Facial and Vocal Markers of Schizophrenia Measured Using Remote Smartphone Assessments: Observational Study.
computer vision
digital biomarkers
facial expressivity
negative symptoms
phenotyping
vocal acoustics
Journal
JMIR formative research
ISSN: 2561-326X
Titre abrégé: JMIR Form Res
Pays: Canada
ID NLM: 101726394
Informations de publication
Date de publication:
21 Jan 2022
21 Jan 2022
Historique:
received:
04
12
2020
accepted:
22
11
2021
revised:
02
03
2021
entrez:
21
1
2022
pubmed:
22
1
2022
medline:
22
1
2022
Statut:
epublish
Résumé
Machine learning-based facial and vocal measurements have demonstrated relationships with schizophrenia diagnosis and severity. Demonstrating utility and validity of remote and automated assessments conducted outside of controlled experimental or clinical settings can facilitate scaling such measurement tools to aid in risk assessment and tracking of treatment response in populations that are difficult to engage. This study aimed to determine the accuracy of machine learning-based facial and vocal measurements acquired through automated assessments conducted remotely through smartphones. Measurements of facial and vocal characteristics including facial expressivity, vocal acoustics, and speech prevalence were assessed in 20 patients with schizophrenia over the course of 2 weeks in response to two classes of prompts previously utilized in experimental laboratory assessments: evoked prompts, where subjects are guided to produce specific facial expressions and speech; and spontaneous prompts, where subjects are presented stimuli in the form of emotionally evocative imagery and asked to freely respond. Facial and vocal measurements were assessed in relation to schizophrenia symptom severity using the Positive and Negative Syndrome Scale. Vocal markers including speech prevalence, vocal jitter, fundamental frequency, and vocal intensity demonstrated specificity as markers of negative symptom severity, while measurement of facial expressivity demonstrated itself as a robust marker of overall schizophrenia symptom severity. Established facial and vocal measurements, collected remotely in schizophrenia patients via smartphones in response to automated task prompts, demonstrated accuracy as markers of schizophrenia symptom severity. Clinical implications are discussed.
Sections du résumé
BACKGROUND
BACKGROUND
Machine learning-based facial and vocal measurements have demonstrated relationships with schizophrenia diagnosis and severity. Demonstrating utility and validity of remote and automated assessments conducted outside of controlled experimental or clinical settings can facilitate scaling such measurement tools to aid in risk assessment and tracking of treatment response in populations that are difficult to engage.
OBJECTIVE
OBJECTIVE
This study aimed to determine the accuracy of machine learning-based facial and vocal measurements acquired through automated assessments conducted remotely through smartphones.
METHODS
METHODS
Measurements of facial and vocal characteristics including facial expressivity, vocal acoustics, and speech prevalence were assessed in 20 patients with schizophrenia over the course of 2 weeks in response to two classes of prompts previously utilized in experimental laboratory assessments: evoked prompts, where subjects are guided to produce specific facial expressions and speech; and spontaneous prompts, where subjects are presented stimuli in the form of emotionally evocative imagery and asked to freely respond. Facial and vocal measurements were assessed in relation to schizophrenia symptom severity using the Positive and Negative Syndrome Scale.
RESULTS
RESULTS
Vocal markers including speech prevalence, vocal jitter, fundamental frequency, and vocal intensity demonstrated specificity as markers of negative symptom severity, while measurement of facial expressivity demonstrated itself as a robust marker of overall schizophrenia symptom severity.
CONCLUSIONS
CONCLUSIONS
Established facial and vocal measurements, collected remotely in schizophrenia patients via smartphones in response to automated task prompts, demonstrated accuracy as markers of schizophrenia symptom severity. Clinical implications are discussed.
Identifiants
pubmed: 35060906
pii: v6i1e26276
doi: 10.2196/26276
pmc: PMC8817208
doi:
Types de publication
Journal Article
Langues
eng
Pagination
e26276Informations de copyright
©Anzar Abbas, Bryan J Hansen, Vidya Koesmahargyo, Vijay Yadav, Paul J Rosenfield, Omkar Patil, Marissa F Dockendorf, Matthew Moyer, Lisa A Shipley, M Mercedez Perez-Rodriguez, Isaac R Galatzer-Levy. Originally published in JMIR Formative Research (https://formative.jmir.org), 21.01.2022.
Références
Schizophr Bull. 1997;23(2):171-7
pubmed: 9165627
Eur Psychiatry. 2007 Sep;22(6):380-6
pubmed: 17524626
Psychopathology. 1997;30(5):263-74
pubmed: 9353855
Schizophr Res. 2008 Oct;105(1-3):30-9
pubmed: 18793827
Schizophr Bull. 2006 Apr;32(2):214-9
pubmed: 16481659
Am J Psychiatry. 2013 Feb;170(2):165-72
pubmed: 23377637
Schizophr Res. 2012 Dec;142(1-3):93-5
pubmed: 23102940
Psychiatry Res. 2006 Dec 7;145(2-3):87-94
pubmed: 17074400
Front Psychiatry. 2020 Jun 03;11:523
pubmed: 32581891
World Psychiatry. 2018 Oct;17(3):276-277
pubmed: 30192103
J Speech Hear Res. 1968 Mar;11(1):194-203
pubmed: 5659069
Neuropsychiatr Dis Treat. 2013;9:1137-44
pubmed: 23966784
Schizophr Res. 2006 Jul;85(1-3):273-9
pubmed: 16730430
Schizophr Res. 2013 Oct;150(1):3-10
pubmed: 23800613
Schizophr Bull. 2015 Jul;41(4):892-9
pubmed: 25528757
Behav Res Methods. 2017 Apr;49(2):457-470
pubmed: 26907748
Span J Psychol. 2015 Nov 02;18:E86
pubmed: 26522128
Community Ment Health J. 2019 Aug;55(6):973-978
pubmed: 31175518
Prim Care Companion CNS Disord. 2020 Oct 1;22(5):
pubmed: 33002350
NPJ Digit Med. 2018 Apr 6;1:15
pubmed: 31304300
IEEE Trans Biomed Eng. 2010 Apr;57(4):884-93
pubmed: 19932995
Psychiatry Res. 2009 Oct 30;169(3):187-90
pubmed: 19729205
Schizophr Res. 2020 Feb;216:24-40
pubmed: 31839552
JMIR Mhealth Uhealth. 2020 May 29;8(5):e17458
pubmed: 32348289
NPJ Digit Med. 2019 May 10;2:40
pubmed: 31304386
Eur Neuropsychopharmacol. 2014 May;24(5):645-92
pubmed: 24820238
Schizophr Bull. 1987;13(2):261-76
pubmed: 3616518
J Abnorm Psychol. 2016 Feb;125(2):299-309
pubmed: 26854511
Schizophr Res. 2018 Jul;197:67-68
pubmed: 29338959
Schizophr Bull. 2011 Mar;37(2):300-5
pubmed: 20558531
J Neurosci Methods. 2008 Feb 15;168(1):224-38
pubmed: 18045693
Schizophr Res. 2007 Sep;95(1-3):151-7
pubmed: 17689931
J Neurosci Methods. 2007 Jul 30;163(2):350-61
pubmed: 17442398
JAMA. 2017 Oct 3;318(13):1215-1216
pubmed: 28973224
Cogn Behav Neurol. 2005 Dec;18(4):206-10
pubmed: 16340393
Am J Public Health. 2019 Jun;109(S3):S168-S170
pubmed: 31242003
J Clin Psychiatry. 1997 Dec;58(12):538-46
pubmed: 9448657
Schizophr Res. 2008 Oct;105(1-3):49-60
pubmed: 18789845
Stroke. 2017 May;48(5):1416-1419
pubmed: 28386037
JMIR Ment Health. 2021 Jan 12;8(1):e24333
pubmed: 33433392
Schizophr Bull. 2006 Apr;32(2):234-7
pubmed: 16492797
Br J Psychiatry. 2010 Sep;197(3):174-9
pubmed: 20807960
Neuropsychopharmacology. 2018 Jul;43(8):1637-1638
pubmed: 29703995
Eur Neuropsychopharmacol. 1998 Feb;8(1):33-42
pubmed: 9452938
Schizophr Res. 2007 Sep;95(1-3):197-204
pubmed: 17630254
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:5575-5579
pubmed: 33019241
PLoS One. 2019 May 31;14(5):e0217404
pubmed: 31150442
Schizophr Res. 1995 Nov;17(3):249-55
pubmed: 8664204
Schizophr Bull. 1998;24(3):399-412
pubmed: 9718632
J Abnorm Psychol. 1992 Feb;101(1):37-44
pubmed: 1537971
NPJ Schizophr. 2020 Apr 20;6(1):10
pubmed: 32313047