Detecting momentary reward and affect with real-time passive digital sensor data DOI Creative Commons
Samir Akre, Zachary D. Cohen,

Amelia Welborn

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 23, 2024

Abstract This study explores the capability of passive digital sensor data from smartphones and smartwatches to predict self-reported ecological momentary assessments (EMA) affect, motivation, interest, pleasure in activities an unseen test sample. Using 245 depressed participants with high-to-low anhedonia (195 train, 50 test) generating 23,812 EMA sessions, we evaluated whether behaviors physiological factors could detect subjective states. For 11 15 questions asked, machine learning models exceeded random chance fully-held-out sample, suggesting detectable signals between measures Dependent on type, optimal aggregation periods ranged minutes 3 hours, generally at least two hours being required. Subgroup analyses revealed variations model performance by demographics, depression severity, severity. These findings demonstrate potential for sensing help monitor aspects mental health a large scale.

Language: Английский

Designing Technologies for Value-based Mental Healthcare: Centering Clinicians' Perspectives on Outcomes Data Specification, Collection, and Use DOI
Daniel A. Adler, Yuewen Yang, Thalia Viranda

et al.

Published: April 24, 2025

Health information technologies are transforming how mental healthcare is paid for through value-based care programs, which tie payment to data quantifying outcomes. But, it unclear what outcomes these should store, engage users in collection, and can improve care. Given challenges, we conducted interviews with 30 U.S.-based health clinicians explore the design space of that support specification, use healthcare. Our findings center clinicians' perspectives on aligning programs care; opportunities personal devices collection; considerations using hold stakeholders including clinicians, insurers, social services financially accountable We conclude implications future research designing developing supporting across involved service delivery.

Language: Английский

Citations

0
Integrating digital health technologies for ecological validity in computational psychiatry: challenges and solutions DOI Creative Commons
Andrea Putica,

Miriam Yurtbasi,

Rahul Khanna

et al.

AI & Society, Journal Year: 2025, Volume and Issue: unknown

Published: April 8, 2025

Language: Английский

Citations

0
Beyond Detection: Towards Actionable Sensing Research in Clinical Mental Healthcare DOI Creative Commons
Daniel A. Adler, Yuewen Yang, Thalia Viranda

et al.

Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies, Journal Year: 2024, Volume and Issue: 8(4), P. 1 - 33

Published: Nov. 21, 2024

Researchers in ubiquitous computing have long promised that passive sensing will revolutionize mental health measurement by detecting individuals a population experiencing disorder or specific symptoms. Recent work suggests detection tools do not generalize well when trained and tested more heterogeneous samples. In this work, we contribute narrative review findings from two studies with 41 clinicians to understand these generalization challenges. Our motivate research on actionable sensing, as an alternative research, studying how can augment traditional measures support actions clinical care. Specifically, identify revealing patients' presenting problems for treatment identifying targets behavior change symptom reduction, but data requires additional contextual information be appropriately interpreted used We conclude suggesting at the intersection of healthcare, align technical needs.

Language: Английский

Citations

1
Ubiquitous Computing in Action: Infrastructure to Support Sensing and Mental Health Research in Practice DOI
Daniel A. Adler, Tanzeem Choudhury

Published: Sept. 22, 2024

Language: Английский

Citations

0
Advancing digital sensing in mental health research DOI Creative Commons
Samir Akre, Darsol Seok, Christopher J. Douglas

et al.

npj Digital Medicine, Journal Year: 2024, Volume and Issue: 7(1)

Published: Dec. 18, 2024

Abstract Digital sensing tools, like smartphones and wearables, offer transformative potential for mental health research by enabling scalable, longitudinal data collection. Realizing this promise requires overcoming significant challenges including limited standards, underpowered studies, a disconnect between aims community needs. This report, based on the 2023 Workshop Advancing Sensing Tools Mental Health, articulates strategies to address these ensure rigorous, equitable, impactful research.

Language: Английский

Citations

0
Detecting momentary reward and affect with real-time passive digital sensor data DOI Creative Commons
Samir Akre, Zachary D. Cohen,

Amelia Welborn

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 23, 2024

Abstract This study explores the capability of passive digital sensor data from smartphones and smartwatches to predict self-reported ecological momentary assessments (EMA) affect, motivation, interest, pleasure in activities an unseen test sample. Using 245 depressed participants with high-to-low anhedonia (195 train, 50 test) generating 23,812 EMA sessions, we evaluated whether behaviors physiological factors could detect subjective states. For 11 15 questions asked, machine learning models exceeded random chance fully-held-out sample, suggesting detectable signals between measures Dependent on type, optimal aggregation periods ranged minutes 3 hours, generally at least two hours being required. Subgroup analyses revealed variations model performance by demographics, depression severity, severity. These findings demonstrate potential for sensing help monitor aspects mental health a large scale.

Language: Английский

Citations

0