JMIR Publications

ABSTRACT

Background:

Multiple symptoms of suicide risk are 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.

Objective:

The goal of this work was to determine if key indicators of the suicide severity could be measured in an objective and automated manner using video data captured during clinical interviews that provided structured questions, but were otherwise kept deliberately open to mimic psychiatric interviewing in routine care.

Methods:

In the current study 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 severity using the Beck Suicide Scale (BSS), controlling for age and gender using multiple linear regression.

Results:

Suicide severity was associated with multiple visual and auditory markers including speech prevalence (β = -0.68; P = .017, r2 = .40, overall expressivity (β = -0.46; P = 0.10, r2 = .27), and head movement measured as head pitch variability (β = -1.24; P = .006, r2 = .48) and head yaw variability (β = -0.54; p = .055, r2 = .32).

Conclusions:

Digital measurements of facial affect, movement, and speech prevalence demonstrated strong effect sizes and significant linear associations with severity of suicidal ideation.