Benchmarking Mental Health Status Using Passive Sensor Data: Protocol for a Prospective Observational Study DOI Creative Commons
Robyn E. Kilshaw, Abigail Boggins, Olivia Everett

et al.

JMIR Research Protocols, Journal Year: 2024, Volume and Issue: 13, P. e53857 - e53857

Published: Feb. 22, 2024

Background Computational psychiatry has the potential to advance diagnosis, mechanistic understanding, and treatment of mental health conditions. Promising results from clinical samples have led calls extend these methods risk assessment in general public; however, data typically used with are neither available nor scalable for research population. Digital phenotyping addresses this by capitalizing on multimodal widely created sensors embedded personal digital devices (eg, smartphones) is a promising approach extending computational improve Objective Building recommendations existing work, we aim create first set that tailored studying population; includes multimodal, sensor-based behavioral features; designed be shared across academia, industry, government using gold standard privacy, confidentiality, integrity. Methods We stratified, random sampling design 2 crossed factors (difficulties emotion regulation perceived life stress) recruit sample 400 community-dwelling adults balanced high- low-risk episodic Participants complete self-report questionnaires assessing current lifetime psychiatric medical diagnoses treatment, psychosocial functioning. then 7-day situ collection phase providing daily audio recordings, passive sensor collected smartphones, self-reports mood significant events, verbal description events during nightly phone call. same baseline 6 12 months after phase. Self-report will scored methods. Raw processed suite summary features time spent at home). Results Data began June 2022 expected conclude July 2024. To date, 310 participants consented study; 149 completed questionnaire intensive phase; 61 31 6- 12-month follow-up questionnaires, respectively. Once completed, proposed made academic researchers, stepped maximize privacy. Conclusions This as complementary research, goal advancing within aims support field’s move away siloed laboratories collecting proprietary toward interdisciplinary collaborations incorporate clinical, technical, quantitative expertise all stages process. International Registered Report Identifier (IRRID) DERR1-10.2196/53857

Language: Английский

Digital phenotyping for mental health based on data analytics: A systematic literature review DOI
Wesllei Felipe Heckler, Luan Paris Feijó, Juliano Varella de Carvalho

et al.

Artificial Intelligence in Medicine, Journal Year: 2025, Volume and Issue: 163, P. 103094 - 103094

Published: March 1, 2025

Language: Английский

Citations

0
Benchmarking Mental Health Status Using Passive Sensor Data: Protocol for a Prospective Observational Study DOI Creative Commons
Robyn E. Kilshaw, Abigail Boggins, Olivia Everett

et al.

JMIR Research Protocols, Journal Year: 2024, Volume and Issue: 13, P. e53857 - e53857

Published: Feb. 22, 2024

Background Computational psychiatry has the potential to advance diagnosis, mechanistic understanding, and treatment of mental health conditions. Promising results from clinical samples have led calls extend these methods risk assessment in general public; however, data typically used with are neither available nor scalable for research population. Digital phenotyping addresses this by capitalizing on multimodal widely created sensors embedded personal digital devices (eg, smartphones) is a promising approach extending computational improve Objective Building recommendations existing work, we aim create first set that tailored studying population; includes multimodal, sensor-based behavioral features; designed be shared across academia, industry, government using gold standard privacy, confidentiality, integrity. Methods We stratified, random sampling design 2 crossed factors (difficulties emotion regulation perceived life stress) recruit sample 400 community-dwelling adults balanced high- low-risk episodic Participants complete self-report questionnaires assessing current lifetime psychiatric medical diagnoses treatment, psychosocial functioning. then 7-day situ collection phase providing daily audio recordings, passive sensor collected smartphones, self-reports mood significant events, verbal description events during nightly phone call. same baseline 6 12 months after phase. Self-report will scored methods. Raw processed suite summary features time spent at home). Results Data began June 2022 expected conclude July 2024. To date, 310 participants consented study; 149 completed questionnaire intensive phase; 61 31 6- 12-month follow-up questionnaires, respectively. Once completed, proposed made academic researchers, stepped maximize privacy. Conclusions This as complementary research, goal advancing within aims support field’s move away siloed laboratories collecting proprietary toward interdisciplinary collaborations incorporate clinical, technical, quantitative expertise all stages process. International Registered Report Identifier (IRRID) DERR1-10.2196/53857

Language: Английский

Citations

2