Validation of Visual and Auditory Digital Markers of Suicidality in Acutely Suicidal Psychiatric Inpatients: Proof-of-Concept Study.
auditory
depression
digital
digital biomarkers
digital health
digital markers
digital phenotyping
facial
suicidal ideation
suicide
suicide risk
visual
Journal
Journal of medical Internet research
ISSN: 1438-8871
Titre abrégé: J Med Internet Res
Pays: Canada
ID NLM: 100959882
Informations de publication
Date de publication:
03 06 2021
03 06 2021
Historique:
received:
26
10
2020
accepted:
16
03
2021
revised:
15
12
2020
entrez:
3
6
2021
pubmed:
4
6
2021
medline:
21
10
2021
Statut:
epublish
Résumé
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 Digital measurements of facial affect, movement, and speech prevalence demonstrated strong effect sizes and linear associations with the severity of suicidal ideation.
Sections du résumé
BACKGROUND
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.
OBJECTIVE
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.
METHODS
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.
RESULTS
Suicide severity was associated with multiple visual and auditory markers, including speech prevalence (β=-0.68, P=.02, r
CONCLUSIONS
Digital measurements of facial affect, movement, and speech prevalence demonstrated strong effect sizes and linear associations with the severity of suicidal ideation.
Identifiants
pubmed: 34081022
pii: v23i6e25199
doi: 10.2196/25199
pmc: PMC8212625
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
e25199Informations de copyright
©Isaac Galatzer-Levy, Anzar Abbas, Anja Ries, Stephanie Homan, Laura Sels, Vidya Koesmahargyo, Vijay Yadav, Michael Colla, Hanne Scheerer, Stefan Vetter, Erich Seifritz, Urte Scholz, Birgit Kleim. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 03.06.2021.
Références
Digit Biomark. 2021 Jan 21;5(1):29-36
pubmed: 33615120
J Psychiatr Res. 2009 Jun;43(9):855-63
pubmed: 19128810
Prog Neuropsychopharmacol Biol Psychiatry. 2011 Mar 30;35(2):395-409
pubmed: 21044654
Innov Clin Neurosci. 2016 Jun 01;13(5-6):16-20
pubmed: 27800282
Proc Int Conf Autom Face Gesture Recognit. 2013;:1-8
pubmed: 24598859
J Neurosci. 1998 Sep 15;18(18):7394-401
pubmed: 9736659
NPJ Digit Med. 2019 May 10;2:40
pubmed: 31304386
JAMA Psychiatry. 2020 Jul 1;77(7):661-662
pubmed: 32186693
J Psychiatr Res. 2003 Sep-Oct;37(5):357-73
pubmed: 12849929
Ann Gen Psychiatry. 2007 Mar 16;6:10
pubmed: 17367524
IEEE J Biomed Health Inform. 2018 Mar;22(2):525-536
pubmed: 28278485
BMC Psychiatry. 2017 Dec 4;17(1):389
pubmed: 29202737
CNS Neurosci Ther. 2010 Jun;16(3):e1-17
pubmed: 20406250
Transl Psychiatry. 2017 Mar 7;7(3):e1053
pubmed: 28267146
Lancet. 2003 Jun 14;361(9374):1999
pubmed: 12814704
JAMA. 2004 Jul 21;292(3):379-81
pubmed: 15265855
Gait Posture. 2018 Mar;61:81-85
pubmed: 29306811
J Nerv Ment Dis. 2000 Dec;188(12):824-9
pubmed: 11191583
J Consult Clin Psychol. 2018 Jan;86(1):56-68
pubmed: 29172592
JAMA Psychiatry. 2020 Jul 1;77(7):663-664
pubmed: 32211837
JAMA Psychiatry. 2019 Oct 1;76(10):999-1000
pubmed: 31290952
Crisis. 2013;34(3):147-55
pubmed: 23628664
Psychol Assess. 2007 Sep;19(3):309-17
pubmed: 17845122
World Psychiatry. 2018 Oct;17(3):276-277
pubmed: 30192103
CNS Spectr. 2014 Dec;19 Suppl 1:57-67; quiz 54-7, 68
pubmed: 25544378