Timely stroke treatment can limit brain damage and improve outcomes, which depends on early recognition of the symptoms. However, stroke cases are often missed by the first respondent paramedics. One of the earliest external symptoms of stroke is based on facial expressions. We propose a computerized analysis of facial expressions using action units to distinguish between Post-Stroke and healthy people. Action units enable analysis of subtle and specific facial movements and are interpretable to the facial expressions. The RGB videos from the Toronto Neuroface Dataset, which were recorded during standard orofacial examinations of 14 people with post-stroke (PS) and 11 healthy controls (HC) were used in this study. Action units were computed using XGBoost which was trained using HC, and classified using regression analysis for each of the nine facial expressions. The analysis was performed without manual intervention. The results were evaluated using leave-one-our validation. The accuracy was 82% for Kiss and Spread, with the best sensitivity of 91% in the differentiation of PS and HC. The features corresponding to mouth muscles were most suitable. This pilot study has shown that our method can detect PS based on two simple facial expressions. However, this needs to be tested in real-world conditions, with people of different ethnicities and smartphone use. The method has the potential for a computerized assessment of the videos for use by the first respondents using a smartphone to perform screening tests, which can facilitate the timely start of the treatment.

中文翻译：

---

通过面部表情识别中风后：一项试点研究

及时的中风治疗可以限制脑损伤并改善预后，这取决于对症状的早期识别。然而，第一反应的护理人员经常会错过中风病例。中风最早的外部症状之一是面部表情。我们提出使用动作单元对面部表情进行计算机分析，以区分中风后和健康人。动作单元能够分析微妙和特定的面部动作，并且可以解释为面部表情。本研究使用了来自多伦多 Neuroface 数据集的 RGB 视频，这些视频是在 14 名中风后患者 (PS) 和 11 名健康对照者 (HC) 进行标准口面部检查时记录的。使用 XGBoost 计算动作单元，并使用 HC 进行训练，并使用回归分析对九种面部表情中的每一种进行分类。分析是在没有人工干预的情况下进行的。使用留一验证对结果进行评估。 Kiss 和 Spread 的准确度为 82%，区分 PS 和 HC 的最佳灵敏度为 91%。与嘴部肌肉对应的特征是最合适的。这项试点研究表明，我们的方法可以根据两个简单的面部表情来检测 PS。然而，这需要在现实条件下进行测试，包括不同种族和智能手机使用情况的人。该方法有可能对视频进行计算机化评估，供第一批受访者使用智能手机进行筛查测试，从而有助于及时开始治疗。