Digital phenotyping for mental health conditions: a systematic review of implementation and application

Introduction Digital phenotyping (DP) has emerged as a promising approach for monitoring mental health conditions using passive and active data from personal digital devices. However, existing research is highly fragmented, with variability in study settings, device choices, data collection procedures, preprocessing pipelines, and analytical strategies. This lack of methodological consistency limits reproducibility, comparability across studies, and the translation of DP into routine clinical practice. Objective The objective of the article is to examine and synthesise the methodological approaches used to implement DP systems for mental health conditions, including setting, device selection, data collection procedures, data storage, preprocessing workflows, feature extraction, and analytical strategies. Methods A systematic search across seven databases (PubMed, Embase, PsycINFO, Scopus, Web of Science, ScienceDirect, and Google Scholar), including studies published till June 2025. We included primary empirical studies using smartphone or wearable-based DP in clinically diagnosed mental health populations. Study quality was assessed using the Mixed Methods Appraisal Tool (MMAT). Findings were synthesised using a narrative approach focused on implementation methodologies. Findings/results Forty-seven studies were included, primarily conducted in high-income countries and focusing on conditions such as schizophrenia, bipolar disorder, and major depressive disorder. Across studies, wide heterogeneity was observed in digital devices used, sensing modalities, preprocessing strategies, feature definitions, and analytical techniques. Conclusions DP demonstrates potential. However, methodological heterogeneity, inconsistent reporting, and concentration of evidence in high-income settings constrain reproducibility and clinical translation. Developing standardised implementation and reporting protocols may enhance the reliability of DP and facilitate its integration into routine mental health care. Systematic Review Registration https://www.crd.york.ac.uk/PROSPERO/view/CRD42023406094 , PROSPERO CRD42023406094.