Guimarães Vânia, Sousa Inês, Correia Miguel Velhote
Fraunhofer Portugal AICOS, Rua Alfredo Allen 455/461, Porto, 4200-135, Portugal.
Faculdade de Engenharia, Universidade do Porto, Rua Dr. Roberto Frias, Porto, 4200-465, Portugal.
BMC Med Inform Decis Mak. 2025 Apr 1;25(1):157. doi: 10.1186/s12911-025-02979-9.
Cognitive impairment is common after a stroke, but it can often go undetected. In this study, we investigated whether using gait and dual tasks could help detect cognitive impairment after stroke.
We analyzed gait and neuropsychological data from 47 participants who were part of the Ontario Neurodegenerative Disease Research Initiative. Based on neuropsychological criteria, participants were categorized as impaired (n = 29) or cognitively normal (n = 18). Nested cross-validation was used for model training, hyperparameter tuning, and evaluation. Grid search with cross-validation was used to optimize the hyperparameters of a set of feature selectors and classifiers. Different gait tests were assessed separately.
The best classification performance was achieved using a comprehensive set of gait metrics, measured by the electronic walkway, that included dual-task costs while performing subtractions by ones. Using a Support Vector Machine (SVM), we could achieve a sensitivity of 96.6%, and a specificity of 61.1%. An optimized threshold of 27 in the Montreal Cognitive Assessment (MoCA) revealed lower classification performance than the gait metrics, although differences in classification results were not significant. Combining the classifications provided by MoCA with those provided by gait metrics in a majority voting approach resulted in a higher specificity of 72.2%, and a high sensitivity of 93.1%.
Our results suggest that gait analysis can be a useful tool for detecting cognitive impairment in patients with cerebrovascular disease, serving as a suitable alternative or complement to MoCA in the screening for cognitive impairment.
中风后认知障碍很常见，但往往未被发现。在本研究中，我们调查了使用步态和双重任务是否有助于检测中风后的认知障碍。
我们分析了安大略省神经退行性疾病研究倡议中的47名参与者的步态和神经心理学数据。根据神经心理学标准，参与者被分为受损组（n = 29）或认知正常组（n = 18）。嵌套交叉验证用于模型训练、超参数调整和评估。使用交叉验证的网格搜索来优化一组特征选择器和分类器的超参数。分别评估不同的步态测试。
使用电子步道测量的一组综合步态指标可实现最佳分类性能，其中包括在逐次减法时的双重任务成本。使用支持向量机（SVM），我们可以实现96.6%的灵敏度和61.1%的特异性。蒙特利尔认知评估（MoCA）中27的优化阈值显示出比步态指标更低的分类性能，尽管分类结果的差异不显著。以多数投票方法将MoCA提供的分类与步态指标提供的分类相结合，可使特异性提高到72.2%，灵敏度提高到93.1%。
我们的结果表明，步态分析可以作为检测脑血管疾病患者认知障碍的有用工具，在认知障碍筛查中作为MoCA的合适替代或补充。
