Predictive Modeling of Mental Illness Onset Using Wearable Devices and Medical Examination Data: Machine Learning Approach

The prevention and treatment of mental illness is a serious social issue. Prediction and intervention, however, have been difficult because of lack of objective biomarkers for mental illness. The objective of this study was to use biometric data acquired from wearable devices as well as medical exam...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Frontiers in digital health Jg. 4; S. 861808
Hauptverfasser: Saito, Tomoki, Suzuki, Hikaru, Kishi, Akifumi
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Switzerland Frontiers Media S.A 14.04.2022
Schlagworte:
ISSN:2673-253X, 2673-253X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract The prevention and treatment of mental illness is a serious social issue. Prediction and intervention, however, have been difficult because of lack of objective biomarkers for mental illness. The objective of this study was to use biometric data acquired from wearable devices as well as medical examination data to build a predictive model that can contribute to the prevention of the onset of mental illness. This was an observational study of 4,612 subjects from the health database of society-managed health insurance in Japan provided by JMDC Inc. The inputs to the predictive model were 3-months of continuous wearable data and medical examinations within and near that period; the output was the presence or absence of mental illness over the following month, as defined by insurance claims data. The features relating to the wearable data were sleep, activity, and resting heart rate, measured by a consumer-grade wearable device (specifically, Fitbit). The predictive model was built using the XGBoost algorithm and presented an area-under-the-receiver-operating-characteristic curve of 0.712 ( SD = 0.02, a repeated stratified group 10-fold cross validation). The top-ranking feature importance measure was wearable data, and its importance was higher than the blood-test values from medical examinations. Detailed verification of the model showed that predictions were made based on disrupted sleep rhythms, mild physical activity duration, alcohol use, and medical examination data on disrupted eating habits as risk factors. In summary, the predictive model showed useful accuracy for grouping the risk of mental illness onset, suggesting the potential of predictive detection, and preventive intervention using wearable devices. Sleep abnormalities in particular were detected as wearable data 3 months prior to mental illness onset, and the possibility of early intervention targeting the stabilization of sleep as an effective measure for mental illness onset was shown.
AbstractList The prevention and treatment of mental illness is a serious social issue. Prediction and intervention, however, have been difficult because of lack of objective biomarkers for mental illness. The objective of this study was to use biometric data acquired from wearable devices as well as medical examination data to build a predictive model that can contribute to the prevention of the onset of mental illness. This was an observational study of 4,612 subjects from the health database of society-managed health insurance in Japan provided by JMDC Inc. The inputs to the predictive model were 3-months of continuous wearable data and medical examinations within and near that period; the output was the presence or absence of mental illness over the following month, as defined by insurance claims data. The features relating to the wearable data were sleep, activity, and resting heart rate, measured by a consumer-grade wearable device (specifically, Fitbit). The predictive model was built using the XGBoost algorithm and presented an area-under-the-receiver-operating-characteristic curve of 0.712 (SD = 0.02, a repeated stratified group 10-fold cross validation). The top-ranking feature importance measure was wearable data, and its importance was higher than the blood-test values from medical examinations. Detailed verification of the model showed that predictions were made based on disrupted sleep rhythms, mild physical activity duration, alcohol use, and medical examination data on disrupted eating habits as risk factors. In summary, the predictive model showed useful accuracy for grouping the risk of mental illness onset, suggesting the potential of predictive detection, and preventive intervention using wearable devices. Sleep abnormalities in particular were detected as wearable data 3 months prior to mental illness onset, and the possibility of early intervention targeting the stabilization of sleep as an effective measure for mental illness onset was shown.The prevention and treatment of mental illness is a serious social issue. Prediction and intervention, however, have been difficult because of lack of objective biomarkers for mental illness. The objective of this study was to use biometric data acquired from wearable devices as well as medical examination data to build a predictive model that can contribute to the prevention of the onset of mental illness. This was an observational study of 4,612 subjects from the health database of society-managed health insurance in Japan provided by JMDC Inc. The inputs to the predictive model were 3-months of continuous wearable data and medical examinations within and near that period; the output was the presence or absence of mental illness over the following month, as defined by insurance claims data. The features relating to the wearable data were sleep, activity, and resting heart rate, measured by a consumer-grade wearable device (specifically, Fitbit). The predictive model was built using the XGBoost algorithm and presented an area-under-the-receiver-operating-characteristic curve of 0.712 (SD = 0.02, a repeated stratified group 10-fold cross validation). The top-ranking feature importance measure was wearable data, and its importance was higher than the blood-test values from medical examinations. Detailed verification of the model showed that predictions were made based on disrupted sleep rhythms, mild physical activity duration, alcohol use, and medical examination data on disrupted eating habits as risk factors. In summary, the predictive model showed useful accuracy for grouping the risk of mental illness onset, suggesting the potential of predictive detection, and preventive intervention using wearable devices. Sleep abnormalities in particular were detected as wearable data 3 months prior to mental illness onset, and the possibility of early intervention targeting the stabilization of sleep as an effective measure for mental illness onset was shown.
The prevention and treatment of mental illness is a serious social issue. Prediction and intervention, however, have been difficult because of lack of objective biomarkers for mental illness. The objective of this study was to use biometric data acquired from wearable devices as well as medical examination data to build a predictive model that can contribute to the prevention of the onset of mental illness. This was an observational study of 4,612 subjects from the health database of society-managed health insurance in Japan provided by JMDC Inc. The inputs to the predictive model were 3-months of continuous wearable data and medical examinations within and near that period; the output was the presence or absence of mental illness over the following month, as defined by insurance claims data. The features relating to the wearable data were sleep, activity, and resting heart rate, measured by a consumer-grade wearable device (specifically, Fitbit). The predictive model was built using the XGBoost algorithm and presented an area-under-the-receiver-operating-characteristic curve of 0.712 ( SD = 0.02, a repeated stratified group 10-fold cross validation). The top-ranking feature importance measure was wearable data, and its importance was higher than the blood-test values from medical examinations. Detailed verification of the model showed that predictions were made based on disrupted sleep rhythms, mild physical activity duration, alcohol use, and medical examination data on disrupted eating habits as risk factors. In summary, the predictive model showed useful accuracy for grouping the risk of mental illness onset, suggesting the potential of predictive detection, and preventive intervention using wearable devices. Sleep abnormalities in particular were detected as wearable data 3 months prior to mental illness onset, and the possibility of early intervention targeting the stabilization of sleep as an effective measure for mental illness onset was shown.
The prevention and treatment of mental illness is a serious social issue. Prediction and intervention, however, have been difficult because of lack of objective biomarkers for mental illness. The objective of this study was to use biometric data acquired from wearable devices as well as medical examination data to build a predictive model that can contribute to the prevention of the onset of mental illness. This was an observational study of 4,612 subjects from the health database of society-managed health insurance in Japan provided by JMDC Inc. The inputs to the predictive model were 3-months of continuous wearable data and medical examinations within and near that period; the output was the presence or absence of mental illness over the following month, as defined by insurance claims data. The features relating to the wearable data were sleep, activity, and resting heart rate, measured by a consumer-grade wearable device (specifically, Fitbit). The predictive model was built using the XGBoost algorithm and presented an area-under-the-receiver-operating-characteristic curve of 0.712 (SD = 0.02, a repeated stratified group 10-fold cross validation). The top-ranking feature importance measure was wearable data, and its importance was higher than the blood-test values from medical examinations. Detailed verification of the model showed that predictions were made based on disrupted sleep rhythms, mild physical activity duration, alcohol use, and medical examination data on disrupted eating habits as risk factors. In summary, the predictive model showed useful accuracy for grouping the risk of mental illness onset, suggesting the potential of predictive detection, and preventive intervention using wearable devices. Sleep abnormalities in particular were detected as wearable data 3 months prior to mental illness onset, and the possibility of early intervention targeting the stabilization of sleep as an effective measure for mental illness onset was shown.
The prevention and treatment of mental illness is a serious social issue. Prediction and intervention, however, have been difficult because of lack of objective biomarkers for mental illness. The objective of this study was to use biometric data acquired from wearable devices as well as medical examination data to build a predictive model that can contribute to the prevention of the onset of mental illness. This was an observational study of 4,612 subjects from the health database of society-managed health insurance in Japan provided by JMDC Inc. The inputs to the predictive model were 3-months of continuous wearable data and medical examinations within and near that period; the output was the presence or absence of mental illness over the following month, as defined by insurance claims data. The features relating to the wearable data were sleep, activity, and resting heart rate, measured by a consumer-grade wearable device (specifically, Fitbit). The predictive model was built using the XGBoost algorithm and presented an area-under-the-receiver-operating-characteristic curve of 0.712 ( = 0.02, a repeated stratified group 10-fold cross validation). The top-ranking feature importance measure was wearable data, and its importance was higher than the blood-test values from medical examinations. Detailed verification of the model showed that predictions were made based on disrupted sleep rhythms, mild physical activity duration, alcohol use, and medical examination data on disrupted eating habits as risk factors. In summary, the predictive model showed useful accuracy for grouping the risk of mental illness onset, suggesting the potential of predictive detection, and preventive intervention using wearable devices. Sleep abnormalities in particular were detected as wearable data 3 months prior to mental illness onset, and the possibility of early intervention targeting the stabilization of sleep as an effective measure for mental illness onset was shown.
Author Saito, Tomoki
Kishi, Akifumi
Suzuki, Hikaru
AuthorAffiliation 1 JMDC Inc. , Tokyo , Japan
2 Graduate School of Education, The University of Tokyo , Tokyo , Japan
AuthorAffiliation_xml – name: 1 JMDC Inc. , Tokyo , Japan
– name: 2 Graduate School of Education, The University of Tokyo , Tokyo , Japan
Author_xml – sequence: 1
  givenname: Tomoki
  surname: Saito
  fullname: Saito, Tomoki
– sequence: 2
  givenname: Hikaru
  surname: Suzuki
  fullname: Suzuki, Hikaru
– sequence: 3
  givenname: Akifumi
  surname: Kishi
  fullname: Kishi, Akifumi
BackLink https://www.ncbi.nlm.nih.gov/pubmed/35493532$$D View this record in MEDLINE/PubMed
BookMark eNp9kk1vEzEQhleoiH7QH8AF-cglwR_r3TUHpKotEClROVDBzZrYs4krxw72JgJ-fZ2kVC0HTrZm3vcZy_OeVkchBqyqN4yOhejU-94uhuWYU87HXcM62r2oTnjTihGX4sfRk_txdZ7zHaWUS8Y5la-qYyFrJaTgJ9WfrwmtM4PbIplFi96FBYk9mWEYwJOJ9wFzJjch40Bu8677HSHB3CO5wq0zmAkEW_SFUgzXv2DlAgwuBnIFA3wgMzBLF5BMiy3s_BfrdYql-Lp62YPPeP5wnlW3n66_XX4ZTW8-Ty4vpiMjBRtGKC0IOu9boH1rqGBqrqwCi8jqtpXU0rlCZRtgDAXwxiBnLYWGYidbJZg4qyYHro1wp9fJrSD91hGc3hdiWmhIgzMetW0lyKbrueFQ15wCdEaJWlHBuezAFtbHA2u9ma_QmvJLCfwz6PNOcEu9iFutaN00qimAdw-AFH9uMA965bJB7yFg3GTNG9k1ZTk1LdK3T2c9Dvm7vCJgB4FJMeeE_aOEUb3LiN5nRO8yog8ZKZ72H49xw35d5bnO_8d5Dx1bwyE
CitedBy_id crossref_primary_10_2196_59660
crossref_primary_10_1016_j_ajp_2024_104168
crossref_primary_10_1371_journal_pone_0304932
crossref_primary_10_3389_fpsyt_2024_1291299
crossref_primary_10_1126_sciadv_adv2643
crossref_primary_10_1038_s41746_023_00890_z
crossref_primary_10_1109_ACCESS_2025_3577968
crossref_primary_10_1109_JSEN_2023_3303436
crossref_primary_10_1371_journal_pdig_0000473
crossref_primary_10_3389_fpubh_2023_1190464
crossref_primary_10_2196_77066
crossref_primary_10_1142_S0218126625504328
crossref_primary_10_18267_j_aip_243
crossref_primary_10_1192_bja_2025_10133
crossref_primary_10_3390_ijerph191911913
Cites_doi 10.1016/S2215-0366(20)30136-X
10.1073/pnas.1312114110
10.1001/jama.262.11.1479
10.1016/S0140-6736(13)61611-6
10.1145/1882471.1882479
10.1016/j.bpsc.2017.11.007
10.1038/s41591-018-0300-7
10.1016/j.cub.2016.04.011
10.2196/16273
10.1016/j.biopsych.2004.04.005
10.1016/j.jad.2020.09.118
10.1002/jgf2.367
10.1016/j.jad.2018.11.077
10.1016/j.jad.2013.12.007
10.1080/07420520500545979
10.2196/18694
10.1109/MSMC.2018.2806565
10.1093/sleep/zsz254
10.1111/jcmm.14170
10.1007/s11920-018-0925-8
10.1093/sleep/zsaa291
10.1016/0006-3223(95)00188-3
10.5665/sleep.1396
10.1111/jsr.12931
10.1001/jamaneurol.2020.2108
10.1093/ije/dyu038
10.1109/ICDM.2003.1250950
10.1176/appi.ajp.162.10.1785
10.1098/rspb.2017.0882
10.1001/jamainternmed.2019.0142
10.1080/07420528.2017.1413578
10.1016/j.jad.2017.04.021
10.15420/ecr.2019.02
10.1016/j.maturitas.2018.03.016
10.1016/j.smrv.2017.12.002
10.1016/j.jad.2012.07.001
10.2196/jmir.9410
10.1093/sleep/zsaa141
10.1109/JBHI.2015.2440764
10.1371/journal.pone.0165267
10.1186/s12966-015-0314-1
10.1038/s41746-020-0226-6
10.1146/annurev-clinpsy-032816-044949
10.1109/RBME.2018.2811735
10.2196/10527
10.1038/nature08227
10.1176/ajp.157.1.81
10.1145/3422821
10.1371/journal.pone.0043539
10.1152/ajpregu.00925.2007
10.1016/j.jad.2017.04.030
10.1177/0748730402239679
10.1038/s41598-018-32402-510.1038/s41598-020-59762-1
10.1152/ajpregu.00349.2016
10.1249/MSS.0000000000001947
10.1016/j.sleep.2019.03.009
10.1016/j.jpsychores.2019.109822
10.2196/1102910.2196/15966
10.1080/07420528.2020.1746796
10.1038/s41598-017-03171-4
10.1109/ACCESS.2020.3010715
10.1103/PhysRevLett.99.138103
10.1038/s41746-021-00400-z
10.1145/2939672.2939785
10.1037/t02254-000
10.1146/annurev-clinpsy-032816-045037
10.1111/jsr.12944
10.3109/09540261.2014.911149
10.3390/ijerph17010331
10.1145/3398069
10.1002/phy2.152
10.1093/sleep/zsz180
ContentType Journal Article
Copyright Copyright © 2022 Saito, Suzuki and Kishi.
Copyright © 2022 Saito, Suzuki and Kishi. 2022 Saito, Suzuki and Kishi
Copyright_xml – notice: Copyright © 2022 Saito, Suzuki and Kishi.
– notice: Copyright © 2022 Saito, Suzuki and Kishi. 2022 Saito, Suzuki and Kishi
DBID AAYXX
CITATION
NPM
7X8
5PM
DOA
DOI 10.3389/fdgth.2022.861808
DatabaseName CrossRef
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
CrossRef

PubMed

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2673-253X
ExternalDocumentID oai_doaj_org_article_d75a568f2c2a4420aa8c9349032258ad
PMC9046696
35493532
10_3389_fdgth_2022_861808
Genre Journal Article
GroupedDBID 53G
9T4
AAFWJ
AAYXX
AFPKN
ALMA_UNASSIGNED_HOLDINGS
CITATION
GROUPED_DOAJ
M~E
OK1
PGMZT
RPM
ACXDI
NPM
7X8
5PM
ID FETCH-LOGICAL-c531t-e5da30bf7a0f7c0319b9d9adee147750d0b9e9d6a11e3a26ce2170a60e8579313
IEDL.DBID DOA
ISICitedReferencesCount 17
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001030200700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2673-253X
IngestDate Fri Oct 03 12:44:01 EDT 2025
Tue Sep 30 16:51:36 EDT 2025
Thu Sep 04 17:13:18 EDT 2025
Thu Jan 02 22:54:07 EST 2025
Tue Nov 18 22:25:17 EST 2025
Sat Nov 29 03:17:42 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords predictive detection
sleep
mental illness
wearable data
mHealth
machine learning
medical examination
physical activity
Language English
License Copyright © 2022 Saito, Suzuki and Kishi.
This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c531t-e5da30bf7a0f7c0319b9d9adee147750d0b9e9d6a11e3a26ce2170a60e8579313
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
This article was submitted to Personalized Medicine, a section of the journal Frontiers in Digital Health
Reviewed by: Ming Huang, Nara Institute of Science and Technology (NAIST), Japan; Raffaele Gravina, University of Calabria, Italy
Edited by: Akane Sano, Rice University, United States
OpenAccessLink https://doaj.org/article/d75a568f2c2a4420aa8c9349032258ad
PMID 35493532
PQID 2658649340
PQPubID 23479
ParticipantIDs doaj_primary_oai_doaj_org_article_d75a568f2c2a4420aa8c9349032258ad
pubmedcentral_primary_oai_pubmedcentral_nih_gov_9046696
proquest_miscellaneous_2658649340
pubmed_primary_35493532
crossref_primary_10_3389_fdgth_2022_861808
crossref_citationtrail_10_3389_fdgth_2022_861808
PublicationCentury 2000
PublicationDate 2022-04-14
PublicationDateYYYYMMDD 2022-04-14
PublicationDate_xml – month: 04
  year: 2022
  text: 2022-04-14
  day: 14
PublicationDecade 2020
PublicationPlace Switzerland
PublicationPlace_xml – name: Switzerland
PublicationTitle Frontiers in digital health
PublicationTitleAlternate Front Digit Health
PublicationYear 2022
Publisher Frontiers Media S.A
Publisher_xml – name: Frontiers Media S.A
References Wright (B44) 2017; 312
Thieme (B11) 2020; 27
Kessler (B1) 2007; 6
Leary (B67) 2020; 77
van de Leemput (B72) 2014; 111
Horne (B28) 1976; 4
Bent (B40) 2020; 3
Kim (B16) 2015; 19
Phillips (B26) 2017; 7
Ojio (B32) 2020; 37
Brooks (B68) 2020; 17
Murray (B69) 2019; 58
Walch (B43) 2019; 42
Sano (B15) 2012; 7
Cho (B17) 2019; 21
Cook (B45) 2017; 217
Kishi (B63) 2008; 294
de Zambotti (B46) 2018; 35
Fang (B13) 2021; 4
Dwyer (B8) 2018; 14
Straiton (B52) 2018; 112
Haghayegh (B54) 2019; 21
Forman (B36) 2010; 12
Nakamura (B14) 2007; 99
Ford (B57) 1989; 262
Hamill (B48) 2020; 29
Foo (B73) 2017; 284
Arfken (B62) 2014; 156
Chen (B33) 2016
Chikersal (B12) 2021; 28
Steel (B2) 2014; 43
Freeman (B61) 2020; 7
Feehan (B53) 2018; 6
Sano (B18) 2018; 20
Zheng (B6) 2018; 4
Mohr (B7) 2017; 13
Wittmann (B23) 2006; 23
Kahawage (B47) 2020; 29
Pesonen (B66) 2019; 245
Roenneberg (B25) 2016; 26
Svensson (B39) 2019; 126
Baron (B24) 2014; 26
Taylor (B31) 2018; 20
Setoyama (B20) 2021; 279
Perkins (B5) 2005; 162
Kishi (B64) 2011; 34
Evenson (B22) 2015; 12
de Zambotti (B42) 2019; 51
Burton (B70) 2013; 145
Roenneberg (B29) 2003; 18
Au (B30) 2017; 218
Gholamiangonabadi (B35) 2020; 8
Whiteford (B3) 2013; 382
Lunsford-Avery (B27) 2020; 10
Depner (B38) 2020; 43
Kishi (B65) 2013; 1
Chinoy (B50) 2021; 44
Fuller (B55) 2020; 8
Scheffer (B71) 2009; 461
Bliwise (B41) 2021; 44
Roberts (B59) 2000; 157
Topol (B10) 2019; 25
Breslau (B58) 1996; 39
Rush (B4) 2004; 56
Nagai (B21) 2020; 21
Massoomi (B51) 2019; 14
Baron (B37) 2018; 40
Setoyama (B19) 2016; 11
Zadrozny (B34) 2003
Roomkham (B49) 2018; 11
Bzdok (B9) 2018; 3
Fang (B60) 2019; 23
Greenland (B56) 2019; 179
References_xml – volume: 7
  start-page: 628
  year: 2020
  ident: B61
  article-title: Sleep disturbance and psychiatric disorders
  publication-title: Lancet Psychiatry.
  doi: 10.1016/S2215-0366(20)30136-X
– volume: 111
  start-page: 87
  year: 2014
  ident: B72
  article-title: Critical slowing down as early warning for the onset and termination of depression
  publication-title: Proc Natl Acad Sci U S A.
  doi: 10.1073/pnas.1312114110
– volume: 262
  start-page: 1479
  year: 1989
  ident: B57
  article-title: Epidemiologic study of sleep disturbances and psychiatric disorders. An opportunity for prevention?
  publication-title: JAMA.
  doi: 10.1001/jama.262.11.1479
– volume: 382
  start-page: 1575
  year: 2013
  ident: B3
  article-title: Global burden of disease attributable to mental and substance use disorders: findings from the Global Burden of Disease Study 2010
  publication-title: Lancet.
  doi: 10.1016/S0140-6736(13)61611-6
– volume: 12
  start-page: 49
  year: 2010
  ident: B36
  article-title: Apples-to-apples in cross-validation studies: pitfalls in classifier performance measurement
  publication-title: ACM SIGKDD Explor Newsl.
  doi: 10.1145/1882471.1882479
– volume: 3
  start-page: 223
  year: 2018
  ident: B9
  article-title: Machine learning for precision psychiatry: opportunities and challenges
  publication-title: Biol Psychiatry Cogn Neurosci Neuroimaging.
  doi: 10.1016/j.bpsc.2017.11.007
– volume: 25
  start-page: 44
  year: 2019
  ident: B10
  article-title: High-performance medicine: the convergence of human and artificial intelligence
  publication-title: Nat Med.
  doi: 10.1038/s41591-018-0300-7
– volume: 26
  start-page: R432
  year: 2016
  ident: B25
  article-title: The circadian clock and human health
  publication-title: Curr Biol.
  doi: 10.1016/j.cub.2016.04.011
– volume: 21
  start-page: e16273
  year: 2019
  ident: B54
  article-title: Accuracy of wristband Fitbit models in assessing sleep: systematic review and meta-analysis
  publication-title: J Med Internet Res.
  doi: 10.2196/16273
– volume: 56
  start-page: 46
  year: 2004
  ident: B4
  article-title: One-year clinical outcomes of depressed public sector outpatients: a benchmark for subsequent studies
  publication-title: Biol Psychiat.
  doi: 10.1016/j.biopsych.2004.04.005
– volume: 279
  start-page: 20
  year: 2021
  ident: B20
  article-title: Personality classification enhances blood metabolome analysis and biotyping for major depressive disorders: two-species investigation
  publication-title: J Affect Disord.
  doi: 10.1016/j.jad.2020.09.118
– volume: 21
  start-page: 211
  year: 2020
  ident: B21
  article-title: Data resource profile: JMDC claims databases sourced from medical institutions
  publication-title: J Gen Fam Med.
  doi: 10.1002/jgf2.367
– volume: 245
  start-page: 757
  year: 2019
  ident: B66
  article-title: REM sleep fragmentation associated with depressive symptoms and genetic risk for depression in a community-based sample of adolescents
  publication-title: J Affect Disord.
  doi: 10.1016/j.jad.2018.11.077
– volume: 156
  start-page: 36
  year: 2014
  ident: B62
  article-title: The status of sleep abnormalities as a diagnostic test for major depressive disorder
  publication-title: J Affect Disord.
  doi: 10.1016/j.jad.2013.12.007
– volume: 23
  start-page: 497
  year: 2006
  ident: B23
  article-title: Social jetlag: misalignment of biological and social time
  publication-title: Chronobiol Int.
  doi: 10.1080/07420520500545979
– volume: 8
  start-page: e18694
  year: 2020
  ident: B55
  article-title: Reliability and validity of commercially available wearable devices for measuring steps, energy expenditure, and heart rate: systematic review
  publication-title: JMIR mHealth uHealth.
  doi: 10.2196/18694
– volume: 4
  start-page: 6
  year: 2018
  ident: B6
  article-title: An emerging wearable world: new gadgetry produces a rising tide of changes and challenges
  publication-title: IEEE Syst Man Cybern Mag.
  doi: 10.1109/MSMC.2018.2806565
– volume: 43
  start-page: zsz254
  year: 2020
  ident: B38
  article-title: Wearable technologies for developing sleep and circadian biomarkers: a summary of workshop discussions
  publication-title: Sleep
  doi: 10.1093/sleep/zsz254
– volume: 23
  start-page: 2324
  year: 2019
  ident: B60
  article-title: Depression in sleep disturbance: a review on a bidirectional relationship, mechanisms and treatment
  publication-title: J Cell Mol Med.
  doi: 10.1111/jcmm.14170
– volume: 20
  start-page: 59
  year: 2018
  ident: B31
  article-title: Chronotype and mental health: recent advances
  publication-title: Curr Psychiatry Rep.
  doi: 10.1007/s11920-018-0925-8
– volume: 44
  start-page: zsaa291
  year: 2021
  ident: B50
  article-title: Performance of seven consumer sleep-tracking devices compared with polysomnography
  publication-title: Sleep
  doi: 10.1093/sleep/zsaa291
– volume: 39
  start-page: 411
  year: 1996
  ident: B58
  article-title: Sleep disturbance and psychiatric disorders: a longitudinal epidemiological study of young adults
  publication-title: Biol Psychiatry.
  doi: 10.1016/0006-3223(95)00188-3
– volume: 34
  start-page: 1551
  year: 2011
  ident: B64
  article-title: Sleep-stage dynamics in patients with chronic fatigue syndrome with or without fibromyalgia
  publication-title: Sleep.
  doi: 10.5665/sleep.1396
– volume: 29
  start-page: e12931
  year: 2020
  ident: B47
  article-title: Validity, potential clinical utility, and comparison of consumer and research-grade activity trackers in Insomnia Disorder I: In-lab validation against polysomnography
  publication-title: J Sleep Res.
  doi: 10.1111/jsr.12931
– volume: 77
  start-page: 1241
  year: 2020
  ident: B67
  article-title: Association of rapid eye movement sleep with mortality in middle-aged and older adults
  publication-title: JAMA Neurol.
  doi: 10.1001/jamaneurol.2020.2108
– volume: 43
  start-page: 476
  year: 2014
  ident: B2
  article-title: The global prevalence of common mental disorders: a systematic review and meta-analysis 1980–2013
  publication-title: Int J Epidemiol.
  doi: 10.1093/ije/dyu038
– start-page: 435
  volume-title: Proceedings of the Third IEEE International Conference on Data Mining
  year: 2003
  ident: B34
  article-title: Cost-sensitive learning by cost-proportionate example weighting
  doi: 10.1109/ICDM.2003.1250950
– volume: 162
  start-page: 1785
  year: 2005
  ident: B5
  article-title: Relationship between duration of untreated psychosis and outcome in first-episode schizophrenia: a critical review and meta-analysis
  publication-title: Am J Psychiat.
  doi: 10.1176/appi.ajp.162.10.1785
– volume: 284
  start-page: 20170882
  year: 2017
  ident: B73
  article-title: Dynamical state transitions into addictive behavior and their early-warning signals
  publication-title: Proc R Soc B.
  doi: 10.1098/rspb.2017.0882
– volume: 179
  start-page: 605
  year: 2019
  ident: B56
  article-title: Precision preventive medicine–ready for prime time?
  publication-title: JAMA Int Med.
  doi: 10.1001/jamainternmed.2019.0142
– volume: 35
  start-page: 465
  year: 2018
  ident: B46
  article-title: A validation study of Fitbit Charge 2™ compared with polysomnography in adults
  publication-title: Chronobiol Int.
  doi: 10.1080/07420528.2017.1413578
– volume: 218
  start-page: 93
  year: 2017
  ident: B30
  article-title: The relationship between chronotype and depressive symptoms: a meta-analysis
  publication-title: J Affect Disord.
  doi: 10.1016/j.jad.2017.04.021
– volume: 14
  start-page: 181
  year: 2019
  ident: B51
  article-title: Increasing and evolving role of smart devices in modern medicine
  publication-title: Eur Cardiol.
  doi: 10.15420/ecr.2019.02
– volume: 6
  start-page: 168
  year: 2007
  ident: B1
  article-title: Lifetime prevalence and age-of-onset distributions of mental disorders in the World Health Organization's World Mental Health Survey Initiative
  publication-title: World Psychiatry.
– volume: 112
  start-page: 85
  year: 2018
  ident: B52
  article-title: The validity and reliability of consumer-grade activity trackers in older, community-dwelling adults: a systematic review
  publication-title: Maturitas.
  doi: 10.1016/j.maturitas.2018.03.016
– volume: 40
  start-page: 151
  year: 2018
  ident: B37
  article-title: Feeling validated yet? A scoping review of the use of consumer-targeted wearable and mobile technology to measure and improve sleep
  publication-title: Sleep Med Rev.
  doi: 10.1016/j.smrv.2017.12.002
– volume: 145
  start-page: 21
  year: 2013
  ident: B70
  article-title: Activity monitoring in patients with depression: a systematic review
  publication-title: J Affect Disord.
  doi: 10.1016/j.jad.2012.07.001
– volume: 20
  start-page: e210
  year: 2018
  ident: B18
  article-title: Identifying objective physiological markers and modifiable behaviors for self-reported stress and mental health status using wearable sensors and mobile phones: observational study
  publication-title: J Med Internet Res.
  doi: 10.2196/jmir.9410
– volume: 44
  start-page: zsaa141
  year: 2021
  ident: B41
  article-title: A multitrait, multimethod matrix approach for a consumer-grade wrist-worn watch measuring sleep duration and continuity
  publication-title: Sleep
  doi: 10.1093/sleep/zsaa141
– volume: 19
  start-page: 1347
  year: 2015
  ident: B16
  article-title: Covariation of depressive mood and spontaneous physical activity in major depressive disorder: toward continuous monitoring of depressive mood
  publication-title: IEEE J Biomed Health Inform.
  doi: 10.1109/JBHI.2015.2440764
– volume: 11
  start-page: e0165267
  year: 2016
  ident: B19
  article-title: Plasma metabolites predict severity of depression and suicidal ideation in psychiatric patients–a multicenter pilot analysis
  publication-title: PLoS ONE.
  doi: 10.1371/journal.pone.0165267
– volume: 12
  start-page: 159
  year: 2015
  ident: B22
  article-title: Systematic review of the validity and reliability of consumer-wearable activity trackers
  publication-title: Int J Behav Nutr Phys Act.
  doi: 10.1186/s12966-015-0314-1
– volume: 3
  start-page: 18
  year: 2020
  ident: B40
  article-title: Investigating sources of inaccuracy in wearable optical heart rate sensors
  publication-title: NPJ Dig Med.
  doi: 10.1038/s41746-020-0226-6
– volume: 13
  start-page: 23
  year: 2017
  ident: B7
  article-title: Personal sensing: understanding mental health using ubiquitous sensors and machine learning
  publication-title: Annu Rev Clin Psychol.
  doi: 10.1146/annurev-clinpsy-032816-044949
– volume: 11
  start-page: 53
  year: 2018
  ident: B49
  article-title: Promises and challenges in the use of consumer-grade devices for sleep monitoring
  publication-title: IEEE Rev Biomed Eng.
  doi: 10.1109/RBME.2018.2811735
– volume: 6
  start-page: e10527
  year: 2018
  ident: B53
  article-title: Accuracy of Fitbit devices: systematic review and narrative syntheses of quantitative data
  publication-title: JMIR mHealth uHealth.
  doi: 10.2196/10527
– volume: 461
  start-page: 53
  year: 2009
  ident: B71
  article-title: Early-warning signals for critical transitions
  publication-title: Nature.
  doi: 10.1038/nature08227
– volume: 157
  start-page: 81
  year: 2000
  ident: B59
  article-title: Sleep complaints and depression in an aging cohort: a prospective perspective
  publication-title: Am J Psychiatry.
  doi: 10.1176/ajp.157.1.81
– volume: 28
  start-page: 1
  year: 2021
  ident: B12
  article-title: Detecting depression and predicting its onset using longitudinal symptoms captured by passive sensing: a machine learning approach with robust feature selection
  publication-title: ACM Trans Comput–Hum Interact.
  doi: 10.1145/3422821
– volume: 7
  start-page: e43539
  year: 2012
  ident: B15
  article-title: Enhanced persistency of resting and active periods of locomotor activity in schizophrenia
  publication-title: PLoS ONE.
  doi: 10.1371/journal.pone.0043539
– volume: 294
  start-page: R1980
  year: 2008
  ident: B63
  article-title: Dynamics of sleep stage transitions in healthy humans and patients with chronic fatigue syndrome
  publication-title: Am J Physiol Regul Integr Comp Physiol.
  doi: 10.1152/ajpregu.00925.2007
– volume: 217
  start-page: 299
  year: 2017
  ident: B45
  article-title: Utility of the Fitbit Flex to evaluate sleep in major depressive disorder: a comparison against polysomnography and wrist-worn actigraphy
  publication-title: J Affect Disord.
  doi: 10.1016/j.jad.2017.04.030
– volume: 18
  start-page: 80
  year: 2003
  ident: B29
  article-title: Life between clocks: daily temporal patterns of human chronotypes
  publication-title: J Biol Rhythms.
  doi: 10.1177/0748730402239679
– volume: 10
  start-page: 2993
  year: 2020
  ident: B27
  article-title: Validation of the sleep regularity index in older adults and associations with cardiometabolic risk
  publication-title: Sci Rep
  doi: 10.1038/s41598-018-32402-510.1038/s41598-020-59762-1
– volume: 312
  start-page: R358
  year: 2017
  ident: B44
  article-title: How consumer physical activity monitors could transform human physiology research
  publication-title: Am J Physiol Regul Integr Comp Physiol.
  doi: 10.1152/ajpregu.00349.2016
– volume: 51
  start-page: 1538
  year: 2019
  ident: B42
  article-title: Wearable sleep technology in clinical and research settings
  publication-title: Med Sci Sports Exerc.
  doi: 10.1249/MSS.0000000000001947
– volume: 58
  start-page: 93
  year: 2019
  ident: B69
  article-title: Delayed Sleep on Melatonin (DelSoM) Study Group Sleep regularity is associated with sleep-wake and circadian timing, and mediates daytime function in Delayed Sleep-Wake Phase Disorder
  publication-title: Sleep Med.
  doi: 10.1016/j.sleep.2019.03.009
– volume: 126
  start-page: 109822
  year: 2019
  ident: B39
  article-title: A validation study of a consumer wearable sleep tracker compared to a portable EEG system in naturalistic conditions
  publication-title: J Psychosom Res.
  doi: 10.1016/j.jpsychores.2019.109822
– volume: 21
  start-page: e15966
  year: 2019
  ident: B17
  article-title: Mood prediction of patients with mood disorders by machine learning using passive digital phenotypes based on the circadian rhythm: prospective observational cohort study
  publication-title: J Med Internet Res.
  doi: 10.2196/1102910.2196/15966
– volume: 37
  start-page: 877
  year: 2020
  ident: B32
  article-title: Association of depressive symptoms with habitual sleep duration and sleep timing in junior high school students
  publication-title: Chronobiol Int.
  doi: 10.1080/07420528.2020.1746796
– volume: 7
  start-page: 3216
  year: 2017
  ident: B26
  article-title: Irregular sleep/wake patterns are associated with poorer academic performance and delayed circadian and sleep/wake timing
  publication-title: Sci Rep.
  doi: 10.1038/s41598-017-03171-4
– volume: 8
  start-page: 133982
  year: 2020
  ident: B35
  article-title: Deep neural networks for human activity recognition with wearable sensors: leave-one-subject-out cross-validation for model selection
  publication-title: IEEE Access.
  doi: 10.1109/ACCESS.2020.3010715
– volume: 99
  start-page: 138103
  year: 2007
  ident: B14
  article-title: Universal scaling law in human behavioral organization
  publication-title: Phys Rev Lett.
  doi: 10.1103/PhysRevLett.99.138103
– volume: 4
  start-page: 28
  year: 2021
  ident: B13
  article-title: Day-to-day variability in sleep parameters and depression risk: a prospective cohort study of training physicians
  publication-title: NPJ Digit Med.
  doi: 10.1038/s41746-021-00400-z
– start-page: 785
  volume-title: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
  year: 2016
  ident: B33
  article-title: Xgboost: a scalable tree boosting system
  doi: 10.1145/2939672.2939785
– volume: 4
  start-page: 97
  year: 1976
  ident: B28
  article-title: A self-assessment questionnaire to determine morningness-eveningness in human circadian rhythms
  publication-title: Int J Chronobiol.
  doi: 10.1037/t02254-000
– volume: 14
  start-page: 91
  year: 2018
  ident: B8
  article-title: Machine learning approaches for clinical psychology and psychiatry
  publication-title: Annu Rev Clin Psychol.
  doi: 10.1146/annurev-clinpsy-032816-045037
– volume: 29
  start-page: e12944
  year: 2020
  ident: B48
  article-title: Validity, potential clinical utility and comparison of a consumer activity tracker and a research-grade activity tracker in insomnia disorder II: outside the laboratory
  publication-title: J Sleep Res.
  doi: 10.1111/jsr.12944
– volume: 26
  start-page: 139
  year: 2014
  ident: B24
  article-title: Circadian misalignment and health
  publication-title: Int Rev Psychiatry.
  doi: 10.3109/09540261.2014.911149
– volume: 17
  start-page: 331
  year: 2020
  ident: B68
  article-title: Sleep regularity index in patients with alcohol dependence: daytime napping and mood disorders as correlates of interest
  publication-title: Int J Environ Res Public Health.
  doi: 10.3390/ijerph17010331
– volume: 27
  start-page: 1
  year: 2020
  ident: B11
  article-title: Machine learning in mental health: a systematic review of the HCI literature to support the development of effective and implementable ML systems
  publication-title: ACM Trans Comput–Hum Interact.
  doi: 10.1145/3398069
– volume: 1
  start-page: e00152
  year: 2013
  ident: B65
  article-title: The effects of exercise on dynamic sleep morphology in healthy controls and patients with chronic fatigue syndrome
  publication-title: Physiol Rep.
  doi: 10.1002/phy2.152
– volume: 42
  start-page: zsz180
  year: 2019
  ident: B43
  article-title: Sleep stage prediction with raw acceleration and photoplethysmography heart rate data derived from a consumer wearable device
  publication-title: Sleep
  doi: 10.1093/sleep/zsz180
SSID ssj0002512205
Score 2.3233254
Snippet The prevention and treatment of mental illness is a serious social issue. Prediction and intervention, however, have been difficult because of lack of...
SourceID doaj
pubmedcentral
proquest
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage 861808
SubjectTerms Digital Health
machine learning
medical examination
mental illness
mHealth
physical activity
predictive detection
Title Predictive Modeling of Mental Illness Onset Using Wearable Devices and Medical Examination Data: Machine Learning Approach
URI https://www.ncbi.nlm.nih.gov/pubmed/35493532
https://www.proquest.com/docview/2658649340
https://pubmed.ncbi.nlm.nih.gov/PMC9046696
https://doaj.org/article/d75a568f2c2a4420aa8c9349032258ad
Volume 4
WOSCitedRecordID wos001030200700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2673-253X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002512205
  issn: 2673-253X
  databaseCode: DOA
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2673-253X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002512205
  issn: 2673-253X
  databaseCode: M~E
  dateStart: 20190101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELagQogLKu_wqIzECSnUr_jRW6FbwWFLDyD2Fk38aCutsmg3RaiH_nY8SbraRQguXKIocRTL8_B8mvE3hLyRXngDPJZKc58BiuJlU2lVpgS6idFKDqlvNmFOTuxs5k43Wn1hTdhADzws3H4wFVTaJuEFKCUYgPVOKsdQEy0E9L7MuA0whT4Yd23BqiGNmVGY20_hrMPkgxDvrOYW20lubEQ9X_-fgszfayU3Np_jXXJ_jBrp4TDbB-RWbB-Su9MxL_6IXJ0u8R5dF8XuZnjGnC4SHRh66Kf5HD0a_dyuYkf7KgH6Las4HpuiR7F3FhTaQMe0DZ38BCyRQaHRI-jggE77ostIRz7WM3o4kpE_Jl-PJ18-fCzHrgqlz_bWlbEKIFmTDLBkPB5ialxwEGLkyuT4IbDGRRc0cB4lCOwYxg0DzaKtsjFz-YTstIs2PiM0gyEvkos57LMZVjaQoxEhktQhqOiSKgi7WeLaj5Tj2PliXmfogVKpe6nUKJV6kEpB3q4_-T7wbfxt8HuU23ogUmX3D7IC1aMC1f9SoIK8vpF6nU0L8yXQxsXlqhY5OtMqj2UFeTpowfpXMuNqWUlRELOlH1tz2X7TXpz39N2OKa2dfv4_Jv-C3MP1wPQWVy_JTre8jK_IHf-ju1gt98htM7N7vWXk6_R68gv5ehOy
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Predictive+Modeling+of+Mental+Illness+Onset+Using+Wearable+Devices+and+Medical+Examination+Data%3A+Machine+Learning+Approach&rft.jtitle=Frontiers+in+digital+health&rft.au=Saito%2C+Tomoki&rft.au=Suzuki%2C+Hikaru&rft.au=Kishi%2C+Akifumi&rft.date=2022-04-14&rft.issn=2673-253X&rft.eissn=2673-253X&rft.volume=4&rft.spage=861808&rft_id=info:doi/10.3389%2Ffdgth.2022.861808&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2673-253X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2673-253X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2673-253X&client=summon