Using heart rate profiles during sleep as a biomarker of depression.
Adolescent
Adult
Aged
Aged, 80 and over
Depression
/ diagnosis
Electrocardiography
/ methods
Electroencephalography
/ methods
Female
Heart Rate
/ physiology
Humans
Machine Learning
Male
Middle Aged
Polysomnography
/ methods
Retrospective Studies
Sleep
/ physiology
Sleep Wake Disorders
/ diagnosis
Young Adult
Autonomic nervous system
Heart rate variability
Major depressive disorder
Journal
BMC psychiatry
ISSN: 1471-244X
Titre abrégé: BMC Psychiatry
Pays: England
ID NLM: 100968559
Informations de publication
Date de publication:
07 06 2019
07 06 2019
Historique:
received:
18
12
2018
accepted:
20
05
2019
entrez:
9
6
2019
pubmed:
9
6
2019
medline:
31
3
2020
Statut:
epublish
Résumé
Abnormalities in heart rate during sleep linked to impaired neuro-cardiac modulation may provide new information about physiological sleep signatures of depression. This study assessed the validity of an algorithm using patterns of heart rate changes during sleep to discriminate between individuals with depression and healthy controls. A heart rate profiling algorithm was modeled using machine-learning based on 1203 polysomnograms from individuals with depression referred to a sleep clinic for the assessment of sleep abnormalities, including insomnia, excessive daytime fatigue, and sleep-related breathing disturbances (n = 664) and mentally healthy controls (n = 529). The final algorithm was tested on a distinct sample (n = 174) to categorize each individual as depressed or not depressed. The resulting categorizations were compared to medical record diagnoses. The algorithm had an overall classification accuracy of 79.9% [sensitivity: 82.8, 95% CI (0.73-0.89), specificity: 77.0, 95% CI (0.67-0.85)]. The algorithm remained highly sensitive across subgroups stratified by age, sex, depression severity, comorbid psychiatric illness, cardiovascular disease, and smoking status. Sleep-derived heart rate patterns could act as an objective biomarker of depression, at least when it co-occurs with sleep disturbances, and may serve as a complimentary objective diagnostic tool. These findings highlight the extent to which some autonomic functions are impaired in individuals with depression, which warrants further investigation about potential underlying mechanisms.
Sections du résumé
BACKGROUND
Abnormalities in heart rate during sleep linked to impaired neuro-cardiac modulation may provide new information about physiological sleep signatures of depression. This study assessed the validity of an algorithm using patterns of heart rate changes during sleep to discriminate between individuals with depression and healthy controls.
METHODS
A heart rate profiling algorithm was modeled using machine-learning based on 1203 polysomnograms from individuals with depression referred to a sleep clinic for the assessment of sleep abnormalities, including insomnia, excessive daytime fatigue, and sleep-related breathing disturbances (n = 664) and mentally healthy controls (n = 529). The final algorithm was tested on a distinct sample (n = 174) to categorize each individual as depressed or not depressed. The resulting categorizations were compared to medical record diagnoses.
RESULTS
The algorithm had an overall classification accuracy of 79.9% [sensitivity: 82.8, 95% CI (0.73-0.89), specificity: 77.0, 95% CI (0.67-0.85)]. The algorithm remained highly sensitive across subgroups stratified by age, sex, depression severity, comorbid psychiatric illness, cardiovascular disease, and smoking status.
CONCLUSIONS
Sleep-derived heart rate patterns could act as an objective biomarker of depression, at least when it co-occurs with sleep disturbances, and may serve as a complimentary objective diagnostic tool. These findings highlight the extent to which some autonomic functions are impaired in individuals with depression, which warrants further investigation about potential underlying mechanisms.
Identifiants
pubmed: 31174510
doi: 10.1186/s12888-019-2152-1
pii: 10.1186/s12888-019-2152-1
pmc: PMC6554996
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
168Références
J Psychiatr Res. 2017 Sep;92:64-73
pubmed: 28411417
Am J Cardiol. 1999 Apr 15;83(8):1242-7
pubmed: 10215292
J Psychiatr Res. 2010 Mar;44(4):242-52
pubmed: 19762038
Ann Intern Med. 2005 Feb 1;142(3):187-97
pubmed: 15684207
Am J Cardiol. 1987 Feb 1;59(4):256-62
pubmed: 3812275
J Clin Endocrinol Metab. 2015 Aug;100(8):3149-58
pubmed: 26046965
Arch Gen Psychiatry. 1992 Aug;49(8):651-68; discussion 669-70
pubmed: 1386215
J Sleep Res. 2014 Dec;23(6):628-635
pubmed: 24909981
Am J Respir Crit Care Med. 1999 May;159(5 Pt 1):1527-32
pubmed: 10228121
Hypertension. 2000 May;35(5):1173-5
pubmed: 10818083
Psychopharmacol Bull. 1993;29(2):201-6
pubmed: 8290666
Am J Respir Crit Care Med. 1995 Mar;151(3 Pt 1):682-7
pubmed: 7881656
Psychol Bull. 2016 Sep;142(9):969-990
pubmed: 27416139
Brain Behav Immun. 2019 Aug;80:219-226
pubmed: 30872091
J Appl Physiol (1985). 2010 Jan;108(1):68-75
pubmed: 19910332
Am Heart J. 1987 Jun;113(6):1489-94
pubmed: 3591616
Sleep Med Rev. 2002 Apr;6(2):97-111
pubmed: 12531146
Psychiatry Res. 2002 Dec 15;113(1-2):139-49
pubmed: 12467953
J Clin Sleep Med. 2007 Mar 15;3(2):121-31
pubmed: 17557422
Auton Neurosci. 2015 Dec;193:138-41
pubmed: 26260435
J ECT. 2004 Jun;20(2):81-8
pubmed: 15167423
Psychiatr Q. 2002 Fall;73(3):195-203
pubmed: 12143081
Arch Gen Psychiatry. 1979 Jan;36(1):85-90
pubmed: 216331
Brain Behav Immun. 2013 Jul;31:189-96
pubmed: 23416033
Am J Cardiol. 1988 Oct 1;62(10 Pt 1):714-7
pubmed: 3421170
PLoS Comput Biol. 2007 Jun;3(6):e116
pubmed: 17604446
Psychosom Med. 2009 Feb;71(2):171-86
pubmed: 19188531
Hypertension. 1991 May;17(5):669-77
pubmed: 2022410
J Psychiatry Neurosci. 2015 Jan;40(1):28-37
pubmed: 25203899
Sleep. 2016 May 01;39(5):1151-64
pubmed: 27070134
Biol Psychiatry. 2010 Jun 1;67(11):1067-74
pubmed: 20138254
J Appl Physiol (1985). 2005 Jun;98(6):2024-32
pubmed: 15718408
Nature. 2002 Dec 19-26;420(6917):853-9
pubmed: 12490958
Lancet. 2009 Aug 22;374(9690):609-19
pubmed: 19640579
J Psychiatr Res. 2014 Dec;59:22-7
pubmed: 25193461
Psychoneuroendocrinology. 2015 Dec;62:18-26
pubmed: 26210676
Psychoneuroendocrinology. 2012 Sep;37(9):1521-30
pubmed: 22406002
Aust N Z J Psychiatry. 1998 Apr;32(2):187-98
pubmed: 9588297
World Health Organ Tech Rep Ser. 2000;894:i-xii, 1-253
pubmed: 11234459
J Clin Invest. 1995 Oct;96(4):1897-904
pubmed: 7560081