Search Articles

View query in Help articles search

Search Results (1 to 3 of 3 Results)

Download search results: CSV END BibTex RIS


Understanding Mental Health Clinicians’ Perceptions and Concerns Regarding Using Passive Patient-Generated Health Data for Clinical Decision-Making: Qualitative Semistructured Interview Study

Understanding Mental Health Clinicians’ Perceptions and Concerns Regarding Using Passive Patient-Generated Health Data for Clinical Decision-Making: Qualitative Semistructured Interview Study

Study sessions were audio recorded, transcribed using a professional service, and anonymized. The 2 co–first authors analyzed the anonymized transcripts using a thematic analysis approach [36-38]. Guided by the literature and research objectives, the transcripts were independently open coded. The coded transcripts were then reviewed to reach a joint interpretation and agreement toward a final codebook.

Jodie Nghiem, Daniel A Adler, Deborah Estrin, Cecilia Livesey, Tanzeem Choudhury

JMIR Form Res 2023;7:e47380

Digital Prompts to Increase Engagement With the Headspace App and for Stress Regulation Among Parents: Feasibility Study

Digital Prompts to Increase Engagement With the Headspace App and for Stress Regulation Among Parents: Feasibility Study

A solution-focused approach prioritizes the development of a solution to a practical problem to produce a sustainable solution [40,42]. A critical first step in supporting parental stress regulation (distal outcome) was to identify whether and under what conditions prompting parents to engage in mindfulness is beneficial. Digital prompts (eg, push notifications) are frequently used to promote engagement.

Lisa Militello, Michael Sobolev, Fabian Okeke, Daniel A Adler, Inbal Nahum-Shani

JMIR Form Res 2022;6(3):e30606

Predicting Early Warning Signs of Psychotic Relapse From Passive Sensing Data: An Approach Using Encoder-Decoder Neural Networks

Predicting Early Warning Signs of Psychotic Relapse From Passive Sensing Data: An Approach Using Encoder-Decoder Neural Networks

We considered each participant’s data to be a time series of varying length L, X={x(1),…,x(L)}, where each x(i) is a multivariate data point, x(i)∈Rm. In our case, each x(i) represented a set of hourly features for a single participant. We created subsequences of data of length l starting at each i, i={i,…,L-l+1}. Note that a given data point, x(i), could be potentially included within each of the 1,…,L subsequences. For the FNN AD model, we let l=1, and for the GRU Seq2 Seq model, we let l=24.

Daniel A Adler, Dror Ben-Zeev, Vincent W-S Tseng, John M Kane, Rachel Brian, Andrew T Campbell, Marta Hauser, Emily A Scherer, Tanzeem Choudhury

JMIR Mhealth Uhealth 2020;8(8):e19962