Passive Monitoring for Detecting Hypomanic Symptoms in Bipolar Disorder Using Explainable Machine Learning: Longitudinal Observational Study

BACKGROUND: When trying to intervene early to prevent manic episodes, clinicians are hindered by patients underreporting their symptoms as they are becoming hypomanic or manic (i.e., emerging symptoms). Continuous passive monitoring using wearable technology offers a potential solution to address this problem by capturing behavioral signals that do not depend on self-awareness. However, its clinical utility requires validation before implementation. OBJECTIVE: This study aimed to evaluate whether passively collected wearable data can detect hypomanic symptoms using an explainable machine learning framework. METHODS: We applied explainable machine learning to densely sampled multimodal data from a two-year observational study of digital monitoring in 178 patients with a diagnosis of bipolar disorder (BD) (mean follow-up 540 days; range 120-706 days). Data on activity and sleep were collected continuously using wearable technology. Self-reported data was collected daily on their mood, energy, and anxiety; and weekly using the Altman Self-Rating Mania (ASRM) scale. To identify robust digital markers of hypomanic symptoms, we analyzed 252 time- and frequency-domain features from 43 participants who experienced at least one ASRM-defined symptomatic interval. RESULTS: Passively collected data achieved high accuracy, comparable to daily self-reported data in detecting symptomatic intervals (AU-ROC 0.93 vs 0.91). Combined daily passive wearable data features achieved higher sensitivity (92.0% vs 85.4%) and balanced accuracy (0.90 vs 0.89), and stronger rule-out utility (NPV 97.8% vs 96.1%) than self-report data, with daily sleep features alone driving most of this signal (AU-ROC 0.91; sensitivity 91.8%). The high classification performance using wearable data was explained by reductions in spectral entropy and flux across domains, consistent with decreased complexity and variability in mood, activity, and sleep patterns, consistent with a shift toward pathologically stable states. CONCLUSIONS: Passive monitoring using wearable technology can detect hypomanic symptoms with high accuracy, supporting its potential as a clinically meaningful tool for continuous, objective monitoring in patients who underreport hypomanic symptoms. These findings are associative and concurrent in nature; they do not establish predictive validity. Prospective studies are needed to evaluate predictive validity for early detection of ASRM-defined symptomatic intervals.

Authors

Institutions

Publication Details

Journal
JMIR mhealth and uhealth
Published
2026-11-18
DOI
https://doi.org/10.2196/105647
Primary Topic
Bipolar Disorder and Treatment
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Passive Monitoring for Detecting Hypomanic Symptoms in Bipolar Disorder Using Explainable Machine Learning: Longitudinal Observational Study

Martin Alda, Benoit H. Mulsant, Arend Hintze, Ramzi Halabi et al.
3 links
JMIR mhealth and uhealth
Bipolar Disorder and Treatment
article

Passive Monitoring for Detecting Hypomanic Symptoms in Bipolar Disorder Using Explainable Machine Learning: Longitudinal Observational Study

Martin Alda, Benoit H. Mulsant, Arend Hintze, Ramzi Halabi, Abigail Ortiz, Claire O’Donovan, Mirkamal Tolend
article en

Abstract

BACKGROUND: When trying to intervene early to prevent manic episodes, clinicians are hindered by patients underreporting their symptoms as they are becoming hypomanic or manic (i.e., emerging symptoms). Continuous passive monitoring using wearable technology offers a potential solution to address this problem by capturing behavioral signals that do not depend on self-awareness. However, its clinical utility requires validation before implementation. OBJECTIVE: This study aimed to evaluate whether passively collected wearable data can detect hypomanic symptoms using an explainable machine learning framework. METHODS: We applied explainable machine learning to densely sampled multimodal data from a two-year observational study of digital monitoring in 178 patients with a diagnosis of bipolar disorder (BD) (mean follow-up 540 days; range 120-706 days). Data on activity and sleep were collected continuously using wearable technology. Self-reported data was collected daily on their mood, energy, and anxiety; and weekly using the Altman Self-Rating Mania (ASRM) scale. To identify robust digital markers of hypomanic symptoms, we analyzed 252 time- and frequency-domain features from 43 participants who experienced at least one ASRM-defined symptomatic interval. RESULTS: Passively collected data achieved high accuracy, comparable to daily self-reported data in detecting symptomatic intervals (AU-ROC 0.93 vs 0.91). Combined daily passive wearable data features achieved higher sensitivity (92.0% vs 85.4%) and balanced accuracy (0.90 vs 0.89), and stronger rule-out utility (NPV 97.8% vs 96.1%) than self-report data, with daily sleep features alone driving most of this signal (AU-ROC 0.91; sensitivity 91.8%). The high classification performance using wearable data was explained by reductions in spectral entropy and flux across domains, consistent with decreased complexity and variability in mood, activity, and sleep patterns, consistent with a shift toward pathologically stable states. CONCLUSIONS: Passive monitoring using wearable technology can detect hypomanic symptoms with high accuracy, supporting its potential as a clinically meaningful tool for continuous, objective monitoring in patients who underreport hypomanic symptoms. These findings are associative and concurrent in nature; they do not establish predictive validity. Prospective studies are needed to evaluate predictive validity for early detection of ASRM-defined symptomatic intervals.

JMIR mhealth and uhealthVol. 14
Dalarna University (SE), Dalhousie University (CA), Centre for Addiction and Mental Health (CA), University of Toronto (CA), Royal Ottawa Mental Health Centre (CA), National Institute of Mental Health (CZ), The University of Texas Southwestern Medical Center (US)
Good health and well-being
Bipolar Disorder and Treatment
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon