Department of Rheumatology & Clinical Immunology, University Medical Center Utrecht, Utrecht University, Utrecht.
Department of Rheumatology.
Rheumatology (Oxford). 2022 Dec 23;62(1):147-157. doi: 10.1093/rheumatology/keac292.
The IMI-APPROACH knee osteoarthritis study used machine learning (ML) to predict structural and/or pain progression, expressed by a structural (S) and pain (P) predicted-progression score, to select patients from existing cohorts. This study evaluates the actual 2-year progression within the IMI-APPROACH, in relation to the predicted-progression scores.
Actual structural progression was measured using minimum joint space width (minJSW). Actual pain (progression) was evaluated using the Knee injury and Osteoarthritis Outcomes Score (KOOS) pain questionnaire. Progression was presented as actual change (Δ) after 2 years, and as progression over 2 years based on a per patient fitted regression line using 0, 0.5, 1 and 2-year values. Differences in predicted-progression scores between actual progressors and non-progressors were evaluated. Receiver operating characteristic (ROC) curves were constructed and corresponding area under the curve (AUC) reported. Using Youden's index, optimal cut-offs were chosen to enable evaluation of both predicted-progression scores to identify actual progressors.
Actual structural progressors were initially assigned higher S predicted-progression scores compared with structural non-progressors. Likewise, actual pain progressors were assigned higher P predicted-progression scores compared with pain non-progressors. The AUC-ROC for the S predicted-progression score to identify actual structural progressors was poor (0.612 and 0.599 for Δ and regression minJSW, respectively). The AUC-ROC for the P predicted-progression score to identify actual pain progressors were good (0.817 and 0.830 for Δ and regression KOOS pain, respectively).
The S and P predicted-progression scores as provided by the ML models developed and used for the selection of IMI-APPROACH patients were to some degree able to distinguish between actual progressors and non-progressors.
ClinicalTrials.gov, https://clinicaltrials.gov, NCT03883568.
IMI-APPROACH 膝骨关节炎研究使用机器学习（ML）来预测结构和/或疼痛进展，用结构（S）和疼痛（P）预测进展评分来表达，从现有队列中选择患者。本研究评估了 IMI-APPROACH 中实际的 2 年进展情况，与预测进展评分相关。
使用最小关节间隙宽度（minJSW）测量实际的结构进展。使用膝关节损伤和骨关节炎结果评分（KOOS）疼痛问卷评估实际疼痛（进展）。进展表现为 2 年后的实际变化（Δ），以及基于患者拟合回归线的 2 年内进展，使用 0、0.5、1 和 2 年的值。评估实际进展者和非进展者之间预测进展评分的差异。构建了接收者操作特征（ROC）曲线，并报告了相应的曲线下面积（AUC）。使用 Youden 指数选择最佳截断值，以评估预测进展评分来识别实际进展者。
最初，与结构无进展者相比，实际结构进展者被分配更高的 S 预测进展评分。同样，与疼痛无进展者相比，实际疼痛进展者被分配更高的 P 预测进展评分。S 预测进展评分识别实际结构进展者的 AUC-ROC 较差（Δ和回归 minJSW 分别为 0.612 和 0.599）。P 预测进展评分识别实际疼痛进展者的 AUC-ROC 较好（Δ和回归 KOOS 疼痛分别为 0.817 和 0.830）。
由用于选择 IMI-APPROACH 患者的 ML 模型提供的 S 和 P 预测进展评分在某种程度上能够区分实际进展者和非进展者。
ClinicalTrials.gov，https://clinicaltrials.gov，NCT03883568。
