Identifying mental health status using deep neural network trained by visual metrics.
Journal
Translational psychiatry
ISSN: 2158-3188
Titre abrégé: Transl Psychiatry
Pays: United States
ID NLM: 101562664
Informations de publication
Date de publication:
14 12 2020
14 12 2020
Historique:
received:
08
01
2020
accepted:
20
10
2020
revised:
15
09
2020
entrez:
15
12
2020
pubmed:
16
12
2020
medline:
22
6
2021
Statut:
epublish
Résumé
Mental health is an integral part of the quality of life of cancer patients. It has been found that mental health issues, such as depression and anxiety, are more common in cancer patients. They may result in catastrophic consequences, including suicide. Therefore, monitoring mental health metrics (such as hope, anxiety, and mental well-being) is recommended. Currently, there is lack of objective method for mental health evaluation, and most of the available methods are limited to subjective face-to-face discussions between the patient and psychotherapist. In this study we introduced an objective method for mental health evaluation using a combination of convolutional neural network and long short-term memory (CNN-LSTM) algorithms learned and validated by visual metrics time-series. Data were recorded by the TobiiPro eyeglasses from 16 patients with cancer after major oncologic surgery and nine individuals without cancer while viewing18 artworks in an in-house art gallery. Pre-study and post-study questionnaires of Herth Hope Index (HHI; for evaluation of hope), anxiety State-Trait Anxiety Inventory for Adults (STAI; for evaluation of anxiety) and Warwick-Edinburgh Mental Wellbeing Scale (WEMWBS; for evaluation of mental well-being) were completed by participants. Clinical psychotherapy and statistical suggestions for cutoff scores were used to assign an individual's mental health metrics level during each session into low (class 0), intermediate (class 1), and high (class 2) levels. Our proposed model was used to objectify evaluation and categorize HHI, STAI, and WEMWBS status of individuals. Classification accuracy of the model was 93.81%, 94.76%, and 95.00% for HHI, STAI, and WEMWBS metrics, respectively. The proposed model can be integrated into applications for home-based mental health monitoring to be used by patients after oncologic surgery to identify patients at risk.
Identifiants
pubmed: 33318471
doi: 10.1038/s41398-020-01117-5
pii: 10.1038/s41398-020-01117-5
pmc: PMC7736364
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
430Références
Cancer. 1985 Jan 1;55(1):72-6
pubmed: 3965087
Brain Behav Immun. 2007 Oct;21(7):953-61
pubmed: 17467230
Cancer. 1987 Oct 1;60(7):1661-7
pubmed: 3621136
Psychooncology. 2016 May;25(5):513-20
pubmed: 26356037
Vision Res. 1999 Nov;39(23):3960-74
pubmed: 10748928
Neurology. 1988 Feb;38(2):272-7
pubmed: 3340292
Child Dev. 2008 Nov-Dec;79(6):1752-60
pubmed: 19037947
Biosystems. 2002 Oct-Dec;67(1-3):239-44
pubmed: 12459304
JAMA. 1999 May 19;281(19):1779-81
pubmed: 10340344
Brain. 2007 Jan;130(Pt 1):10-35
pubmed: 17121745
Science. 2000 Feb 18;287(5456):1273-6
pubmed: 10678835
Cancer. 1996 Aug 1;78(3 Suppl):615-26
pubmed: 8681300
Psychophysiology. 2008 Jul;45(4):602-7
pubmed: 18282202
Neuropsychobiology. 1998;37(3):117-23
pubmed: 9597667
Nature. 2006 Feb 23;439(7079):936-42
pubmed: 16495990
Behav Med. 2000 Winter;25(4):152-60
pubmed: 10789021
J Adv Nurs. 1992 Oct;17(10):1251-9
pubmed: 1430629
Nature. 2015 May 28;521(7553):436-44
pubmed: 26017442
Psychol Sci. 2003 Nov;14(6):612-7
pubmed: 14629694
Psychooncology. 2007 Apr;16(4):352-7
pubmed: 16991106
Hum Factors. 2020 Dec;62(8):1365-1386
pubmed: 31560573
Psychooncology. 2002 Jul-Aug;11(4):273-81
pubmed: 12203741
J Psychosom Res. 1999 May;46(5):437-43
pubmed: 10404478
Biol Psychiatry. 2005 May 1;57(9):1052-60
pubmed: 15860346
J Clin Oncol. 2008 Oct 10;26(29):4731-8
pubmed: 18695257
BMJ Open. 2014 Sep 19;4(9):e005878
pubmed: 25239293
Neural Comput. 1997 Nov 15;9(8):1735-80
pubmed: 9377276
Arch Ophthalmol. 1982 May;100(5):755-60
pubmed: 7082205
J Consult Clin Psychol. 2001 Apr;69(2):305-16
pubmed: 11393607
Cancer Nurs. 2012 Jul-Aug;35(4):E14-26
pubmed: 21946906
Comput Biol Med. 2018 Nov 1;102:411-420
pubmed: 30245122
Int J Geriatr Psychiatry. 2005 Jul;20(7):629-34
pubmed: 16021666
Dev Cogn Neurosci. 2017 Jun;25:69-91
pubmed: 27908561
Comput Biol Med. 2018 Mar 1;94:19-26
pubmed: 29358103
Artif Intell Med. 2018 Sep;91:39-48
pubmed: 30026049
J Alzheimers Dis. 2010;19(3):781-93
pubmed: 20157236
Sci Rep. 2019 Sep 16;9(1):13414
pubmed: 31527640
Brain. 1983 Sep;106 (Pt 3):571-87
pubmed: 6640270
Comput Biol Med. 2018 Nov 1;102:278-287
pubmed: 29903630
Biol Psychiatry. 1994 Feb 1;35(3):195-202
pubmed: 8173020
J Pain Symptom Manage. 2013 Nov;46(5):661-70
pubmed: 23535324
J R Soc Med. 2010 Dec;103(12):490-9
pubmed: 21127332
J Physiol. 2007 Jun 15;581(Pt 3):893-8
pubmed: 17430985
Psychol Assess. 2001 Mar;13(1):99-109
pubmed: 11281043
Curr Opin Neurol. 2004 Feb;17(1):17-25
pubmed: 15090873
J Laryngol Otol. 1988 May;102(5):435-9
pubmed: 3397639
J Psychiatr Pract. 2013 Jul;19(4):316-22
pubmed: 23852107