Sorbonne Universités, UPMC Univ Paris 06, CNRS UMR 7222, Institut des Systèmes Intelligents et de Robotique, Paris, France; CEPOI EA 7388, Unité de Pédopsychiatrie de Liaison, Pôle de Santé Mentale, CHU Sud Réunion, Université de la Réunion, Saint-Pierre, France; CESP Inserm U1178, Groupe IPSOM, Paris, France.
Sorbonne Universités, UPMC Univ Paris 06, CNRS UMR 7222, Institut des Systèmes Intelligents et de Robotique, Paris, France.
Prog Neuropsychopharmacol Biol Psychiatry. 2018 Mar 2;82:107-114. doi: 10.1016/j.pnpbp.2017.11.023. Epub 2017 Nov 27.
Stress reactivity is a complex phenomenon associated to multiple and multimodal expressions. Response to stressors has an obvious survival function and may be seen as an internal regulation to adapt to threat or danger. The intensity of this internal response can be assessed as the self-perception of the stress response. In species with social organization, this response also serves a communicative function, so-called hetero-perception. Our study presents multimodal stress detection assessment - a new methodology combining behavioral imaging and physiological monitoring for analyzing stress from these two perspectives. The system is based on automatic extraction of 39 behavioral (2D+3D video recording) and 62 physiological (Nexus-10 recording) features during a socially evaluated mental arithmetic test. The analysis with machine learning techniques for automatic classification using Support Vector Machine (SVM) show that self-perception and hetero-perception of social stress are both close but different phenomena: self-perception was significantly correlated with hetero-perception but significantly differed from it. Also, assessing stress with SVM through multimodality gave excellent classification results (F1 score values: 0.9±0.012 for hetero-perception and 0.87±0.021 for self-perception). In the best selected feature subsets, we found some common behavioral and physiological features that allow classification of both self- and hetero-perceived stress. However, we also found the contributing features for automatic classifications had opposite distributions: self-perception classification was mainly based on physiological features and hetero-perception was mainly based on behavioral features.
应激反应是一种与多种模态表达相关的复杂现象。对压力源的反应具有明显的生存功能，可以被视为一种内部调节机制，以适应威胁或危险。这种内部反应的强度可以通过对压力反应的自我感知来评估。在具有社会组织的物种中，这种反应还具有一种交流功能，即所谓的异感。我们的研究提出了多模态应激检测评估——一种新的方法学，它结合了行为成像和生理监测，从这两个角度分析应激。该系统基于在社会评估性心算测试期间自动提取 39 种行为（2D+3D 视频记录）和 62 种生理（Nexus-10 记录）特征。使用支持向量机（SVM）进行自动分类的机器学习技术分析表明，社会应激的自我感知和异感都是密切相关但不同的现象：自我感知与异感显著相关，但与异感显著不同。此外，通过多模态评估 SVM 对压力进行评估可获得出色的分类结果（异感的 F1 评分值为 0.9±0.012，自我感知的 F1 评分值为 0.87±0.021）。在所选择的最佳特征子集中，我们发现了一些常见的行为和生理特征，这些特征可以用于分类自我感知和异感压力。然而，我们还发现，用于自动分类的特征具有相反的分布：自我感知分类主要基于生理特征，而异感分类主要基于行为特征。
