Filali Razzouki Anas, Jeancolas Laetitia, Sambin Sara, Mangone Graziella, Chalançon Alizé, Gomes Manon, Lehéricy Stéphane, Vidailhet Marie, Arnulf Isabelle, Corvol Jean-Christophe, Petrovska-Delacrétaz Dijana, El-Yacoubi Mounim A
Laboratoire SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris, Palaiseau, France.
Sorbonne Université, Paris Brain Institute - ICM, Inserm, CNRS, APHP, Hôpital Pitié-Salpêtrière, Paris, France.
NPJ Parkinsons Dis. 2025 Mar 21;11(1):53. doi: 10.1038/s41531-025-00895-3.
This study aimed to identify facial regions characterizing hypomimia through facial action units (AU). It included video recordings from 109 early-stage Parkinson's disease (PD) and 45 healthy control (HC) subjects, performing rapid syllable repetitions. We identified the features contributing most to hypomimia by interpreting an XGBoost model classifying PD vs. HC. We evaluated the impact of biological sex and time on features and classification, and the correlation between model's predictions, AUs, and PD clinical scores over different times. The most discriminant AUs of hypomimia were found on the face lower part, independent of sex, and stable over time. Significant correlations were observed between AU17 (chin raiser) and rigidity of the upper left limb (r = - 0.4), as well as between AU9 (nose wrinkle) and neck rigidity (r = - 0.36). Correlations between XGBoost predictions and MDS-UPDRS3 and neck rigidity scores were also significant (r = 0.3). We obtained for PD detection an AUC of 79.8% and a balanced accuracy of 71.5%.
本研究旨在通过面部动作单元（AU）识别出表征面部表情减少的面部区域。该研究纳入了109名早期帕金森病（PD）患者和45名健康对照（HC）受试者的视频记录，这些受试者进行了快速音节重复任务。我们通过解释一个区分PD与HC的XGBoost模型，确定了对面部表情减少贡献最大的特征。我们评估了生物性别和时间对特征及分类的影响，以及模型预测、AU与不同时间的PD临床评分之间的相关性。发现面部表情减少最具判别力的AU位于面部下半部分，与性别无关，且随时间稳定。观察到AU17（提颏肌）与左上肢体僵硬之间存在显著相关性（r = -0.4），以及AU9（皱鼻肌）与颈部僵硬之间存在显著相关性（r = -0.36）。XGBoost预测与MDS-UPDRS3及颈部僵硬评分之间的相关性也很显著（r = 0.3）。我们在PD检测中获得了79.8%的曲线下面积（AUC）和71.5%的平衡准确率。
