Rosalind Picard

Background: Decentralized (ie, fully remote) clinical trials (DCTs) offer a scalable and ecologically valid approach to evaluating digital mental health interventions (DMHIs). Yet, incorporating objective measures of well-being within DCTs poses novel methodological and feasibility challenges that can limit the rigor and precision of data collection in the field. Objective: We recently conducted the Behavior, Biology, and Well-being (BeWell) Study, a large-scale, 3-arm randomized DCT evaluating the Healthy Minds Program app (Humin)—a self-guided DMHI that includes didactic well-being information and meditation components. The current paper’s objective is to describe the methodological approach to collecting and processing a multimodal battery of psychological (questionnaires and structured clinical interview), biological (blood and stool assays), and behavioral (stimulus-elicited affect [SEA] task, video log, and Mnemonic Similarity Task [MST]) measures, longitudinally across baseline, the 4-week intervention period, and 17-week follow-up. Secondarily, we evaluate its feasibility. Methods: The BeWell Study methodology is described. Descriptive statistics characterized recruitment and retention, as well as data completion and data quality. Binary logistic regressions evaluated whether recruitment sources, demographics, and depression severity predicted measure completion and data quality. Results: From June 1, 2022, through July 15, 2024, 52,052 individuals started the screening questionnaire. Of these, 2.22% (n=1156 participants; mean age 38.69, SD 12.14 years; women=75.50%; non-Hispanic White=68.88%) completed the screener, met eligibility criteria (including elevated depressive symptoms [Patient Health Questionnaire-9 [PHQ-9] score≥5]), completed baseline measures, were enrolled, and were randomized. Participants were recruited from Craigslist (694/1154, 60.14%), a US-based advertisement website, and university email messages (107/1154, 9.27%); participants were enrolled from every US state. Across the study, 84% (971/1156) of participants were retained (completed ≥1 measure at 17-week follow-up). Across time points, ≥81.40% (941/1156) of participants completed questionnaires and ≥75.17% (869/1156) completed biological samples. Of those completing questionnaires, ≥84.14% (796/946) completed SEA and video log tasks and ≥91.75% (868/946) completed the MST. Of completed assessments, high-quality or analyzable data rates across all time points were ≥97.89% (926/946) for questionnaires, ≥90.20% (773/857) for SEA, ≥84.60% (725/857) for video logs, ≥94.20% (1056/1121) for the MST, ≥98.84% (849/859) for dried blood spots, and ≥99.43% () for microbiome samples. Greater depressive symptoms at screening, but not age, predicted completion of baseline measures (odds ratios 0.96‐0.99; P <.001). For enrolled participants, recruitment sources and baseline depressive symptoms were not predictive of data completion or quality. Older age and having a college degree predicted significantly higher rates of data completion across all data types (questionnaire, behavioral, and biological) at week 4 or week 17 follow-ups. Conclusions: This methodological approach offers one model of incorporating objective measures of well-being into DCTs testing DMHIs. Implications and limitations of our approach are discussed.

This paper explores the design, development and evaluation of a digital platform that aims to assist young people who have experienced trauma in understanding and expressing their emotions and fostering social connections. Integrating principles from expressive arts and narrative-based therapies, we collaborate with lived experts to iteratively design a novel, user-centered digital tool for young people to create and share comics that represent their experiences. Specifically, we conduct a series of nine workshops with N=54 trauma-impacted youth and young adults to test and refine our tool, beginning with three workshops using low-fidelity prototypes, followed by six workshops with Cube, a web version of the tool. A qualitative analysis of workshop feedback and empathic relations analysis of artifacts provides valuable insights into the usability and potential impact of the tool, as well as the specific needs of young people who have experienced trauma. Our findings suggest that the integration of expressive and narrative therapy principles into Cube can offer a unique avenue for trauma-impacted young people to process their experiences, more easily communicate their emotions, and connect with supportive communities. We end by presenting implications for the design of social technologies that aim to support the emotional well-being and social integration of youth and young adults who have faced trauma.

Approximately 400,000 youth in the US are living in foster care due to experiences with abuse or neglect at home[17]. For multiple reasons, these youth often don't receive adequate social support from those around them. Despite technology's potential, very little work has explored how these tools can provide more support to foster-involved youth. To begin to fill this gap, we worked with current and former foster-involved youth to develop the first digital tool that aims to increase social support for this population, creating a novel system in which users complete reflective check-ins in an online community setting. We then conducted a pilot study with 15 current and former foster-involved youth, comparing the effect of using the app for two weeks to two weeks of no intervention. We collected qualitative and quantitative data, which demonstrated that this type of interface can provide youth with types of social support that are often not provided by foster care services and other digital interventions. The paper details the motivation behind the app, the trauma-informed design process, and insights gained from this initial evaluation study. Finally, the paper concludes with recommendations for designing digital tools that effectively provide social support to foster-involved youth.

People inherently use experiences of their past while imagining their future, a capability that plays a crucial role in mental health. Resonance is an AI-powered journaling tool designed to augment this ability by offering AI-generated, action-oriented suggestions for future activities based on the user's own past memories. Suggestions are offered when a new memory is logged and are followed by a prompt for the user to imagine carrying out the suggestion. In a two-week randomized controlled study (N=55), we found that using Resonance significantly improved mental health outcomes, reducing the users' PHQ8 scores, a measure of current depression, and increasing their daily positive affect, particularly when they would likely act on the suggestion. Notably, the effectiveness of the suggestions was higher when they were personal, novel, and referenced the user's logged memories. Finally, through open-ended feedback, we discuss the factors that encouraged or hindered the use of the tool.

This paper studies the contribution of the visual road scene to estimate the driver-reported stress levels. Our research leverages on previous work showing that environmental factors, such as traffic congestion, weather conditions, and driving context, impact driver's stress. Each of the models we evaluated is trained and tested with the publicly available AffectiveROAD dataset to estimate three categories of driver-reported stress level. We test three types of modelling approaches: (i) single-frame baselines (Random Forest, SVM, and Convolutional Neural Networks); (ii) Temporal Segment Networks (TSN) and two variants of it, which use learned weights (TSN-w) and LSTM (TSN-LSTM) as consensus functions; and (iii) video classification Transformers. Our experiments reveal that the TSN-w, TSN-LSTM, and Transformer models achieve statistically equivalent performances, all significantly outperforming the other models. Particularly noteworthy is TSN-w, which attains the highest performance observed with an average accuracy of 0.77. We further provide an explainability analysis using Class Activation Mapping and image semantic segmentation to identify the elements of the road scene that contribute the most to high levels of stress. Our results demonstrate that the visible road scene offers significant contextual information for estimating driver-reported stress levels, with potential implications for the design of safer urban road environments.

Background: There is increasing interest in the development of scalable digital mental health interventions for perinatal populations to increase accessibility. Mobile behavioral activation (BA) is efficacious for the treatment of perinatal depression; however, the effect of comorbid anxiety and depression (CAD) on symptom trajectories remains underexplored. This is important given that at least 10% of women in the perinatal period experience CAD. Objective: We assessed whether there were differences in symptom trajectories in pregnant participants with CAD as compared to those with depression only (ie, major depressive disorder [MDD]) during intervention with a BA mobile gaming app. Methods: Pregnant adults with either CAD (n=10) or MDD (n=7) used a BA app for 10 weeks and completed biweekly symptom severity questionnaires for depression and anxiety. We assessed whether baseline diagnoses were associated with differential symptom trajectories across the study with mixed effects longitudinal models. Results: When controlling for baseline symptoms, results revealed a significant interaction between baseline diagnosis and the quadratic component of study week on anxiety (β=.18, SE 0.07; t₆₂=2.61; P=.01), revealing a tendency for anxiety in the CAD group to increase initially and then decrease at an accelerated rate, whereas MDD symptoms were relatively stable across time. There was a significant effect of linear time on depression (β=−.39, SE 0.11; t₆₈=−3.51; P=.001), showing that depression declined steadily across time for both groups. There was a significant effect of baseline diagnosis on depression (β=−8.53, SE 3.93; t₁₃=−2.17; P=.05), suggesting that those with MDD had higher follow-up depression compared to those with CAD when holding other predictors constant. Conclusions: The app was beneficial in reducing depression symptoms in perinatal individuals with different comorbidity profiles. With respect to anxiety symptom trajectories, however, there was more variability. The app may be especially effective for the treatment of anxiety symptoms among individuals with CAD, as it encourages in-the-moment ecologically relevant exposure to anxiety-provoking stimuli. Despite no significant group difference in baseline anxiety symptoms, the MDD group did not have a significant reduction in their anxiety symptoms across the study period, and some individuals had an increase in anxiety. Findings may point to opportunities for the augmentation of BA gaming apps for those with MDD to more effectively target anxiety symptoms. Overall, findings suggest there may be value in considering comorbidities and individual variations in participants when developing scalable mobile interventions for perinatal populations.