Deep learning paired with wearable passive sensing data predicts deterioration in anxiety disorder symptoms across 17-18 years.
anxiety disorders
artficial intelligence
deep learning
digital phenotyping
passive sensing
wearable movement
Journal
Journal of affective disorders
ISSN: 1573-2517
Titre abrégé: J Affect Disord
Pays: Netherlands
ID NLM: 7906073
Informations de publication
Date de publication:
01 03 2021
01 03 2021
Historique:
received:
18
08
2020
revised:
01
11
2020
accepted:
22
12
2020
pubmed:
6
1
2021
medline:
24
4
2021
entrez:
5
1
2021
Statut:
ppublish
Résumé
Recent studies have demonstrated that passive smartphone and wearable sensor data collected throughout daily life can predict anxiety symptoms cross-sectionally. However, to date, no research has demonstrated the capacity for these digital biomarkers to predict long-term prognosis. We utilized deep learning models based on wearable sensor technology to predict long-term (17-18-year) deterioration in generalized anxiety disorder and panic disorder symptoms from actigraphy data on daytime movement and nighttime sleeping patterns. As part of Midlife in the United States (MIDUS), a national longitudinal study of health and well-being, subjects (N = 265) (i) completed a phone-based interview that assessed generalized anxiety disorder and panic disorder symptoms at enrollment, (ii) participated in a one-week actigraphy study 9-14 years later, and (iii) completed a long-term follow-up, phone-based interview to quantify generalized anxiety disorder and panic disorder symptoms 17-18 years from initial enrollment. A deep auto-encoder paired with a multi-layered ensemble deep learning model was leveraged to predict whether participants experienced increased anxiety disorder symptoms across this 17-18 year period. Out-of-sample cross-validated results suggested that wearable movement data could significantly predict which individuals would experience symptom deterioration (AUC = 0.696, CI [0.598, 0.793], 84.6% sensitivity, 52.7% specificity, balanced accuracy = 68.7%). Passive wearable actigraphy data could be utilized to predict long-term deterioration of anxiety disorder symptoms. Future studies should examine whether these methods could be implemented to prevent deterioration of anxiety disorder symptoms.
Sections du résumé
BACKGROUND
Recent studies have demonstrated that passive smartphone and wearable sensor data collected throughout daily life can predict anxiety symptoms cross-sectionally. However, to date, no research has demonstrated the capacity for these digital biomarkers to predict long-term prognosis.
METHODS
We utilized deep learning models based on wearable sensor technology to predict long-term (17-18-year) deterioration in generalized anxiety disorder and panic disorder symptoms from actigraphy data on daytime movement and nighttime sleeping patterns. As part of Midlife in the United States (MIDUS), a national longitudinal study of health and well-being, subjects (N = 265) (i) completed a phone-based interview that assessed generalized anxiety disorder and panic disorder symptoms at enrollment, (ii) participated in a one-week actigraphy study 9-14 years later, and (iii) completed a long-term follow-up, phone-based interview to quantify generalized anxiety disorder and panic disorder symptoms 17-18 years from initial enrollment. A deep auto-encoder paired with a multi-layered ensemble deep learning model was leveraged to predict whether participants experienced increased anxiety disorder symptoms across this 17-18 year period.
RESULTS
Out-of-sample cross-validated results suggested that wearable movement data could significantly predict which individuals would experience symptom deterioration (AUC = 0.696, CI [0.598, 0.793], 84.6% sensitivity, 52.7% specificity, balanced accuracy = 68.7%).
CONCLUSIONS
Passive wearable actigraphy data could be utilized to predict long-term deterioration of anxiety disorder symptoms. Future studies should examine whether these methods could be implemented to prevent deterioration of anxiety disorder symptoms.
Identifiants
pubmed: 33401123
pii: S0165-0327(20)33176-1
doi: 10.1016/j.jad.2020.12.086
pmc: PMC7889722
mid: NIHMS1659982
pii:
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
104-111Subventions
Organisme : NIMH NIH HHS
ID : R01 MH123482
Pays : United States
Organisme : NCATS NIH HHS
ID : UL1 TR001409
Pays : United States
Organisme : NCRR NIH HHS
ID : UL1 RR025011
Pays : United States
Organisme : NIA NIH HHS
ID : U19 AG051426
Pays : United States
Organisme : NCATS NIH HHS
ID : UL1 TR001881
Pays : United States
Organisme : NCATS NIH HHS
ID : UL1 TR002373
Pays : United States
Organisme : NIA NIH HHS
ID : P01 AG020166
Pays : United States
Informations de copyright
Copyright © 2020. Published by Elsevier B.V.
Références
Eur Psychiatry. 2013 Mar;28(3):154-60
pubmed: 22520956
Sci Rep. 2021 Jan 21;11(1):1980
pubmed: 33479383
Arch Gen Psychiatry. 1989 Nov;46(11):984-92
pubmed: 2684086
Prim Care Companion J Clin Psychiatry. 2004;6(1):35-41
pubmed: 15486599
Depress Anxiety. 2016 Jan;33(1):66-74
pubmed: 26290461
Psychol Med. 2000 May;30(3):693-703
pubmed: 10883723
Soc Psychiatry Psychiatr Epidemiol. 2003 Jan;38(1):1-11
pubmed: 12563553
Arch Gen Psychiatry. 1988 Dec;45(12):1069-77
pubmed: 2848472
J Anxiety Disord. 2014 Jun;28(5):437-45
pubmed: 24858656
Int J Methods Psychiatr Res. 2012 Sep;21(3):169-84
pubmed: 22865617
Transl Psychiatry. 2015 Mar 17;5:e530
pubmed: 25781229
J Affect Disord. 2011 Sep;133(1-2):76-85
pubmed: 21496929
Health Aff (Millwood). 2015 May;34(5):727-31
pubmed: 25941272
Int J Methods Psychiatr Res. 2011 Sep;20(3):157-68
pubmed: 22547298
J Anxiety Disord. 2013 Oct;27(7):720-7
pubmed: 24135257
Int J Methods Psychiatr Res. 2008;17(3):121-40
pubmed: 18763692
Curr Psychiatry Rep. 2011 Aug;13(4):258-66
pubmed: 21484451
Prim Care Companion CNS Disord. 2011;13(2):
pubmed: 21977354
Behav Res Methods. 2019 Feb;51(1):295-315
pubmed: 30120682
Psychiatr Clin North Am. 2006 Dec;29(4):1047-58; abstract x
pubmed: 17118281
Am J Epidemiol. 2006 Apr 1;163(7):670-5
pubmed: 16410346
J Med Internet Res. 2020 May 29;22(5):e16875
pubmed: 32348284
Eur Neuropsychopharmacol. 2006 Jul;16 Suppl 2:S101-8
pubmed: 16730165
Br J Psychiatry. 2019 Jul 12;:1-3
pubmed: 31298167
J Anxiety Disord. 2016 Dec;44:92-101
pubmed: 27842240
J Abnorm Psychol. 2019 May;128(4):295-304
pubmed: 31045412
Depress Anxiety. 2008;25(1):72-90
pubmed: 17146763
Int J Methods Psychiatr Res. 2015 Sep;24(3):213-25
pubmed: 26140369
J Clin Psychiatry. 2011 Mar;72(3):341-8
pubmed: 21294994
J Affect Disord. 2017 Mar 15;211:83-91
pubmed: 28103522
Depress Anxiety. 2002;16(4):162-71
pubmed: 12497648
Br J Health Psychol. 2008 Feb;13(Pt 1):135-53
pubmed: 17535492
NPJ Digit Med. 2019 Feb 1;2:3
pubmed: 31304353
Dialogues Clin Neurosci. 2011;13(4):381-99
pubmed: 22275845
Behav Ther. 2012 Jun;43(2):450-64
pubmed: 22440079
Lancet. 2006 Sep 16;368(9540):1023-32
pubmed: 16980119
Am J Psychiatry. 2005 Jun;162(6):1179-87
pubmed: 15930067
J Abnorm Psychol. 2000 Nov;109(4):695-704
pubmed: 11195993
J Anxiety Disord. 2008 Oct;22(7):1227-43
pubmed: 18281190
Depress Anxiety. 2016 Jan;33(1):75-83
pubmed: 26367018
Clinicoecon Outcomes Res. 2014 Apr 02;6:151-63
pubmed: 24729720