Comprehensive evaluation of machine learning algorithms for predicting sleep-wake conditions and differentiating between the wake conditions before and after sleep during pregnancy based on heart rate variability.
deep learning
heart rate variability
machine learning
pregnant women
sleep condition
wake condition
Journal
Frontiers in psychiatry
ISSN: 1664-0640
Titre abrégé: Front Psychiatry
Pays: Switzerland
ID NLM: 101545006
Informations de publication
Date de publication:
2023
2023
Historique:
received:
21
11
2022
accepted:
19
05
2023
medline:
7
7
2023
pubmed:
7
7
2023
entrez:
7
7
2023
Statut:
epublish
Résumé
Perinatal women tend to have difficulties with sleep along with autonomic characteristics. This study aimed to identify a machine learning algorithm capable of achieving high accuracy in predicting sleep-wake conditions and differentiating between the wake conditions before and after sleep during pregnancy based on heart rate variability (HRV). Nine HRV indicators (features) and sleep-wake conditions of 154 pregnant women were measured for 1 week, from the 23rd to the 32nd weeks of pregnancy. Ten machine learning and three deep learning methods were applied to predict three types of sleep-wake conditions (wake, shallow sleep, and deep sleep). In addition, the prediction of four conditions, in which the wake conditions before and after sleep were differentiated-shallow sleep, deep sleep, and the two types of wake conditions-was also tested. In the test for predicting three types of sleep-wake conditions, most of the algorithms, except for Naïve Bayes, showed higher areas under the curve (AUCs; 0.82-0.88) and accuracy (0.78-0.81). The test using four types of sleep-wake conditions with differentiation between the wake conditions before and after sleep also resulted in successful prediction by the gated recurrent unit with the highest AUC (0.86) and accuracy (0.79). Among the nine features, seven made major contributions to predicting sleep-wake conditions. Among the seven features, "the number of interval differences of successive RR intervals greater than 50 ms (NN50)" and "the proportion dividing NN50 by the total number of RR intervals (pNN50)" were useful to predict sleep-wake conditions unique to pregnancy. These findings suggest alterations in the vagal tone system specific to pregnancy.
Identifiants
pubmed: 37415686
doi: 10.3389/fpsyt.2023.1104222
pmc: PMC10322181
doi:
Types de publication
Journal Article
Langues
eng
Pagination
1104222Informations de copyright
Copyright © 2023 Li, Ono, Warita, Shoji, Nakagawa, Usukura, Yu, Takahashi, Ichiji, Sugita, Kobayashi, Kikuchi, Kimura, Hamaie, Hino, Kunii, Murakami, Ishikuro, Obara, Nakamura, Nagami, Takai, Ogishima, Sugawara, Hoshiai, Saito, Tamiya, Fuse, Fujii, Nakayama, Kuriyama, Yamamoto, Yaegashi, Homma and Tomita.
Déclaration de conflit d'intérêts
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Références
Sleep Breath. 2017 Dec;21(4):837-843
pubmed: 28612268
Am J Physiol. 1998 Sep;275(3):H946-50
pubmed: 9724299
J Affect Disord. 2021 Dec 1;295:632-638
pubmed: 34509778
J Sleep Res. 2012 Feb;21(1):122-7
pubmed: 21447050
Electroencephalogr Clin Neurophysiol. 1997 May;102(5):390-6
pubmed: 9191582
Comput Med Imaging Graph. 2017 Sep;60:42-49
pubmed: 28087102
Hypertens Res. 2005 Feb;28(2):113-8
pubmed: 16025737
Circ J. 2022 Jan 25;86(2):189-191
pubmed: 34471069
Psychophysiology. 1983 Sep;20(5):562-8
pubmed: 6635096
BMC Pregnancy Childbirth. 2012 Dec 10;12:144
pubmed: 23228137
Aust N Z J Obstet Gynaecol. 2011 Feb;51(1):38-46
pubmed: 21299507
Biol Psychol. 2015 Oct;111:83-9
pubmed: 26316361
Front Physiol. 2018 Jan 10;8:1100
pubmed: 29367845
Sleep. 2007 Oct;30(10):1362-9
pubmed: 17969470
Heart. 2000 Mar;83(3):290-4
pubmed: 10677408
Annu Int Conf IEEE Eng Med Biol Soc. 2008;2008:1151-4
pubmed: 19162868
Sleep Med. 2007 Jun;8(4):302-30
pubmed: 17468046
IEEE Trans Biomed Eng. 2009 Apr;56(4):1005-14
pubmed: 19272873
Comput Biol Med. 2017 Oct 1;89:389-396
pubmed: 28869899
Front Psychiatry. 2022 Jan 27;12:799029
pubmed: 35153864
Ann Biomed Eng. 2016 Oct;44(10):3124-3135
pubmed: 27059225
Sleep. 2005 Oct;28(10):1299-305
pubmed: 16295215
J Epidemiol. 2016 Sep 5;26(9):493-511
pubmed: 27374138
J Auton Nerv Syst. 1994 Apr;47(1-2):121-9
pubmed: 8188978
Electroencephalogr Clin Neurophysiol. 1995 Mar;94(3):155-62
pubmed: 7536150
Physiol Meas. 2018 Dec 21;39(12):124005
pubmed: 30524025
Eur Heart J. 1996 Mar;17(3):354-81
pubmed: 8737210
J Sleep Res. 2000 Mar;9(1):13-8
pubmed: 10733684
JMIR Med Inform. 2020 Apr 30;8(4):e15516
pubmed: 32352387
Artif Intell Med. 2019 Jun;97:79-88
pubmed: 30477892
Curr Psychiatry Rep. 2019 Mar 2;21(3):20
pubmed: 30826881
Nat Med. 2023 Jan;29(1):247-257
pubmed: 36265510
Neural Netw. 2019 Aug;116:237-245
pubmed: 31121421
J Sleep Res. 2011 Mar;20(1 Pt 2):183-200
pubmed: 20374444
Behav Sleep Med. 2017 Nov-Dec;15(6):451-465
pubmed: 27149648
Australas Phys Eng Sci Med. 2019 Dec;42(4):959-979
pubmed: 31515685
Circ J. 2022 Jan 25;86(2):182-188
pubmed: 34148927
IEEE Trans Neural Netw Learn Syst. 2020 Nov;31(11):4688-4698
pubmed: 31902775
Obstet Gynecol. 2010 Jan;115(1):77-83
pubmed: 20027038
Chest. 2000 Feb;117(2):460-6
pubmed: 10669691
Entropy (Basel). 2022 Jun 20;24(6):
pubmed: 35741565
Int J Psychophysiol. 1986 Jul;4(2):129-41
pubmed: 3733490
Hellenic J Cardiol. 2006 Jan-Feb;47(1):13-20
pubmed: 16532711
Sensors (Basel). 2020 Dec 23;21(1):
pubmed: 33374527
Neurosci Biobehav Rev. 2017 Mar;74(Pt B):321-329
pubmed: 27397854
Sleep Med. 2015 Apr;16(4):483-8
pubmed: 25666847
Ital J Neurol Sci. 1996 Dec;17(6):437-9
pubmed: 8978452
Int J Behav Nutr Phys Act. 2015 Dec 18;12:159
pubmed: 26684758
J Clin Sleep Med. 2016 Feb;12(2):215-23
pubmed: 26414976
J Healthc Inform Res. 2018 Apr 20;2(1-2):152-178
pubmed: 35415400
Ann Intern Med. 1993 Mar 15;118(6):436-47
pubmed: 8439119
Psychosom Med. 2004 Jan-Feb;66(1):56-62
pubmed: 14747638
Biol Psychol. 2005 Apr;69(1):23-38
pubmed: 15740823
Comput Methods Programs Biomed. 2012 Oct;108(1):10-9
pubmed: 22178068
J Child Psychol Psychiatry. 2014;55(2):172-9
pubmed: 24117807
Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:6784-6788
pubmed: 31947398
Swiss Med Wkly. 2004 Sep 4;134(35-36):514-22
pubmed: 15517504
J Sports Med Phys Fitness. 2008 Dec;48(4):495-501
pubmed: 18997654
Physiologie. 1989 Jan-Mar;26(1):39-49
pubmed: 2502783
Neural Netw. 2005 Jun-Jul;18(5-6):602-10
pubmed: 16112549
Clin Sci (Lond). 2023 Apr 26;137(8):697-706
pubmed: 36661051
IEEE Trans Biomed Eng. 2003 Oct;50(10):1143-51
pubmed: 14560767
Sleep. 1992 Oct;15(5):461-9
pubmed: 1455130
Sleep Med Rev. 2020 Feb;49:101227
pubmed: 31901524
Ann Behav Med. 2021 Mar 16;55(2):155-164
pubmed: 32525208
Sci Rep. 2019 Oct 2;9(1):14149
pubmed: 31578345
Eur Neurol. 2009;62(1):23-9
pubmed: 19407452
Sleep. 2020 Sep 14;43(9):
pubmed: 32249911
Am J Physiol. 1997 Oct;273(4):H1761-8
pubmed: 9362241
Stem Cells Int. 2023 Jan 5;2023:7545635
pubmed: 36644009
J Clin Monit Comput. 2014 Oct;28(5):481-6
pubmed: 23508826
Comput Methods Programs Biomed. 2013 Oct;112(1):47-57
pubmed: 23895941
Conf Proc IEEE Eng Med Biol Soc. 2005;2005:5523-5
pubmed: 17281504
Biol Psychol. 2003 May;63(2):149-62
pubmed: 12738405
Psychosom Med. 2014 Jan;76(1):66-73
pubmed: 24367127
Med Biol Eng Comput. 2006 Dec;44(12):1031-51
pubmed: 17111118
PLoS One. 2015 Aug 31;10(8):e0136661
pubmed: 26322889
Behav Brain Sci. 2000 Dec;23(6):851-66; discussion 904-1121
pubmed: 11515145
Stud Health Technol Inform. 2019 Aug 21;264:888-892
pubmed: 31438052
Sleep Med. 2002 Jan;3(1):37-42
pubmed: 14592252
Curr Psychiatry Rep. 2016 Jul;18(7):66
pubmed: 27222140
Sleep Med Rev. 2012 Feb;16(1):47-66
pubmed: 21658979
Int J Epidemiol. 2020 Feb 1;49(1):18-19m
pubmed: 31504573