Machine learning-optimized Combinatorial MRI scale (COMRISv2) correlates highly with cognitive and physical disability scales in Multiple Sclerosis patients.
Machine learning-optimized Combinatorial MRI scale (COMRISv2) correlates highly with cognitive and physical disability scales in Multiple Sclerosis patients.
复制标题
DOI：
10.3389/fradi.2022.1026442
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Bielekova, Bibiana
中科院分区：
文献类型：
--
作者：
Kelly, Erin;Varosanec, Mihael;Kosa, Peter;Prchkovska, Vesna;Moreno-Dominguez, David;Bielekova, Bibiana
在多发性硬化症（MS）患者中，中枢神经系统组织破坏的复合MRI量表与临床结局的相关性比其单个组分更强。使用机器学习（ML），我们之前仅从半定量（半qMRI）生物标志物开发了组合MRI量表（COMRISv 1）。在这里，我们询问了通过包含定量（qMRI）体积特征和采用更强大的ML算法，COMRISv 2可能会变得更好。将前瞻性获得的MS患者分为训练（n = 172）和验证（n = 83）队列，进行脑MRI成像和临床评价。将神经系统检查转录至自动计算残疾量表的NeurEx™ App。采用病灶-TOADS算法计算qMRI特征。修改的随机森林管道选择用于训练群组中的最佳模型的生物标志物。COMRISv 2模型验证了与认知障碍的中度相关性[斯皮尔曼Rho = 0.674;林一致性系数（CCC）= 0.458; p < 0.001]和与身体残疾的强相关性（斯皮尔曼Rho = 0.830-0.852; CCC = 0.789-0.823; p < 0.001）。NeurEx导致了最强的COMRISv 2模型。增加qMRI特征仅增强了认知障碍模型的性能，可能是因为半qMRI生物标志物测量幕下损伤的准确性更高。COMRISv 2模型预测MS的大多数粒度临床量表，具有显著的标准有效性，扩大了临床数据缺失队列的科学利用。
Composite MRI scales of central nervous system tissue destruction correlate stronger with clinical outcomes than their individual components in multiple sclerosis (MS) patients. Using machine learning (ML), we previously developed Combinatorial MRI scale (COMRISv1) solely from semi-quantitative (semi-qMRI) biomarkers. Here, we asked how much better COMRISv2 might become with the inclusion of quantitative (qMRI) volumetric features and employment of more powerful ML algorithm. The prospectively acquired MS patients, divided into training (n = 172) and validation (n = 83) cohorts underwent brain MRI imaging and clinical evaluation. Neurological examination was transcribed to NeurEx™ App that automatically computes disability scales. qMRI features were computed by lesion-TOADS algorithm. Modified random forest pipeline selected biomarkers for optimal model(s) in the training cohort. COMRISv2 models validated moderate correlation with cognitive disability [Spearman Rho = 0.674; Lin's concordance coefficient (CCC) = 0.458; p < 0.001] and strong correlations with physical disability (Spearman Rho = 0.830–0.852; CCC = 0.789–0.823; p < 0.001). The NeurEx led to the strongest COMRISv2 model. Addition of qMRI features enhanced performance only of cognitive disability model, likely because semi-qMRI biomarkers measure infratentorial injury with greater accuracy. COMRISv2 models predict most granular clinical scales in MS with remarkable criterion validity, expanding scientific utilization of cohorts with missing clinical data.
登录
查看更多内容
影响因子：
3.4
作者：
Andelova, Michaela;Uher, Tomas;Vaneckova, Manuela
通讯作者：
Vaneckova, Manuela
影响因子：
9.9
作者：
Mainero, C;De Stefano, N;Filippi, M
通讯作者：
Filippi, M
影响因子：
11.2
作者：
Polman CH;Reingold SC;Banwell B;Clanet M;Cohen JA;Filippi M;Fujihara K;Havrdova E;Hutchinson M;Kappos L;Lublin FD;Montalban X;O'Connor P;Sandberg-Wollheim M;Thompson AJ;Waubant E;Weinshenker B;Wolinsky JS
通讯作者：
Wolinsky JS
影响因子：
9.9
作者：
FILIPPI, M;PATY, DW;MILLER, DH
通讯作者：
MILLER, DH
影响因子：
9.9
作者：
Ebers, G. C.;Heigenhauser, L.;Noseworthy, J. H.
通讯作者：
Noseworthy, J. H.