Research and Development, AiCure, New York, NY, United States.
Psychiatry, New York University School of Medicine, New York, NY, United States.
J Med Internet Res. 2021 Jun 3;23(6):e25199. doi: 10.2196/25199.
Multiple symptoms of suicide risk have been assessed based on visual and auditory information, including flattened affect, reduced movement, and slowed speech. Objective quantification of such symptomatology from novel data sources can increase the sensitivity, scalability, and timeliness of suicide risk assessment.
We aimed to examine measurements extracted from video interviews using open-source deep learning algorithms to quantify facial, vocal, and movement behaviors in relation to suicide risk severity in recently admitted patients following a suicide attempt.
We utilized video to quantify facial, vocal, and movement markers associated with mood, emotion, and motor functioning from a structured clinical conversation in 20 patients admitted to a psychiatric hospital following a suicide risk attempt. Measures were calculated using open-source deep learning algorithms for processing facial expressivity, head movement, and vocal characteristics. Derived digital measures of flattened affect, reduced movement, and slowed speech were compared to suicide risk with the Beck Scale for Suicide Ideation controlling for age and sex, using multiple linear regression.
Suicide severity was associated with multiple visual and auditory markers, including speech prevalence (β=-0.68, P=.02, r=0.40), overall expressivity (β=-0.46, P=.10, r=0.27), and head movement measured as head pitch variability (β=-1.24, P=.006, r=0.48) and head yaw variability (β=-0.54, P=.06, r=0.32).
Digital measurements of facial affect, movement, and speech prevalence demonstrated strong effect sizes and linear associations with the severity of suicidal ideation.
已经基于视觉和听觉信息评估了多种自杀风险症状，包括情感平淡、动作减少和言语缓慢。从新的数据来源客观量化这些症状可以提高自杀风险评估的灵敏度、可扩展性和及时性。
我们旨在检查使用开源深度学习算法从视频采访中提取的测量值，以量化与自杀风险严重程度相关的面部、声音和运动行为，这些患者是最近在自杀未遂后被收入精神病院的。
我们利用视频来量化情绪、情感和运动功能相关的面部、声音和运动标记，这是在 20 名因自杀风险而被收入精神病院的患者中进行的结构化临床对话。使用开源深度学习算法来计算面部表情、头部运动和声音特征的指标。使用贝克自杀意念量表来控制年龄和性别，将衍生的数字平坦表情、动作减少和言语缓慢测量值与自杀风险进行比较，采用多元线性回归。
自杀严重程度与多种视觉和听觉标记物相关，包括言语发生率（β=-0.68，P=.02，r=0.40）、整体表现力（β=-0.46，P=.10，r=0.27）和头部运动，表现为头部俯仰变异性（β=-1.24，P=.006，r=0.48）和头部偏航变异性（β=-0.54，P=.06，r=0.32）。
面部表情、动作和言语发生率的数字测量值与自杀意念严重程度具有很强的效应量和线性关联。
