Rajashekar Deepthi, Hill Michael D, Demchuk Andrew M, Goyal Mayank, Fiehler Jens, Forkert Nils D
Biomedical Engineering Graduate Program, University of Calgary, Calgary, AB, Canada.
Depertment of Radiology, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada.
Front Neurol. 2021 May 6;12:663899. doi: 10.3389/fneur.2021.663899. eCollection 2021.
Clinical stroke rehabilitation decision making relies on multi-modal data, including imaging and other clinical assessments. However, most previously described methods for predicting long-term stroke outcomes do not make use of the full multi-modal data available. The aim of this work was to develop and evaluate the benefit of nested regression models that utilise clinical assessments as well as image-based biomarkers to model 30-day NIHSS. 221 subjects were pooled from two prospective trials with follow-up MRI or CT scans, and NIHSS assessed at baseline, as well as 48-hours and 30 days after symptom onset. Three prediction models for 30-day NIHSS were developed using a support vector regression model: one clinical model based on modifiable and non-modifiable risk factors (M) and two nested regression models that aggregate clinical and image-based features that differed with respect to the method used for selection of important brain regions for the modelling task. The first model used the widely accepted RreliefF (M) machine learning method for this purpose, while the second model employed a lesion-symptom mapping technique (M) often used in neuroscience to investigate structure-function relationships and identify eloquent regions in the brain. The two nested models achieved a similar performance while considerably outperforming the clinical model. However, M required fewer brain regions and achieved a lower mean absolute error than M while being less computationally expensive. Aggregating clinical and imaging information leads to considerably better outcome prediction models. While lesion-symptom mapping is a useful tool to investigate structure-function relationships of the brain, it does not lead to better outcome predictions compared to a simple data-driven feature selection approach, which is less computationally expensive and easier to implement.
临床中风康复决策依赖于多模态数据，包括影像学和其他临床评估。然而，大多数先前描述的预测中风长期预后的方法并未充分利用现有的全部多模态数据。这项工作的目的是开发并评估嵌套回归模型的益处，该模型利用临床评估以及基于图像的生物标志物来对30天的美国国立卫生研究院卒中量表（NIHSS）进行建模。从两项前瞻性试验中汇集了221名受试者，这些试验有随访的磁共振成像（MRI）或计算机断层扫描（CT），并在基线以及症状发作后48小时和30天评估NIHSS。使用支持向量回归模型开发了三种预测30天NIHSS的模型：一种基于可修改和不可修改风险因素的临床模型（M），以及两种嵌套回归模型，它们汇总了临床和基于图像的特征，这些特征在用于为建模任务选择重要脑区的方法方面有所不同。第一个模型为此目的使用了广泛接受的RreliefF（M）机器学习方法，而第二个模型采用了神经科学中常用于研究结构 - 功能关系并识别大脑中明确区域的病变 - 症状映射技术（M）。这两个嵌套模型表现相似，同时明显优于临床模型。然而，M所需的脑区较少，平均绝对误差低于M，且计算成本较低。汇总临床和影像学信息可产生明显更好的预后预测模型。虽然病变 - 症状映射是研究大脑结构 - 功能关系的有用工具，但与简单的数据驱动特征选择方法相比，它并不能带来更好的预后预测，后者计算成本更低且更易于实施。
