low differences in performance AUC < 0.025). For both clinical and imaging datasets, Gradient Boosting Machine (GBM) models performed the best in the external validation, with a clinically acceptable AUC of 0.734 (95% CI 0.687-0.781) and 0.747 (95% CI 0.701-0.792), respectively. The five features identified included educational background, family history of osteoarthritis, co-morbidities, use of osteoporosis medications and previous knee procedures. This is the first study to demonstrate that ML models achieve comparable performance with and without imaging features.
膝关节骨关节炎（OA）在全球影响着超过6.5亿患者。全膝关节置换术旨在治疗终末期OA，以缓解疼痛、僵硬和活动能力下降等症状。然而，成像模态在监测症状性疾病进展中的作用仍不明确。本研究旨在比较有无成像特征的机器学习（ML）模型在预测膝关节OA患者两年的西安大略和麦克马斯特大学骨关节炎指数（WOMAC）评分方面的表现。我们纳入了来自骨关节炎倡议（OAI）数据库的2408名患者，以及来自多中心骨关节炎研究（MOST）数据库的629名患者。临床数据集包括18个临床特征，而成像数据集还包含另外10个成像特征。最小临床重要差异（MCID）设定为24，反映有意义的身体损伤。临床和成像数据集模型产生了相似的曲线下面积（AUC）分数，突出了性能差异较小（AUC < 0.025）。对于临床和成像数据集，梯度提升机（GBM）模型在外部验证中表现最佳，临床可接受的AUC分别为0.734（95%CI 0.687 - 0.781）和0.747（95%CI 0.701 - 0.792）。确定的五个特征包括教育背景、骨关节炎家族史、合并症、骨质疏松药物使用情况和既往膝关节手术史。这是第一项证明有无成像特征的ML模型性能相当的研究。
