Deriving symptom networks from digital phenotyping data in serious mental illness.
EMA
mhealth
networks
psychosis
smartphones
Journal
BJPsych open
ISSN: 2056-4724
Titre abrégé: BJPsych Open
Pays: England
ID NLM: 101667931
Informations de publication
Date de publication:
03 Nov 2020
03 Nov 2020
Historique:
entrez:
3
11
2020
pubmed:
4
11
2020
medline:
4
11
2020
Statut:
epublish
Résumé
Symptoms of serious mental illness are multidimensional and often interact in complex ways. Generative models offer value in elucidating the underlying relationships that characterise these networks of symptoms. In this paper we use generative models to find unique interactions of schizophrenia symptoms as experienced on a moment-by-moment basis. Self-reported mood, anxiety and psychosis symptoms, self-reported measurements of sleep quality and social function, cognitive assessment, and smartphone touch screen data from two assessments modelled after the Trail Making A and B tests were collected with a digital phenotyping app for 47 patients in active treatment for schizophrenia over a 90-day period. Patients were retrospectively divided up into various non-exclusive subgroups based on measurements of depression, anxiety, sleep duration, cognition and psychosis symptoms taken in the clinic. Associated transition probabilities for the patient cohort and for the clinical subgroups were calculated using state transitions between adjacent 3-day timesteps of pairwise survey domains. The three highest probabilities for associated transitions across all patients were anxiety-inducing mood (0.357, P < 0.001), psychosis-inducing mood (0.276, P < 0.001), and anxiety-inducing poor sleep (0.268, P < 0.001). These transition probabilities were compared against a validation set of 17 patients from a pilot study, and no significant differences were found. Unique symptom networks were found for clinical subgroups. Using a generative model using digital phenotyping data, we show that certain symptoms of schizophrenia may play a role in elevating other schizophrenia symptoms in future timesteps. Symptom networks show that it is feasible to create clinically interpretable models that reflect the unique symptom interactions of psychosis-spectrum illness. These results offer a framework for researchers capturing temporal dynamics, for clinicians seeking to move towards preventative care, and for patients to better understand their lived experience.
Sections du résumé
BACKGROUND
BACKGROUND
Symptoms of serious mental illness are multidimensional and often interact in complex ways. Generative models offer value in elucidating the underlying relationships that characterise these networks of symptoms.
AIMS
OBJECTIVE
In this paper we use generative models to find unique interactions of schizophrenia symptoms as experienced on a moment-by-moment basis.
METHOD
METHODS
Self-reported mood, anxiety and psychosis symptoms, self-reported measurements of sleep quality and social function, cognitive assessment, and smartphone touch screen data from two assessments modelled after the Trail Making A and B tests were collected with a digital phenotyping app for 47 patients in active treatment for schizophrenia over a 90-day period. Patients were retrospectively divided up into various non-exclusive subgroups based on measurements of depression, anxiety, sleep duration, cognition and psychosis symptoms taken in the clinic. Associated transition probabilities for the patient cohort and for the clinical subgroups were calculated using state transitions between adjacent 3-day timesteps of pairwise survey domains.
RESULTS
RESULTS
The three highest probabilities for associated transitions across all patients were anxiety-inducing mood (0.357, P < 0.001), psychosis-inducing mood (0.276, P < 0.001), and anxiety-inducing poor sleep (0.268, P < 0.001). These transition probabilities were compared against a validation set of 17 patients from a pilot study, and no significant differences were found. Unique symptom networks were found for clinical subgroups.
CONCLUSIONS
CONCLUSIONS
Using a generative model using digital phenotyping data, we show that certain symptoms of schizophrenia may play a role in elevating other schizophrenia symptoms in future timesteps. Symptom networks show that it is feasible to create clinically interpretable models that reflect the unique symptom interactions of psychosis-spectrum illness. These results offer a framework for researchers capturing temporal dynamics, for clinicians seeking to move towards preventative care, and for patients to better understand their lived experience.
Identifiants
pubmed: 33138889
doi: 10.1192/bjo.2020.94
pii: S2056472420000940
pmc: PMC7745255
doi:
Types de publication
Journal Article
Langues
eng
Pagination
e135Références
Depress Anxiety. 2018 Jul;35(7):601-608
pubmed: 29637663
Schizophr Res. 1998 Jun 22;32(1):17-22
pubmed: 9690330
Psychiatr Rehabil J. 2017 Sep;40(3):266-275
pubmed: 28368138
Schizophr Res. 2004 Jun 1;68(2-3):283-97
pubmed: 15099610
CNS Spectr. 2005 Sep;10(9):721-31
pubmed: 16142212
Gen Hosp Psychiatry. 2020 Sep - Oct;66:59-66
pubmed: 32688094
J Med Internet Res. 2019 Apr 17;21(4):e11029
pubmed: 30994461
Nat Neurosci. 2016 Mar;19(3):404-13
pubmed: 26906507
Br J Clin Psychol. 2005 Mar;44(Pt 1):113-25
pubmed: 15826348
Neuropsychopharmacology. 2018 Jul;43(8):1660-1666
pubmed: 29511333
BMC Med. 2019 Jul 17;17(1):137
pubmed: 31311535
J Gen Intern Med. 2001 Sep;16(9):606-13
pubmed: 11556941
J Nerv Ment Dis. 2017 Jan;205(1):4-8
pubmed: 28005647
Schizophr Res. 2018 Dec;202:72-79
pubmed: 30007868
Transl Psychiatry. 2017 Mar 7;7(3):e1053
pubmed: 28267146
Arch Intern Med. 2006 May 22;166(10):1092-7
pubmed: 16717171
Am J Bioeth. 2019 Jun;19(6):4-6
pubmed: 31135306
JAMA Surg. 2020 Feb 1;155(2):123-129
pubmed: 31657854
Psychiatry Res. 1989 May;28(2):193-213
pubmed: 2748771
Schizophr Res. 2019 Jun;208:82-89
pubmed: 31047723
NPJ Digit Med. 2018 Apr 6;1:15
pubmed: 31304300
J Physiother. 2017 Jan;63(1):55-58
pubmed: 27914733
NPJ Schizophr. 2017 Oct 16;3(1):37
pubmed: 29038553
Br J Psychiatry. 1990 Dec;157:853-9
pubmed: 2289094
Schizophr Res. 2018 Mar;193:232-239
pubmed: 28844638
Schizophr Bull. 2014 Jan;40(1):120-31
pubmed: 23180756
Curr Opin Biomed Eng. 2019 Mar;9:8-13
pubmed: 31650093
J Am Med Inform Assoc. 2019 Nov 1;26(11):1412-1420
pubmed: 31260049
Psychiatry Res. 2019 Aug;278:228-234
pubmed: 31226549
Aust N Z J Psychiatry. 2018 Jun;52(6):573-584
pubmed: 29232967
Wiley Interdiscip Rev Cogn Sci. 2018 May;9(3):e1460
pubmed: 29369526
Schizophr Bull. 1987;13(2):261-76
pubmed: 3616518
Psychol Assess. 2019 Mar;31(3):329-339
pubmed: 30802118
Schizophr Res Cogn. 2019 Apr 18;17:100144
pubmed: 31024801
J Med Internet Res. 2017 Feb 08;19(2):e38
pubmed: 28179216
J Abnorm Psychol. 2017 Oct;126(7):989-999
pubmed: 29106282
Acta Psychiatr Scand. 2013 Nov;128(5):327-46
pubmed: 23379898
J Abnorm Psychol. 2017 Oct;126(7):969-988
pubmed: 29106281
Psychiatr Clin North Am. 2019 Dec;42(4):611-625
pubmed: 31672211
Med Care. 1992 Jun;30(6):473-83
pubmed: 1593914
Neuroimage. 2012 Aug 15;62(2):1230-3
pubmed: 22023743
Mhealth. 2019 Aug 12;5:25
pubmed: 31559270
J Am Med Inform Assoc. 2018 Dec 1;25(12):1669-1674
pubmed: 30272176
J R Soc Interface. 2017 Nov;14(136):
pubmed: 29187640
JAMA Psychiatry. 2017 Jul 1;74(7):665-666
pubmed: 28514455
Int J Psychiatry Clin Pract. 2007;11(1):36-43
pubmed: 24941274