Mood Prediction of Patients With Mood Disorders by Machine Learning Using Passive Digital Phenotypes Based on the Circadian Rhythm: Prospective Observational Cohort Study.
Open accessPublished version of a preprint
Abstract
BACKGROUND: Virtually, all organisms on Earth have their own circadian rhythm, and humans are no exception. Circadian rhythms are associated with various human states, especially mood disorders, and disturbance of the circadian rhythm is known to be very closely related. Attempts have also been made to derive clinical implications associated with mood disorders using the vast amounts of digital log that is acquired by digital technologies develop and using computational analysis techniques. OBJECTIVE: This study was conducted to evaluate the mood state or episode, activity, sleep, light exposure, and heart rate during a period of about 2 years by acquiring various digital log data through wearable devices and smartphone apps as well as conventional clinical assessments. We investigated a mood prediction algorithm developed with machine learning using passive data phenotypes based on circadian rhythms. METHODS: We performed a prospective observational cohort study on 55 patients with mood disorders (major depressive disorder [MDD] and bipolar disorder type 1 [BD I] and 2 [BD II]) for 2 years. A smartphone app for self-recording daily mood scores and detecting light exposure (using the installed sensor) were provided. From daily worn activity trackers, digital log data of activity, sleep, and heart rate were collected. Passive digital phenotypes were processed into 130 features based on circadian rhythms, and a mood prediction algorithm was developed by random forest. RESULTS: The mood state prediction accuracies for the next 3 days in all patients, MDD patients, BD I patients, and BD II patients were 65%, 65%, 64%, and 65% with 0.7, 0.69, 0.67, and 0.67 area under the curve (AUC) values, respectively. The accuracies of all patients for no episode (NE), depressive episode (DE), manic episode (ME), and hypomanic episode (HME) were 85.3%, 87%, 94%, and 91.2% with 0.87, 0.87, 0.958, and 0.912 AUC values, respectively. The prediction accuracy in BD II patients was distinctively balanced as high showing 82.6%, 74.4%, and 87.5% of accuracy (with generally good sensitivity and specificity) with 0.919, 0.868, and 0.949 AUC values for NE, DE, and HME, respectively. CONCLUSIONS: On the basis of the theoretical basis of chronobiology, this study proposed a good model for future research by developing a mood prediction algorithm using machine learning by processing and reclassifying digital log data. In addition to academic value, it is expected that this study will be of practical help to improve the prognosis of patients with mood disorders by making it possible to apply actual clinical application owing to the rapid expansion of digital technology.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
12 of the 17 included studies had sample sizes smaller than 100.
“12 of the 17 included studies had sample sizes smaller than 100 [28–31,33–35,37–39,41,42].”
From Artificial intelligence and machine learning in mobile apps for mental health: A scoping review (2022) · cites this paper as [34]
The most common use of artificial intelligence in the mental health apps was prediction (of mood, stress, and risk) (8/17 studies).
“The most common uses of artificial intelligence in the mental health apps were prediction (of mood, stress, and risk) (8/17 studies) [31–37,41]”
From Artificial intelligence and machine learning in mobile apps for mental health: A scoping review (2022) · cites this paper as [34]
There were a large variety of study types among the 17 studies, including pilot randomised controlled trials, observational studies, model evaluations, and a qualitative study.
“There were a large variety of study types among the 17 studies, including pilot randomised controlled trials (RCTs) [28–30], observational studies [31–35], model evaluations [36,37], and a qualitative study [38].”
From Artificial intelligence and machine learning in mobile apps for mental health: A scoping review (2022) · cites this paper as [34]
3 of the 17 studies focused on predicting mood in people with mood disorders.
“3 studies each focused on predicting mood in people with mood disorders [34,35,37]”
From Artificial intelligence and machine learning in mobile apps for mental health: A scoping review (2022) · cites this paper as [34]
Of the 12 studies that included an intervention period, only 3 (25%) had intervention periods longer than 1 year.
“of the 12 studies that included an intervention period, only 3 (25%) had intervention periods longer than 1 year [33–35].”
From Artificial intelligence and machine learning in mobile apps for mental health: A scoping review (2022) · cites this paper as [34]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · see citing works
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016 · see citing works
Affect Detection: An Interdisciplinary Review of Models, Methods, and Their Applications
Calvo, R. A., & D'Mello, S. (2010) · IEEE Transactions on Affective Computing · doi:10.1109/t-affc.2010.1 · Cited by 1,893 · cited 1× · see citing works
“…communicating with other people [16], entropy of subject’s location changes based on the global positioning system (GPS) [39], behavioral movement detection from accelerometer sensors [17,40], ambient light and noise sounds [17], and the paralinguistic feature of speech from smartphones [40].”
BackgroundJudd, L. L., Akiskal, H. S., Schettler, P. J., Coryell, W., Endicott, J., Maser, J. D., Solomon, D. A., Leon, A. C., & Keller, M. B. (2003) · Archives of General Psychiatry · doi:10.1001/archpsyc.60.3.261 · Cited by 1,243 · see citing works
An Introduction to Machine Learning
Kubát, M. (2015) · Springer eBooks · doi:10.1007/978-3-319-20010-1 · Cited by 1,024 · see citing works
Light as a central modulator of circadian rhythms, sleep and affect
LeGates, T. A., Fernandez, D. C., & Hattar, S. (2014) · Nature Reviews Neuroscience · doi:10.1038/nrn3743 · Cited by 1,001 · see citing works
Two-Year Outcomes for Interpersonal and Social Rhythm Therapy in Individuals With Bipolar I Disorder
Frank, E., Kupfer, D. J., Thase, M. E., Mallinger, A. G., Swartz, H. A., Fagiolini, A. M., Grochocinski, V., Houck, P., Scott, J., Thompson, W., et al. (2005) · Archives of General Psychiatry · doi:10.1001/archpsyc.62.9.996 · Cited by 770 · cited 1× · see citing works
“BD has even more robust results reported than MDD in relation to circadian rhythms, from an association with circadian gene variants [34], through sleep and circadian phenotypes [4,6,7], to the therapeutic approaches focusing on circadian rhythms and sleep [35].”
BackgroundCircadian genes, rhythms and the biology of mood disorders
McClung, C. A. (2007) · Pharmacology & Therapeutics · doi:10.1016/j.pharmthera.2007.02.003 · Cited by 666 · see citing works
Adapting to Artificial Intelligence: Radiologists and Pathologists as Information Specialists
Jha, S., & Topol, E. J. (2016) · JAMA · doi:10.1001/jama.2016.17438 · Cited by 622 · see citing works
MoodScope: building a mood sensor from smartphone usage patterns
LiKamWa, R., Liu, Y., Lane, N. D., & Zhong, L. (2013) · Proceeding of the 11th annual international conference on Mobile systems, applications, and services · doi:10.1145/2462456.2464449 · Cited by 444 · see citing works
Machine Learning and the Profession of Medicine
Darcy, A. M., Louie, A. K., & Roberts, L. W. (2016) · JAMA · doi:10.1001/jama.2015.18421 · Cited by 436 · see citing works
Social and economic burden of mood disorders
Simon, G. E. (2003) · Biological Psychiatry · doi:10.1016/s0006-3223(03)00420-7 · Cited by 430 · see citing works
Jain, S. H., Powers, B. W., Hawkins, J. B., & Brownstein, J. S. (2015) · Nature Biotechnology · doi:10.1038/nbt.3223 · Cited by 425 · see citing works
Beyond self-report: tools to compare estimated and real-world smartphone use
Andrews, S., Ellis, D. A., Shaw, H., & Piwek, L. (2015) · PLOS ONE · doi:10.1371/journal.pone.0139004 · Cited by 408 · see citing works
The social zeitgeber theory, circadian rhythms, and mood disorders: Review and evaluation
Sylvia, L. G., Alloy, L. B., & Abramson, L. Y. (2006) · Clinical Psychology Review · doi:10.1016/j.cpr.2006.07.001 · Cited by 404 · see citing works
Finkelstein, E. A., Haaland, B. A., Bilger, M., Sahasranaman, A., Sloan, R. A., Nang, E. E. K., & Evenson, K. R. (2016) · The Lancet Diabetes & Endocrinology · doi:10.1016/s2213-8587(16)30284-4 · Cited by 402 · see citing works
Casper, R. C. (1985) · Archives of General Psychiatry · doi:10.1001/archpsyc.1985.01790340082012 · Cited by 279 · see citing works
Geoffroy, P. A., Bellivier, F., Scott, J., & Etain, B. (2014) · Journal of Affective Disorders · doi:10.1016/j.jad.2014.07.002 · Cited by 251 · see citing works
Influence of sleep-wake and circadian rhythm disturbances in psychiatric disorders.
Boivin, D. B. (2000) · PubMed Central · Cited by 247 · see citing works
The burden of recurrent depression: causes, consequences, and future prospects.
Greden, J. F. (2001) · PubMed · Cited by 229 · see citing works
Social sensing for epidemiological behavior change
Madan, A., Cebrian, M., Lazer, D., & Pentland, A. (2010) · Proceedings of the 12th ACM international conference on Ubiquitous computing · doi:10.1145/1864349.1864394 · Cited by 219 · see citing works
Mobile phones as medical devices in mental disorder treatment: an overview
Gravenhorst, F., Muaremi, A., Bardram, J. E., Grünerbl, A., Mayora, O., Wurzer, G., Frost, M. M., Osmani, V., Bert Arnrich, A., Lukowicz, P., et al. (2014) · Personal and Ubiquitous Computing · doi:10.1007/s00779-014-0829-5 · Cited by 196 · see citing works
The circadian basis of mood disorders: Recent developments and treatment implications
Monteleone, P., & Maj, M. (2008) · European Neuropsychopharmacology · doi:10.1016/j.euroneuro.2008.06.007 · Cited by 185 · see citing works
Detecting Bipolar Depression From Geographic Location Data
Palmius, N., Tsanas, A., Saunders, K. E. A., Bilderbeck, A. C., Geddes, J. R., Goodwin, G. M., & De Vos, M. (2017) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2016.2611862 · Cited by 180 · see citing works
Moon, J.-H., Cho, C.-H., Son, G. H., Geum, D., Chung, S., Kim, H., Kang, S.-G., Park, Y.-M., Yoon, H.-K., Kim, L., et al. (2016) · EBioMedicine · doi:10.1016/j.ebiom.2016.08.019 · Cited by 163 · see citing works
Self-citationHeun, R., & Maier, W. (1993) · Acta Psychiatrica Scandinavica · doi:10.1111/j.1600-0447.1993.tb03372.x · Cited by 145 · see citing works
Berk, M., & Dodd, S. (2005) · Bipolar Disorders · doi:10.1111/j.1399-5618.2004.00152.x · Cited by 134 · see citing works
Kim, H., Lee, S., Lee, S., Hong, S., Kang, H., & Kim, N. (2019) · JMIR mHealth and uHealth · doi:10.2196/14149 · Cited by 131 · see citing works
Sprouse, J., Braselton, J., & Reynolds, L. (2006) · Biological Psychiatry · doi:10.1016/j.biopsych.2006.03.003 · Cited by 122 · see citing works
Diurnal mood variation in depression: A signal of disturbed circadian function?
Murray, G. (2007) · Journal of Affective Disorders · doi:10.1016/j.jad.2006.12.001 · Cited by 118 · see citing works
The Relationship Between Bipolar Disorder and Biological Rhythms
Gonzalez, R. (2014) · The Journal of Clinical Psychiatry · doi:10.4088/jcp.13r08507 · Cited by 118 · see citing works
Lee, H. A., Lee, H., Moon, J.-H., Lee, T., Kim, M.-G., In, H., Cho, C., & Kim, L. (2017) · Psychiatry Investigation · doi:10.4306/pi.2017.14.2.179 · Cited by 102 · see citing works
Self-citationTazawa, Y., Liang, K.-C., Yoshimura, M., Kitazawa, M., Kaise, Y., Takamiya, A., Kishi, A., Horigome, T., Mitsukura, Y., Mimura, M., et al. (2020) · Heliyon · doi:10.1016/j.heliyon.2020.e03274 · Cited by 101 · see citing works
Daily Mood Assessment Based on Mobile Phone Sensing
Ma, Y., Xu, B., Bai, Y. L., Sun, G., & Zhu, R. (2012) · Wearable and Implantable Body Sensor Networks · doi:10.1109/bsn.2012.3 · Cited by 88 · see citing works
Differences in white matter abnormalities between bipolar I and II disorders
Liu, J.-X., Chen, Y., Hsieh, J., Su, T., Yeh, T., & Chen, L. (2010) · Journal of Affective Disorders · doi:10.1016/j.jad.2010.05.026 · Cited by 80 · see citing works
Carr, O., Saunders, K. E. A., Tsanas, A., Bilderbeck, A. C., Palmius, N., Geddes, J. R., Foster, R., Goodwin, G. M., & De Vos, M. (2018) · Scientific Reports · doi:10.1038/s41598-018-19888-9 · Cited by 57 · see citing works
Friedman, E. S., Gyulai, L., Bhargava, M., et al. (2006) · Acta Psychiatrica Scandinavica · doi:10.1111/j.1600-0447.2005.00701.x · Cited by 55 · see citing works
Chronobiology of mood disorders
Malhi, G. S., & Kuiper, S. (2013) · Acta Psychiatrica Scandinavica · doi:10.1111/acps.12173 · Cited by 53 · see citing works
Goetze, U., & Tölle, R. (2008) · Neuropsychobiology · doi:10.1159/000118414 · Cited by 50 · see citing works
Cho, C., Moon, J.-H., Yoon, H., Kang, S., Geum, D., Son, G. H., Lim, J.-M., Kim, L., Lee, E., & Lee, H. (2016) · Scientific Reports · doi:10.1038/srep31846 · Cited by 45 · see citing works
Self-citationIntegrating sleep, neuroimaging, and computational approaches for precision psychiatry
Goldstein‐Piekarski, A. N., Holt-Gosselin, B., O’Hora, K., & Williams, L. M. (2019) · Neuropsychopharmacology · doi:10.1038/s41386-019-0483-8 · Cited by 38 · see citing works
Could Digital Therapeutics be a Game Changer in Psychiatry?
Cho, C., & Lee, H. (2019) · Psychiatry Investigation · doi:10.30773/pi.2019.01.20 · Cited by 34 · see citing works
Self-citationKrauss, S. S., Depue, R. A., Arbisi, P. A., & Spoont, M. R. (1992) · Psychiatry Research · doi:10.1016/0165-1781(92)90129-q · Cited by 28 · see citing works
Design and Methods of the Mood Disorder Cohort Research Consortium (MDCRC) Study
Cho, C., Ahn, Y. M., Kim, S. J., Ha, T. H., Jeon, H. J., Cha, B., Moon, E., Park, D. Y., Baek, J. H., Kang, H., et al. (2017) · Psychiatry Investigation · doi:10.4306/pi.2017.14.1.100 · Cited by 22 · see citing works
Self-citationWhy Do Mania and Suicide Occur Most Often in the Spring?
Cho, C., & Lee, H. (2018) · Psychiatry Investigation · doi:10.30773/pi.2017.12.20 · Cited by 19 · see citing works
Self-citationUsing Chronobiological Phenotypes to Address Heterogeneity in Bipolar Disorder
Gonzalez, R., Gonzalez, S., & McCarthy, M. J. (2019) · Complex Psychiatry · doi:10.1159/000506636 · Cited by 17 · see citing works
Analysis of the Causes and the Consequences of Consecutive RMB Appreciation
Luo, S., Zhang, Y., Hu, M., et al. (2014) · Journal of Financial Risk Management · doi:10.4236/jfrm.2014.31001 · Cited by 2 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- [11]American Psychiatric Association Diagnostic and Statistical Manual of Mental Disorders, 5th Edition: DSM-5 2013 Washington, DC American Psychiatric Pub
Cited by
Sorted by citations
Abd-Alrazaq, A., AlSaad, R., Shuweihdi, F., Ahmed, A., Aziz, S., & Sheikh, J. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00828-5 · Cited by 138 · see citing works
Kim, H., Lee, S., Lee, S., Hong, S., Kang, H., & Kim, N. (2019) · JMIR mHealth and uHealth · doi:10.2196/14149 · Cited by 131 · see citing works
Tazawa, Y., Liang, K.-C., Yoshimura, M., Kitazawa, M., Kaise, Y., Takamiya, A., Kishi, A., Horigome, T., Mitsukura, Y., Mimura, M., et al. (2020) · Heliyon · doi:10.1016/j.heliyon.2020.e03274 · Cited by 101 · see citing works
Haines-Delmont, A., Chahal, G., Bruen, A. J., Wall, A., Khan, C. T., Sadashiv, R., & Fearnley, D. (2020) · JMIR mhealth and uhealth · doi:10.2196/15901 · Cited by 87 · see citing works
Cho, C.-H., Lee, T., Lee, J.-B., Seo, J. Y., Jee, H.-J., Son, S., An, H., Kim, L., & Lee, H.-J. (2020) · doi:10.2196/preprints.21283 · Cited by 69 · see citing works
Self-citationArtificial intelligence and machine learning in mobile apps for mental health: A scoping review
Milne-Ives, M., Selby, E., Inkster, B., Lam, C., & Meinert, E. (2022) · PLOS Digital Health · doi:10.1371/journal.pdig.0000079 · Cited by 68 · see citing works
Kornfield, R., Zhang, R., Nicholas, J., Schueller, S. M., Cambo, S. A., Mohr, D. C., & Reddy, M. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376309 · Cited by 64 · see citing works
- Authors
- Cho, C.-H., Lee, T., Kim, M.-G., In, H. P., Kim, L., & Lee, H.-J.
- Affiliations
- Korea University (KR)
- Corresponding author
- Lee, Heon-Jeong
- Venue
- Journal of Medical Internet Research
- Publisher
- JMIR Publications Inc.
- Published
- 2019-04-17
- Volume
- 21
- Issue
- 4
- Pages
- e11029
- ISSN
- 1438-8871 (ISSN-L)
- PMC
- PMC6492069
- OpenAlex
- W2929646074
- Cited by
- 183
- References
- 47
- Citations by year
- 2026: 24 · 2025: 26 · 2024: 28 · 2023: 18 · 2022: 25 · 2021: 22 · 2020: 32 · 2019: 8
- FWCI
- 25.54
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- Journal of Medical Internet Research (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- National Research Foundation (2016M3C7A1904345)
- National Research Foundation of Korea (2016M3C7A1904345, 2017 M3A9F1031220)
- Topics
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Mental Health Research Topics
- Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
- Health Sciences › Medicine › Psychiatry and Mental health › Bipolar Disorder and Treatment
- Keywords
- mood disorders, mood prediction, circadian rhythm, wearable devices, mobile application, major depressive disorder, bipolar disorder, light exposure, sleep, physical activity, heart rate, random forest, digital health monitoring, wearable activity trackers, hypomanic episodes, manic episodes, depressive episodes
- MeSH terms
- Machine Learning, Circadian Rhythm, Female, Humans, Male, Phenotype, Prospective Studies, Cohort Studies, Mood Disorders
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
