{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T10:37:43Z","timestamp":1792147063828,"version":"4.4.0"},"reference-count":47,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Bipolar disorder (BD) is a highly recurrent disorder. Early detection, early intervention, and prevention of recurrent bipolar mood symptoms are key to a better prognosis.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to build prediction models for BD with machine learning algorithms.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n This study recruited 24 participants with BD. The Beck Depression Inventory and Young Mania Rating Scale were used to evaluate depressive and manic episodes, respectively. Using digital biomarkers collected from wearable devices as input, 6 machine learning algorithms (logistic regression, decision tree, k-nearest neighbors, random forest, adaptive boosting, and Extreme Gradient Boosting) were used to build predictive models.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n The prediction model for depressive symptoms achieved 83% accuracy, an area under the receiver operating characteristic curve (AUROC) of 0.89, and an\n F<\/jats:italic>\n 1<\/jats:sub>\n -score of 0.65 on testing data. The prediction model for manic symptoms achieved 91% accuracy, an AUROC of 0.88, and an\n F<\/jats:italic>\n 1<\/jats:sub>\n -score of 0.25 on testing data. With the interpretable model Shapley Additive Explanations, we found that relatively high resting heart rate, low activity, and lack of sleep may predict depressive symptoms.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This study demonstrated that digital biomarkers could be used to predict depressive and manic symptoms. This prediction model may be beneficial for the early detection of mood symptoms, facilitating timely treatment and helping to prevent BD recurrence.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/66277","type":"journal-article","created":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T10:00:09Z","timestamp":1739872809000},"page":"e66277-e66277","source":"Crossref","is-referenced-by-count":13,"title":["Using Wearable Device and Machine Learning to Predict Mood Symptoms in Bipolar Disorder: Development and Usability Study"],"prefix":"10.2196","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5612-8607","authenticated-orcid":false,"given":"Chia-Tung","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3585-7843","authenticated-orcid":false,"given":"Ming H","family":"Hsieh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7759-6648","authenticated-orcid":false,"given":"I-Ming","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4782-099X","authenticated-orcid":false,"given":"Lian-Yin","family":"Jhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7838-8963","authenticated-orcid":false,"given":"Ding-Shan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4359-1683","authenticated-orcid":false,"given":"Ssu-Ming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1066-9981","authenticated-orcid":false,"given":"Chia-Ting","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3477-3015","authenticated-orcid":false,"given":"Yi-Ling","family":"Chien","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"issue":"3","key":"R1","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1016\/s0006-3223(03)00420-7","article-title":"Social and economic burden of mood disorders","volume":"54","author":"Simon","journal-title":"Biol Psychiatry"},{"issue":"3 Suppl","key":"R2","first-page":"S80","volume":"11","author":"Sajatovic","journal-title":"Am J Manag Care"},{"issue":"10","key":"R3","doi-asserted-by":"publisher","first-page":"1501","DOI":"10.1016\/j.euroneuro.2015.07.013","article-title":"Recurrence rates in bipolar disorder: systematic comparison of long-term prospective, naturalistic studies versus randomized controlled trials","volume":"25","author":"V\u00e1zquez","journal-title":"Eur Neuropsychopharmacol"},{"issue":"5","key":"R4","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1176\/appi.ajp.2017.17090972","article-title":"Early intervention in bipolar disorder","volume":"175","author":"Vieta","journal-title":"Am J Psychiatry"},{"issue":"4","key":"R5","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1002\/mpr.1502","article-title":"Behavioral activities collected through smartphones and the association with illness activity in bipolar disorder","volume":"25","author":"Faurholt-Jepsen","journal-title":"Int J Methods Psychiatr Res"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1111\/nyas.13048","article-title":"Innovative approaches to bipolar disorder and its treatment","volume":"1366","author":"Harrison","journal-title":"Ann N Y Acad Sci"},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.03.442","article-title":"Predicting anxiety, depression and stress in modern life using machine learning algorithms","volume":"167","author":"Priya","journal-title":"Procedia Comput Sci"},{"issue":"6","key":"R8","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1049\/htl.2016.0096","article-title":"Predicting anxiety and depression in elderly patients using machine learning technology","volume":"4","author":"Sau","journal-title":"Healthcare Tech Letters"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2022.895860","article-title":"Digital phenotype of mood disorders: a conceptual and critical review","volume":"13","author":"Maatoug","journal-title":"Front Psychiatry"},{"issue":"8","key":"R10","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0231995","article-title":"Applying machine learning in motor activity time series of depressed bipolar and unipolar patients compared to healthy controls","volume":"15","author":"Jakobsen","journal-title":"PLoS One"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2015.09.076","article-title":"Sleep, residual mood symptoms, and time to relapse in recovered patients with bipolar disorder","volume":"190","author":"Cretu","journal-title":"J Affect Disord"},{"issue":"1","key":"R12","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01333-z","article-title":"Accurately predicting mood episodes in mood disorder patients using wearable sleep and circadian rhythm features","volume":"7","author":"Lim","journal-title":"NPJ Digit Med"},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2017.02.003","article-title":"The hierarchical basis of neurovisceral integration","volume":"75","author":"Smith","journal-title":"Neurosci Biobehav Rev"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.1016\/j.biopsycho.2024.108786","article-title":"Heart rate and heart rate variability in obsessive-compulsive disorder: evidence from patients and unaffected first-degree relatives","volume":"189","author":"J\u00fcres","journal-title":"Biol Psychol"},{"issue":"3","key":"R15","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/s0301-0511(97)00027-6","article-title":"Anxiety and autonomic flexibility: a cardiovascular approach","volume":"47","author":"Friedman","journal-title":"Biol Psychol"},{"issue":"2","key":"R16","doi-asserted-by":"publisher","first-page":"H728","DOI":"10.1152\/ajpheart.00825.2003","article-title":"Respiratory sinus arrhythmia, cardiac vagal control, and daily activity","volume":"287","author":"Grossman","journal-title":"Am J Physiol Heart Circ Physiol"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpsychires.2018.01.008","article-title":"Heart rate variability in patients with bipolar disorder: from mania to euthymia","volume":"99","author":"Wazen","journal-title":"J Psychiatr Res"},{"issue":"1-2","key":"R18","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/s0165-1781(02)00225-1","article-title":"Relationship between major depression and heart rate variability. Clinical consequences and implications for antidepressive treatment","volume":"113","author":"Agelink","journal-title":"Psychiatry Res"},{"issue":"11","key":"R19","doi-asserted-by":"publisher","first-page":"1067","DOI":"10.1016\/j.biopsych.2009.12.012","article-title":"Impact of depression and antidepressant treatment on heart rate variability: a review and meta-analysis","volume":"67","author":"Kemp","journal-title":"Biol Psychiatry"},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpr.2016.04.013","article-title":"Depression and resting state heart rate variability in children and adolescents - a systematic review and meta-analysis","volume":"46","author":"Koenig","journal-title":"Clin Psychol Rev"},{"issue":"4","key":"R21","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1109\/JBHI.2016.2554546","article-title":"Predicting mood changes in bipolar disorder through heartbeat nonlinear dynamics","volume":"20","author":"Valenza","journal-title":"IEEE J Biomed Health Inform"},{"key":"R22","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2019.103381","article-title":"Detection of major depressive disorder from linear and nonlinear heart rate variability features during mental task protocol","volume":"112","author":"Byun","journal-title":"Comput Biol Med"},{"issue":"10","key":"R23","doi-asserted-by":"publisher","DOI":"10.2196\/24872","article-title":"Digital biomarkers for depression screening with wearable devices: cross-sectional study with machine learning modeling","volume":"9","author":"Rykov","journal-title":"JMIR Mhealth Uhealth"},{"issue":"4","key":"R24","doi-asserted-by":"publisher","DOI":"10.2196\/11029","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","volume":"21","author":"Cho","journal-title":"J Med Internet Res"},{"key":"R25","doi-asserted-by":"crossref","unstructured":"Diagnostic and Statistical Manual of Mental Disorders. 5th ed. American Psychiatric Association; 2013.","DOI":"10.1176\/appi.books.9780890425596"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.1001\/archpsyc.1961.01710120031004","article-title":"An inventory for measuring depression","volume":"4","author":"BECK","journal-title":"Arch Gen Psychiatry"},{"issue":"3","key":"R27","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1207\/s15327752jpa6703_13","article-title":"Comparison of beck depression inventories -IA and -II in psychiatric outpatients","volume":"67","author":"Beck","journal-title":"J Pers Assess"},{"issue":"5","key":"R28","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1016\/0010-440x(88)90063-6","article-title":"Applicability of the Chinese Beck Depression Inventory","volume":"29","author":"Zheng","journal-title":"Compr Psychiatry"},{"key":"R29","doi-asserted-by":"publisher","DOI":"10.1192\/bjp.133.5.429","article-title":"A rating scale for mania: reliability, validity and sensitivity","volume":"133","author":"Young","journal-title":"Br J Psychiatry"},{"issue":"2","key":"R30","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1123\/jmpb.2019-0035","article-title":"Review of validity and reliability of garmin activity trackers","volume":"3","author":"Evenson","journal-title":"J Meas Phys Behav"},{"key":"R31","doi-asserted-by":"publisher","DOI":"10.2196\/52192","article-title":"Accuracy of Fitbit Charge 4, Garmin Vivosmart 4, and WHOOP versus polysomnography: systematic review","volume":"12","author":"Schyvens","journal-title":"JMIR Mhealth Uhealth"},{"issue":"1","key":"R32","doi-asserted-by":"publisher","DOI":"10.1007\/s00423-024-03442-5","article-title":"Feasibility and usefulness of postoperative mobilization goals in the enhanced recovery after surgery (ERAS) clinical pathway for elective colorectal surgery","volume":"409","author":"Wiesenberger","journal-title":"Langenbecks Arch Surg"},{"issue":"2","key":"R33","doi-asserted-by":"publisher","DOI":"10.2196\/33063","article-title":"Panic attack prediction using wearable devices and machine learning: development and cohort study","volume":"10","author":"Tsai","journal-title":"JMIR Med Inform"},{"key":"R34","doi-asserted-by":"publisher","DOI":"10.1016\/j.sleep.2023.12.013","article-title":"Sleep, physical activity and panic attacks: a two-year prospective cohort study using smartwatches, deep learning and an explainable artificial intelligence model","volume":"114","author":"Tsai","journal-title":"Sleep Med"},{"key":"R35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2946081","article-title":"Threat analysis for wearable health devices and environment monitoring internet of things integration system","volume":"7","author":"Tseng","journal-title":"IEEE Access"},{"key":"R36","doi-asserted-by":"publisher","DOI":"10.1109\/JTEHM.2022.3207825","article-title":"A precision health service for chronic diseases: development and cohort study using wearable device, machine learning, and deep learning","volume":"10","author":"Wu","journal-title":"IEEE J Transl Eng Health Med"},{"issue":"5","key":"R37","doi-asserted-by":"publisher","DOI":"10.2196\/22591","article-title":"Acute exacerbation of a chronic obstructive pulmonary disease prediction system using wearable device data, machine learning, and deep learning: development and cohort study","volume":"9","author":"Wu","journal-title":"JMIR Mhealth Uhealth"},{"issue":"5","key":"R38","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1016\/j.compbiomed.2010.03.005","article-title":"A learning method for the class imbalance problem with medical data sets","volume":"40","author":"Li","journal-title":"Comput Biol Med"},{"key":"R39","unstructured":"Raschka S . Model evaluation, model selection, and algorithm selection in machine learning. arXiv. Preprint posted online on Nov 13, 2018. [doi: 10.48550\/arXiv.1811.12808]"},{"key":"R40","unstructured":"Lundberg SM Lee SI . A unified approach to interpreting model predictions. Presented at: Proceedings of the 31st International Conference on Neural Information Processing Systems; Dec 4-9, 2017; Long Beach, California, USA."},{"issue":"1","key":"R41","doi-asserted-by":"publisher","DOI":"10.1186\/s12888-019-2152-1","article-title":"Using heart rate profiles during sleep as a biomarker of depression","volume":"19","author":"Saad","journal-title":"BMC Psychiatry"},{"key":"R42","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpsychires.2017.03.026","article-title":"Heart rate variability and cordance in rapid eye movement sleep as biomarkers of depression and treatment response","volume":"92","author":"Pawlowski","journal-title":"J Psychiatr Res"},{"issue":"9","key":"R43","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1002\/da.22386","article-title":"Sleep duration and depression among adults: a meta-analysis of prospective studies","volume":"32","author":"Zhai","journal-title":"Depress Anxiety"},{"issue":"9","key":"R44","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0238811","article-title":"Association between sleep duration and quality and depressive symptoms among university students: a cross-sectional study","volume":"15","author":"Li","journal-title":"PLoS One"},{"key":"R45","doi-asserted-by":"publisher","DOI":"10.1080\/13854046.2024.2432058","article-title":"Symptom validity indices for the Beck Depression Inventory-II: development and cross-validation in research and clinical samples","author":"Shura","journal-title":"Clin Neuropsychol"},{"issue":"2","key":"R46","doi-asserted-by":"publisher","first-page":"296","DOI":"10.9758\/cpn.2023.21.2.296","article-title":"Discrepancy between clinician-rated and self-reported depression severity is associated with adverse childhood experience, autistic-like traits, and coping styles in mood disorders","volume":"21","author":"Yamada","journal-title":"Clin Psychopharmacol Neurosci"},{"issue":"1","key":"R47","doi-asserted-by":"publisher","DOI":"10.2196\/13770","article-title":"Mobile app-based self-report questionnaires for the assessment and monitoring of bipolar disorder: systematic review","volume":"5","author":"Chan","journal-title":"JMIR Form Res"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e66277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:28:56Z","timestamp":1785536936000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e66277"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"references-count":47,"URL":"https:\/\/doi.org\/10.2196\/66277","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,16]]},"article-number":"v13i3e66277"}}