Big Data Approaches to Mood Disorders: Applications of Digital Phenotyping, Personal Sensing, and Multimodal Data Integration
Journal of Education, Humanities and Social Sciences · 07.03.2026 · 63 · 202-209
DOI: 10.54097/2v3wk313 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Education, Humanities and Social Sciences, online erschienen am 07.03.2026. Verfasst von Chenhao Bao. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
This review discusses how big data approaches, digital phenotyping, personal sensing, and multimodal data integration, are revolutionizing research and clinical care in mood disorders including depression and bipolar disorder. These approaches enable the continuous, ecologically valid, and personalized monitoring of behavioural and physiological phenotypes that go well beyond episodic assessments. Digital phenotyping involves the use of smartphone and wearable sensors to monitor individuals passively and in real-time, collecting data on activity, sleep, mobility, and communication. Personal sensing involves the integration of multiple streams of data to detect deviations from the person's own baseline. Multimodal frameworks integrate sensor-based, clinical, and self-report data through machine learning approaches to improve prediction accuracy and to aid in distinguishing valid diagnoses. Empirical work has shown the feasibility and clinical utility of these approaches, including the use of smartphone and wearable data to predict depressive risk and to identify early signs of bipolar relapse, as well as improving diagnostic accuracy through integration. However, the present study demonstrates that, algorithmic transparency, and real-world clinical validation. Importantly, the promise of big data in mental health care will only be realized through rigorous attention to explainable AI, large-scale replication, and ethical governance.
Zitieren
APA
Bao, C. (2026). Big Data Approaches to Mood Disorders: Applications of Digital Phenotyping, Personal Sensing, and Multimodal Data Integration. Journal of Education, Humanities and Social Sciences, 63, 202-209. https://doi.org/10.54097/2v3wk313
Vancouver
Bao C. Big Data Approaches to Mood Disorders: Applications of Digital Phenotyping, Personal Sensing, and Multimodal Data Integration. Journal of Education, Humanities and Social Sciences. 2026;63:202-209. doi:10.54097/2v3wk313
BibTeX
@article{Bao2026,
author = {Bao, Chenhao},
title = {Big Data Approaches to Mood Disorders: Applications of Digital Phenotyping, Personal Sensing, and Multimodal Data Integration},
journal = {Journal of Education, Humanities and Social Sciences},
year = {2026},
volume = {63},
pages = {202--209},
doi = {10.54097/2v3wk313}
}
EUVIMED