MS Center Amsterdam, Anatomy and Neurosciences, Vrije Universiteit Amsterdam, Amsterdam Neuroscience, Amsterdam UMC Location VUmc, Amsterdam, The Netherlands.
Department of Psychiatry and Psychotherapy, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany.
J Neurol. 2024 Aug;271(8):5577-5589. doi: 10.1007/s00415-024-12507-w. Epub 2024 Jun 23.
Robust predictive models of clinical impairment and worsening in multiple sclerosis (MS) are needed to identify patients at risk and optimize treatment strategies.
To evaluate whether machine learning (ML) methods can classify clinical impairment and predict worsening in people with MS (pwMS) and, if so, which combination of clinical and magnetic resonance imaging (MRI) features and ML algorithm is optimal.
We used baseline clinical and structural MRI data from two MS cohorts (Berlin: n = 125, Amsterdam: n = 330) to evaluate the capability of five ML models in classifying clinical impairment at baseline and predicting future clinical worsening over a follow-up of 2 and 5 years. Clinical worsening was defined by increases in the Expanded Disability Status Scale (EDSS), Timed 25-Foot Walk Test (T25FW), 9-Hole Peg Test (9HPT), or Symbol Digit Modalities Test (SDMT). Different combinations of clinical and volumetric MRI measures were systematically assessed in predicting clinical outcomes. ML models were evaluated using Monte Carlo cross-validation, area under the curve (AUC), and permutation testing to assess significance.
The ML models significantly determined clinical impairment at baseline for the Amsterdam cohort, but did not reach significance for predicting clinical worsening over a follow-up of 2 and 5 years. High disability (EDSS ≥ 4) was best determined by a support vector machine (SVM) classifier using clinical and global MRI volumes (AUC = 0.83 ± 0.07, p = 0.015). Impaired cognition (SDMT Z-score ≤ -1.5) was best determined by a SVM using regional MRI volumes (thalamus, ventricles, lesions, and hippocampus), reaching an AUC of 0.73 ± 0.04 (p = 0.008).
ML models could aid in classifying pwMS with clinical impairment and identify relevant biomarkers, but prediction of clinical worsening is an unmet need.
需要稳健的预测模型来识别多发性硬化症（MS）患者的临床损伤和恶化风险，并优化治疗策略。
评估机器学习（ML）方法是否可以对 MS 患者（pwMS）进行临床损伤分类和预测恶化，并确定最佳的临床和磁共振成像（MRI）特征组合以及 ML 算法。
我们使用来自两个 MS 队列（柏林：n=125，阿姆斯特丹：n=330）的基线临床和结构 MRI 数据，评估了五种 ML 模型在基线时对临床损伤进行分类以及在 2 年和 5 年的随访中预测未来临床恶化的能力。临床恶化定义为扩展残疾状况量表（EDSS）、定时 25 英尺步行测试（T25FW）、9 孔钉测试（9HPT）或符号数字模态测试（SDMT）的增加。系统评估了不同的临床和容积 MRI 测量组合对预测临床结局的作用。使用蒙特卡罗交叉验证、曲线下面积（AUC）和置换检验来评估 ML 模型的性能，以评估其显著性。
ML 模型显著确定了阿姆斯特丹队列的基线临床损伤，但未达到在 2 年和 5 年随访中预测临床恶化的显著性。使用支持向量机（SVM）分类器，结合临床和全局 MRI 容积，可最佳确定高残疾（EDSS≥4）（AUC=0.83±0.07，p=0.015）。使用 SVM 结合区域 MRI 容积（丘脑、脑室、病变和海马体），最佳确定认知障碍（SDMT Z 分数≤-1.5），AUC 为 0.73±0.04（p=0.008）。
ML 模型可以辅助分类 pwMS 的临床损伤，并识别相关生物标志物，但对临床恶化的预测仍存在未满足的需求。
