Authors
Sohee Kim, Jinyeong Kim, Wai Tong Chien, Tzu Tsun Luk, Yu Zhang, Zhen Yang Abel Tan, Eunju Park, Heejung Kim
Published in
JMIR mHealth and uHealth. Volume 14. Pages e98616. Aug 13, 2026. Epub Aug 13, 2026.
Abstract
Suicide is a leading cause of preventable mortality worldwide, with more than 700,000 deaths annually. Although suicidal ideation fluctuates rapidly, conventional risk assessments rely on retrospective self-report collected infrequently, and the detection of short-term suicide risk remains limited. Passive digital sensing using smartphones and wearable devices enables continuous monitoring of behavioral and physiological signals associated with suicide-related outcomes. However, current evidence remains fragmented, without a clear framework for translation into clinically interpretable risk indicators.
This scoping review synthesized and mapped passive digital markers associated with suicide-related outcomes via the layered hierarchical sensemaking framework (LHSF), which structures information from raw sensor data to high-level behavioral markers. We aimed to illustrate a clinically interpretable mapping of digital markers for suicide-specific digital phenotyping.
Following Arksey and O'Malley and the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines, this scoping review was conducted using the population-concept-context framework (population: not restricted; concept: passively collected digital data from smartphones or wearable devices; and context: suicide-related outcomes). PubMed, CINAHL, PsycINFO, and IEEE Xplore were searched for studies published between 2015 and 2025. Studies were included if they (1) collected passive digital data from smartphones or wearable devices, and (2) measured suicide-related outcomes. Narrative mapping was conducted using LHSF to distinguish between low-level features (ie, measurable properties extracted from sensors) and high-level behavioral markers (ie, clinically meaningful constructs interpreted from low-level features).
Of 626 studies identified, 14 (2.2%) met inclusion criteria. Six (42.9%) used predictive modeling, and 8 (57.1%) conducted correlational analyses. Among predictive studies (area under the curve [AUC]=0.56-0.89), a lower heart rate variability predicted an elevated suicide risk in 1 study (AUC=0.89). Of correlational studies, 7 (87.5%) of 8 reported at least one significant association between passive sensor data and suicide-related outcomes. Mapped to the LHSF, low-level features spanned 7 domains, linked to high-level markers, such as autonomic dysregulation, sleep disturbance, social withdrawal, smartphone use patterns, and suicide-related expression. Physiological indicators of autonomic regulation were associated with suicide-related outcomes in all 4 studies examining them and achieved the highest predictive performance (AUC=0.89). Smartphone use metrics were significantly associated in both studies, whereas linguistic (2/3 studies, 66.7%) and location-based features (2/2 studies, 100%) were associated with at least one outcome, with nonsignificant findings for some indicators or studies. Sleep parameters and movement intensity showed few significant associations.
Physiological indicators were associated with suicide-related outcomes across all relevant studies and showed the highest predictive performance (AUC=0.89), followed by smartphone-derived behavioral features. Linguistic and location-based features showed mixed associations, whereas sleep- and activity-related indicators showed few significant associations. Future research should prioritize multimodal data integration, algorithmic refinement, and external validation to strengthen clinical utility in digital suicide phenotyping based on the LHSF.
PMID:
42596517
Bibliographic data and abstract were imported from PubMed on 14 Aug 2026.
Read full publication at:
Please sign in
to see all details.
Advertisement
Stats
- Recommendations n/a n/a positive of 0 vote(s)
- Views 2
- Comments 0