Machine learning to predict incident radiographic knee osteoarthritis over 8 Years using combined MR imaging features, demographics, and clinical factors: data from the Osteoarthritis Initiative.
Machine learning to predict incident radiographic knee osteoarthritis over 8 Years using combined MR imaging features, demographics, and clinical factors: data from the Osteoarthritis Initiative.
复制标题
机器学习预测8年内发生的放射学膝关节骨关节炎，使用组合的MR成像特征，人口统计学和临床因素：来自骨关节炎倡议的数据。
DOI：
10.1016/j.joca.2021.11.007
复制
发表时间：
2022-03
影响因子：
7
通讯作者：
Sohn JH
中科院分区：
文献类型：
--
作者：
Joseph GB;McCulloch CE;Nevitt MC;Link TM;Sohn JH
利用基于MRI的软骨生化成分、膝关节结构、人口统计学以及包括肌肉力量和症状在内的临床预测因子，建立基于机器学习的膝关节放射学骨关节炎(OA)发病8年的预测模型。来自骨关节炎倡议数据库的右膝基线Kellgren Lawrence(KL)0-1级的个体(n=1044)被分析。用3T磁共振成像对膝关节T2软骨进行定量，并获得软骨、半月板和骨髓的全身磁共振成像评分(WORMS)。如果受试者右膝出现KL2-4级骨性关节炎超过8年(n=183)，则结果为真，如果受试者保持KL0-1超过8年(n=861)，则结果为假。我们开发并比较了三个模型：模型1：112个基于骨性关节炎危险因素的预测因素；模型2：基于模型1的特征重要性分数和临床相关性的前十个预测因素；模型3：没有成像预测因素的模型2。我们使用由抵抗数据得出的ROC曲线下面积对模型进行了比较。有10个预测因子的模型(模型2，包括软骨和半月板蠕虫评分和软骨T2)的AUC值(0.772)略低于有112个预测值的模型(模型1：AUC值=0.792，p=0.739)，但与没有MR成像预测因子的模型(模型3，AUC值=0.669，p=0.011)相比，AUC值明显升高。包括人口统计学、症状、肌肉和体力活动评分在内的MRI参数的10项预测模型可以很好地预测8年内发生的放射性骨性关节炎。
To develop a machine learning-based prediction model for incident radiographic osteoarthritis (OA) of the knee over 8 years using MRI-based cartilage biochemical composition and knee joint structure, demographics, and clinical predictors including muscle strength and symptoms. Individuals (n=1044) with baseline Kellgren Lawrence (KL) grade 0–1 in the right knee from the Osteoarthritis Initiative database were analyzed. 3T MRI at baseline was used to quantify knee cartilage T2, and Whole-Organ Magnetic Resonance Imaging Scores (WORMS) were obtained for cartilage, meniscus, and bone marrow. The outcome was set as true if a subject developed KL grade 2–4 OA in the right knee over 8 years (n=183) and false if the subject remained at KL 0–1 over 8 years (n=861). We developed and compared three models: Model 1: 112 predictors based on OA risk factors; Model 2: top ten predictors based on feature importance score from Model 1 and clinical relevance; Model 3: Model 2 without the imaging predictors. We compared the models using the area under the R OC curve derived from holdout data. The 10-predictor model (Model 2, that includes cartilage and meniscus WORMS scores and cartilage T2) had a slightly lower AUC (0.772) compared to the model with 112 predictors (Model 1: AUC=0.792, p=0.739); and had a significantly higher AUC compared to the model without MR imaging predictors (Model 3, AUC=0.669, p=0.011). A 10-predictor model including MRI parameters coupled with demographics, symptoms, muscle, and physical activity scores provides good prediction of incident radiographic OA over 8 years.
登录
查看更多内容
影响因子：
4.7
作者：
Baum, Thomas;Joseph, Gabby B.;Arulanandan, Ahilan;Nardo, Lorenzo;Virayavanich, Warapat;Carballido-Gamio, Julio;Nevitt, Michael C.;Lynch, John;McCulloch, Charles E.;Link, Thomas M.
通讯作者：
Link, Thomas M.
影响因子：
2
作者：
Friedman, JH;Meulman, JJ
通讯作者：
Meulman, JJ
影响因子：
33.7
作者：
Jamshidi, Afshin;Pelletier, Jean-Pierre;Martel-Pelletier, Johanne
通讯作者：
Martel-Pelletier, Johanne
影响因子：
2.7
作者：
Murphy, Louise;Helmick, Charles G.
通讯作者：
Helmick, Charles G.
影响因子：
4.8
作者：
Elith, J.;Leathwick, J. R.;Hastie, T.
通讯作者：
Hastie, T.