Department of Health Sciences and Technology (D-HEST), ETH Zurich, Switzerland; SIB Swiss Institute of Bioinformatics, Switzerland.
Department of Health Sciences and Technology (D-HEST), ETH Zurich, Switzerland; SIB Swiss Institute of Bioinformatics, Switzerland.
Exp Neurol. 2024 Oct;380:114905. doi: 10.1016/j.expneurol.2024.114905. Epub 2024 Aug 3.
Neurological and functional recovery after traumatic spinal cord injury (SCI) is highly challenged by the level of the lesion and the high heterogeneity in severity (different degrees of in/complete SCI) and spinal cord syndromes (hemi-, ant-, central-, and posterior cord). So far outcome predictions in clinical trials are limited in targeting sum motor scores of the upper (UEMS) and lower limb (LEMS) while neglecting that the distribution of motor function is essential for functional outcomes. The development of data-driven prediction models of detailed segmental motor recovery for all spinal segments from the level of lesion towards the lowest motor segments will improve the design of rehabilitation programs and the sensitivity of clinical trials.
This study used acute-phase International Standards for Neurological Classification of SCI exams to forecast 6-month recovery of segmental motor scores as the primary evaluation endpoint. Secondary endpoints included severity grade improvement, independent walking, and self-care ability. Different similarity metrics were explored for k-nearest neighbor (kNN) matching within 1267 patients from the European Multicenter Study about Spinal Cord Injury before validation in 411 patients from the Sygen trial. The kNN performance was compared to linear and logistic regression models.
We obtained a population-wide root-mean-squared error (RMSE) in motor score sequence of 0.76(0.14, 2.77) and competitive functional score predictions (AUC = 0.92, AUC = 0.83) for the kNN algorithm, improving beyond the linear regression task (RMSE = 0.98(0.22, 2.57)). The validation cohort showed comparable results (RMSE = 0.75(0.13, 2.57), AUC = 0.92). We deploy the final historic control model as a web tool for easy user interaction (https://hicsci.ethz.ch/).
Our approach is the first to provide predictions across all motor segments independent of the level and severity of SCI. We provide a machine learning concept that is highly interpretable, i.e. the prediction formation process is transparent, that has been validated across European and American data sets, and provides reliable and validated algorithms to incorporate external control data to increase sensitivity and feasibility of multinational clinical trials.
外伤性脊髓损伤（SCI）后的神经和功能恢复受到损伤水平和严重程度（不同程度的完全/不完全 SCI）以及脊髓综合征（半侧、前侧、中央、后侧）的高度异质性的挑战。到目前为止，临床试验中的预后预测仅限于针对上肢（UEMS）和下肢（LEMS）的总运动评分，而忽略了运动功能的分布对于功能结果至关重要。开发针对从损伤水平到最低运动节段的所有脊髓节段的详细节段性运动恢复的基于数据的预测模型，将改善康复计划的设计和临床试验的敏感性。
本研究使用急性期国际 SCI 神经分类标准检查来预测 6 个月的节段性运动评分恢复作为主要评估终点。次要终点包括严重程度分级改善、独立行走和自理能力。在对来自 Sygen 试验的 411 名患者进行验证之前，在来自欧洲多中心 SCI 研究的 1267 名患者中探索了不同的相似性度量，以进行 k-最近邻（kNN）匹配。比较了 kNN 性能与线性和逻辑回归模型。
我们获得了运动评分序列的全人群均方根误差（RMSE）为 0.76（0.14，2.77）和有竞争力的功能评分预测（AUC=0.92，AUC=0.83），优于线性回归任务（RMSE=0.98（0.22，2.57））。验证队列显示出可比的结果（RMSE=0.75（0.13，2.57），AUC=0.92）。我们将最终的历史对照模型作为一个易于用户交互的网络工具进行部署（https://hicsci.ethz.ch/）。
我们的方法是第一个提供独立于 SCI 水平和严重程度的所有运动节段的预测的方法。我们提供了一个机器学习概念，该概念具有高度可解释性，即预测形成过程是透明的，已经在欧洲和美国的数据集中进行了验证，并提供了可靠和经过验证的算法来纳入外部对照数据，以提高跨国临床试验的敏感性和可行性。
