Experiential negative symptoms (ENS) of schizophrenia, such as asociality, anhedonia, and avolition, are associated with poor outcomes, yet no FDA-approved pharmacotherapies currently exist specifically to target these symptoms. With the increasing use of smartphones, evidence-based digital interventions delivered by prescription digital therapeutics (DTx) may present an opportunity to address the unmet therapeutic need for ENS of schizophrenia. CT‑155/BI 3972080 (CT-155) is being developed as a smartphone-based prescription DTx for the treatment of ENS. A multicenter, 7-week, single-arm, open-label, exploratory study (NCT05486312) evaluated the engagement, adherence, potential effectiveness, acceptability, user experience, and safety of an abbreviated version of CT-155 (CT‑155 beta). Engagement and adherence with CT-155 beta were measured passively throughout the study using the study app. Change in ENS severity was assessed using the clinically administered clinical assessment interview for negative symptoms, motivation, and pleasure subscale (CAINS-MAP). Acceptability and user experience were assessed using the validated Mobile App Rating Scale (MARS) along with an episodic user experience survey, respectively. Fifty participants with a clinically confirmed schizophrenia diagnosis were enrolled; 80% were male, 58% were Black or African American, and the median (range) age was 53.5 (23–64) years. At baseline, participants' mean (SD) CAINS-MAP total score was 20.5 (8.3). Most participants (n = 43; 86%) completed the 7-week study. Participants readily engaged with CT-155 beta. Kaplan–Meier retention analysis showed that 84% of participants (N = 42/50) engaged with CT-155 beta (i.e., last app open) until the end of the study period. Daily app check-ins were completed on a median (IQR) of 43.0 (19–47) days of the 49 possible days (88%). The median (IQR) duration of engagement was 11.6 (8.1–16.1) min per session. Additionally, adherence with CT-155 was high, with participants completing a median of 18 (IQR 13–20) of the 21 therapeutic lessons available. After 7 weeks of CT-155 beta usage, the mean change in within-subject CAINS-MAP score was 3.6 points from baseline (95% CI 1.3, 5.8; p = 0.0026; baseline: 20.4 (8.6) Week 7: 16.8 (7.7)). Most participants (91%; n = 39/43) rated CT-155 beta functionality using MARS assessment as acceptable or higher, with an overall mean MARS functionality subscale score of 4.2 points out of 5 points, with 5 corresponding to “excellent” at Week 7. The end of study participant feedback survey showed that 95% (n = 42/44) of participants would recommend using CT-155 beta. No app-related adverse events nor severe adverse events leading to discontinuation of the study were reported. Overall, the study demonstrated the feasibility of CT-155 beta in participants with ENS of schizophrenia. Results from this feasibility study show the potential of evidence-based DTx approaches to address ENS of schizophrenia.

Seasonal and weather changes can significantly impact depression severity, yet findings remain inconsistent across populations. This study explored depression variations across the seasons and the interplays between weather changes, physical activity, and depression severity among 428 participants in a real-world longitudinal mobile health study. Clustering analysis identified four participant subgroups with distinct patterns of depression severity variations in 1 year. While one subgroup showed stable depression levels throughout the year, others peaked at various seasons. The subgroup with stable depression had older participants with lower baseline depression severity. Mediation analysis revealed temperature and day length significantly influenced depression severity, which in turn impacted physical activity levels indirectly. Notably, these indirect influences manifested differently or even oppositely across participants with varying responses to weather. These findings support the hypothesis of heterogeneity in individuals’ seasonal depression variations and responses to weather, underscoring the necessity for personalized approaches in depression management and treatment.

Background:The generalizability of clinical research hinges on robust study designs, which include the recruitment and maintenance of a representative study population. This study examines the evolution of the demographic characteristics of 329,038 participants who enrolled and participated in The All of Us Research Program (AoURP), a decentralized study aimed at representing the diversity of the United States. Objective:The primary objectives of this study were to assess alterations in the demographic composition of the cohort at different protocol stages within AoURP, while analyzing completion rates and timeframes for survey and substudy completion. Additionally, we examined how participant interactions with the program impacted engagement and survey responses. Methods:We conducted a longitudinal analysis of the AoURP data, tracking changes in demographic composition, completion rates, and completion times for surveys and substudies. Comparative analyses were performed to assess differences in engagement and survey completion based on sociodemographic characteristics of participants involved in postenrollment study components. Results:The sociodemographic composition of the cohort that participated in the postenrollment study (eg, optional components) differed significantly from that of the recruited population. The proportion of self-identified White participants increased by 21.2%, whereas the proportion of Black or African American participants decreased by 12.18% (P=.02). Participants who identified as White (n=93,614, 52.7%) and NonHispanic (n=109,279, 42.21%) were more engaged compared to those identifying as Black or African American (n=10,887, 15.76%), Asian (n=4274, 38.72%), or Hispanic (n=12,530, 20.7%; P=.006). Participants' response times to study surveys and completeness varied across all demographic groups (P<.001). Furthermore, those identifying as White skipped fewer survey questions (1.19) compared to those identifying as Black or African American (1.40) or other racial and ethnic identities (P<.001). Conclusions:The AoURP dataset serves as an exceptional resource for investigating diverse public health concerns. However, the longitudinal analysis of participant-level data underscores a significant skew in population diversity, suggesting the need for targeted strategies to enhance engagement and retention across all groups. Ensuring diversity in the cohort is essential for maintaining the study's representativeness and the broad applicability of its findings.

Healthcare researchers are increasingly utilizing smartphone sensor data as a scalable and cost-effective approach to studying individualized health-related behaviors in real-world settings. However, to develop reliable and robust digital behavioral signatures that may help in the early prediction of the individualized disease trajectory and future prognosis, there is a critical need to quantify the potential variability that may be present in the underlying sensor data due to variations in the smartphone hardware and software used by large population. Using sensor data collected in real-world settings from 3000 participants’ smartphones for up to 84 days, we compared differences in the completeness, correctness, and consistency of the three most common smartphone sensors—the accelerometer, gyroscope, and GPS— within and across Android and iOS devices. Our findings show considerable variation in sensor data quality within and across Android and iOS devices. Sensor data from iOS devices showed significantly lower levels of anomalous point density (APD) compared to Android across all sensors (p < 1 × 10−4). iOS devices showed a considerably lower missing data ratio (MDR) for the accelerometer compared to the GPS data (p < 1 × 10−4). Notably, the quality features derived from raw sensor data across devices alone could predict the device type (Android vs. iOS) with an up to 0.98 accuracy 95% CI [0.977, 0.982]. Such significant differences in sensor data quantity and quality gathered from iOS and Android platforms could lead to considerable variation in health-related inference derived from heterogenous consumer-owned smartphones. Our research highlights the importance of assessing, measuring, and adjusting for such critical differences in smartphone sensor-based assessments. Understanding the factors contributing to the variation in sensor data based on daily device usage will help develop reliable, standardized, inclusive, and practically applicable digital behavioral patterns that may be linked to health outcomes in real-world settings.

Prior research has shown that changes in seasons and weather can have a significant impact on depression severity. However, findings are inconsistent across populations, and the interplay between weather, behavior, and depression has not been fully quantified. This study analyzed real-world data from 428 participants (a subset; 68.7% of the cohort) in the RADAR-MDD longitudinal mobile health study to investigate seasonal variations in depression (measured through a remote validated assessment - PHQ-8) and examine the potential interplay between dynamic weather changes, physical activity (monitored via wearables), and depression severity. The clustering of PHQ-8 scores identified four distinct seasonal variations in depression severity: one stable trend and three varying patterns where depression peaks in different seasons. Among these patterns, participants within the stable trend had the oldest average age (p=0.002) and the lowest baseline PHQ-8 score (p=0.003). Mediation analysis assessing the indirect effect of weather on physical activity and depression showed significant differences among participants with different affective responses to weather. These findings illustrate the heterogeneity in individuals' seasonal depression variations and responses to weather, underscoring the necessity for personalized approaches to help understand the impact of environmental factors on the real-world effectiveness of behavioral treatments.

Digital therapeutics–web-based programs, smartphone applications, and wearable devices designed to prevent, treat, or manage clinical conditions through software-driven, evidence-based intervention–can provide accessible alternatives and/or may supplement standard care for patients with serious mental illnesses (SMI), including schizophrenia. In this paper we provide a targeted summary of the rapidly growing field of digital therapeutics for schizophrenia and related SMI. We first define digital therapeutics. We then provide a brief summary of the emerging evidence of efficacy of digital therapeutics for improving clinical outcomes, focusing on potential mechanisms of action for addressing some of the most challenging problems, including negative symptoms of psychosis. Our focus on these promising targets for digital therapeutics, including the latest in prescription models in the commercial space, highlights future directions for research and practice in this exciting field.

Bipolar disorder (BD) is a mood disorder with different phases alternating between euthymia, manic or hypomanic episodes, and depressive episodes. While motor abnormalities are commonly seen during depressive or manic episodes, not much attention has been paid to postural abnormalities during periods of euthymia and their association with illness burden. We collected 24-hour posture data in 32 euthymic participants diagnosed with BD using a shirt-based wearable. We extracted a set of nine time-domain features, and performed unsupervised participant clustering. We investigated the association between posture variables and 12 clinical characteristics of illness burden. Based on their postural dynamics during the daytime, evening, or nighttime, participants clustered in three clusters. Higher illness burden was associated with lower postural variability, in particular during daytime. Participants who exhibited a mostly upright sitting/standing posture during the night with frequent nighttime postural transitions had the highest number of lifetime depressive episodes. Euthymic participants with BD exhibit postural abnormalities that are associated with illness burden, especially with the number of depressive episodes. Our results contribute to understanding the role of illness burden on posture changes and sleep consolidation in periods of euthymia.

Recent growth in digital technologies has enabled the recruitment and monitoring of large and diverse populations in remote health studies. However, the generalizability of inference drawn from remotely collected health data could be severely impacted by uneven participant engagement and attrition over the course of the study. We report findings on long-term participant retention and engagement patterns in a large multinational observational digital study for depression containing active (surveys) and passive sensor data collected via Android smartphones, and Fitbit devices from 614 participants for up to 2 years. Majority of participants (67.6%) continued to remain engaged in the study after 43 weeks. Unsupervised clustering of participants' study apps and Fitbit usage data showed 3 distinct engagement subgroups for each data stream. We found: (i) the least engaged group had the highest depression severity (4 PHQ8 points higher) across all data streams; (ii) the least engaged group (completed 4 bi-weekly surveys) took significantly longer to respond to survey notifications (3.8 h more) and were 5 years younger compared to the most engaged group (completed 20 bi-weekly surveys); and (iii) a considerable proportion (44.6%) of the participants who stopped completing surveys after 8 weeks continued to share passive Fitbit data for significantly longer (average 42 weeks). Additionally, multivariate survival models showed participants' age, ownership and brand of smartphones, and recruitment sites to be associated with retention in the study. Together these findings could inform the design of future digital health studies to enable equitable and balanced data collection from diverse populations.

Objective:Recruitment of a sufficiently large and representative patient sample and its retention during central nervous system (CNS) trials presents major challenges for study sponsors. Technological advances are reshaping clinical trial operations to meet these challenges, and the COVID-19 pandemic further accelerated this development.Method of Research:The International Society for CNS Clinical Trials and Methodology (ISCTM; www.isctm.org) Innovative Technologies for CNS Trials Working Group surveyed the state of technological innovations for improved recruitment and retention and assessed their promises and pitfalls.Results:Online advertisement and electronic patient registries can enhance recruitment, but challenges with sample representativeness, conversion rates from eligible prescreening to enrolled patients, data privacy and security, and patient identification remain hurdles for optimal use of these technologies. Electronic medical records (EMR) mining with artificial intelligence (AI)/machine learning (ML) methods is promising but awaits translation into trials. During the study treatment phase, technological innovations increasingly support participant retention, including adherence with the investigational treatment. Digital tools for adherence and retention support take many forms, including patient-centric communication channels between researchers and participants, real-time study reminders, and digital behavioral interventions to increase study compliance. However, such tools add technical complexities to trials, and their impact on the generalizability of results are largely unknown.Conclusion:Overall, the group found a scarcity of systematic data directly assessing the impact of technological innovations on study recruitment and retention in CNS trials, even for strategies with already high adoption, such as online recruitment. Given the added complexity and costs associated with most technological innovations, such data is needed to fully harness technologies for CNS trials and drive further adoption.

IMPORTANCE The use of consumer-grade wearable devices for collecting data for biomedical research may be associated with social determinants of health (SDoHs) linked to people's understanding of and willingness to join and remain engaged in remote health studies. OBJECTIVE To examine whether demographic and socioeconomic indicators are associated with willingness to join a wearable device study and adherence to wearable data collection in children. DESIGN, SETTING, AND PARTICIPANTS This cohort study used wearable device usage data collected from 10 414 participants (aged 11-13 years) at the year-2 follow-up (2018-2020) of the ongoing Adolescent Brain and Cognitive Development (ABCD) Study, performed at 21 sites across the United States. Data were analyzed from November 2021 to July 2022. MAIN OUTCOMES AND MEASURES The 2 primary outcomeswere (1) participant retention in the wearable device substudy and (2) total devicewear time during the 21-day observation period. Associations between the primary end points and sociodemographic and economic indicatorswere examined. RESULTS The mean (SD) age of the 10 414 participants was 12.00 (0.72) years, with 5444 (52.3%) male participants. Overall, 1424 participants (13.7%) were Black; 2048 (19.7%), Hispanic; and 5615 (53.9%) White. Substantial differences were observed between the cohort that participated and shared wearable device data (wearable device cohort [WDC]; 7424 participants [71.3%]) compared with those who did not participate or share data (no wearable device cohort [NWDC]; 2900 participants [28.7%]). Black children were significantly underrepresented (- 59%) in the WDC (847 [11.4%]) compared with the NWDC (577 [19.3%]; P <.001). In contrast, White children were overrepresented (+132%) in the WDC (4301 [57.9%]) vs the NWDC (1314 [43.9%]; P <.001). Children from low-income households (<$24 999) were significantly underrepresented in WDC (638 [8.6%]) compared with NWDC (492 [16.5%]; P <.001). Overall, Black children were retained for a substantially shorter duration (16 days; 95% CI, 14-17 days) compared with White children (21 days; 95% CI, 21-21 days; P <.001) in the wearable device substudy. In addition, total device wear time during the observation was notably different between Black vs White children (beta = -43.00 hours; 95% CI, -55.11 to -30.88 hours; P <.001). CONCLUSIONS AND RELEVANCE In this cohort study, large-scale wearable device data collected from children showed considerable differences between White and Black children in terms of enrollment and daily wear time. While wearable devices provide an opportunity for real-time, highfrequency contextual monitoring of individuals' health, future studies should account for and address considerable representational bias in wearable data collection associated with demographic and SDoH factors.

We recruited 53 BD participants at two Canadian academic psychiatric hospitals (the Centre for Addiction and Mental Health, Toronto; the Royal Ottawa Hospital, Ottawa) between April 2016 and December 2019. Participants were provided with a BioHarness™ 3.0 wearable physiological electronic (e-) monitoring device, which they wore continuously for 24 hours. Posture data were recorded in units of degrees from vertical, sampled every sec (1 Hz) with a sensitivity range of 1° to 8°, and a dynamic range of ±180°. The sensors were configured such that a posture value of -90° indicates a supine posture (i.e., lying face up), and a 90° posture indicates a prone posture (i.e., lying face down). Posture was represented as a 1 Hz-discretized single channel of angular positions of a participant’s chest over the course of 24 hours. We extracted a set of 9 time-domain features to characterize postural dynamics in terms of amplitude, energy, variability, and transitions for 3 different periods: day (from 7:00 AM to 2:59 PM), evening (from 3:00 PM to 10:59 PM), and night (from 11:00 PM to 6:59 AM). To assess posture amplitude, we computed the mean posture (angle in degrees) and its range; to assess posture dynamics’ energy content, we computed the root mean squared (RMS) value; to assess posture variability, we computed the coefficient of variation (CV), interquartile range (IQR), and median absolute deviation (MAD). Kurtosis and skewness were computed to assess the postural statistical distribution in terms of distribution sharpness and symmetry. Lastly, the number of postural transitions was computed using Bayesian Online Changepoint Detection (BOCD) which identifies the abrupt changes in sequential data generative parameters, such that each changepoint is indicative of a postural transition (e.g., being upright to bending over, or lying down to sitting upright). We used the Kruskal-Wallis test to assess the level of inter-cluster statistical significance for each posture feature, and corrected the p-values using the Benjamini-Hochberg (BH) method. Then, in each posture-specific cluster, we assessed the median and IQR of cluster-specific illness burden variables. We computed pairwise Spearman correlation coefficients to assess the strength and direction of the association between the postural dynamics descriptors (e.g., mean, IQR) and illness burden continuous variables (e.g., lifetime number of depressive episodes). We used a Chi Square test to assess the association between posture and categorical illness burden variables (e.g., history of suicide attempts, family history of suicide). We controlled for age, baseline functional capacity, and body mass index (BMI) by setting them as control variables in a multiple linear regression model. The p-values were corrected using the BH method. To identify cluster members (i.e., participants who shared similar postural dynamics), we performed hierarchical clustering of BD participants using posture features as model input.

Real-world data (RWD) like electronic health records (EHR) has great potential for secondary use by health systems and researchers. However, collected primarily for efficient health care, EHR data may not equitably represent local regions and populations, impacting the generalizability of insights learned from it. We assessed the geospatial representativeness of regions in a large health system EHR data using a spatial analysis workflow, which provides a data-driven way to quantify geospatial representation and identify adequately represented regions. We applied the workflow to investigate geospatial patterns of overweight/obesity and depression patients to find regional "hotspots" for potential targeted interventions. Our findings show the presence of geospatial bias in EHR and demonstrate the workflow to identify spatial clusters after adjusting for bias due to the geospatial representativeness. This work highlights the importance of evaluating geospatial representativeness in RWD to guide targeted deployment of limited healthcare resources and generate equitable real-world evidence.

Most people with mental health disorders cannot receive timely and evidence-based care despite billions of dollars spent by healthcare systems. Researchers have been exploring using digital health technologies to measure behavior in real-world settings with mixed results. There is a need to create accessible and computable digital mental health datasets to advance inclusive and transparently validated research for creating robust real-world digital biomarkers of mental health. Here we share and describe one of the largest and most diverse real-world behavior datasets from over two thousand individuals across the US. The data were generated as part of the two NIMH-funded randomized clinical trials conducted to assess the effectiveness of delivering mental health care continuously remotely. The longitudinal dataset consists of self-assessment of mood, depression, anxiety, and passively gathered phone-based behavioral data streams in real-world settings. This dataset will provide a timely and long-term data resource to evaluate analytical approaches for developing digital behavioral markers and understand the effectiveness of mental health care delivered continuously and remotely.

Background Smartphones are increasingly used in health research. They provide a continuous connection between participants and researchers to monitor long-term health trajectories of large populations at a fraction of the cost of traditional research studies. However, despite the potential of using smartphones in remote research, there is an urgent need to develop effective strategies to reach, recruit, and retain the target populations in a representative and equitable manner. Objective We aimed to investigate the impact of combining different recruitment and incentive distribution approaches used in remote research on cohort characteristics and long-term retention. The real-world factors significantly impacting active and passive data collection were also evaluated. Methods We conducted a secondary data analysis of participant recruitment and retention using data from a large remote observation study aimed at understanding real-world factors linked to cold, influenza, and the impact of traumatic brain injury on daily functioning. We conducted recruitment in 2 phases between March 15, 2020, and January 4, 2022. Over 10,000 smartphone owners in the United States were recruited to provide 12 weeks of daily surveys and smartphone-based passive-sensing data. Using multivariate statistics, we investigated the potential impact of different recruitment and incentive distribution approaches on cohort characteristics. Survival analysis was used to assess the effects of sociodemographic characteristics on participant retention across the 2 recruitment phases. Associations between passive data-sharing patterns and demographic characteristics of the cohort were evaluated using logistic regression. Results We analyzed over 330,000 days of engagement data collected from 10,000 participants. Our key findings are as follows: first, the overall characteristics of participants recruited using digital advertisements on social media and news media differed significantly from those of participants recruited using crowdsourcing platforms (Prolific and Amazon Mechanical Turk; P<.001). Second, participant retention in the study varied significantly across study phases, recruitment sources, and socioeconomic and demographic factors (P<.001). Third, notable differences in passive data collection were associated with device type (Android vs iOS) and participants’ sociodemographic characteristics. Black or African American participants were significantly less likely to share passive sensor data streams than non-Hispanic White participants (odds ratio 0.44-0.49, 95% CI 0.35-0.61; P<.001). Fourth, participants were more likely to adhere to baseline surveys if the surveys were administered immediately after enrollment. Fifth, technical glitches could significantly impact real-world data collection in remote settings, which can severely impact generation of reliable evidence. Conclusions Our findings highlight several factors, such as recruitment platforms, incentive distribution frequency, the timing of baseline surveys, device heterogeneity, and technical glitches in data collection infrastructure, that could impact remote long-term data collection. Combined together, these empirical findings could help inform best practices for monitoring anomalies during real-world data collection and for recruiting and retaining target populations in a representative and equitable manner.

Ideally, a patient’s response to medication can be monitored by measuring changes in performance of some activity. In observational studies, however, any detected association between treatment (“on-medication” vs “off-medication”) and the outcome (performance in the activity) might be due to confounders. In particular, causal inferences at the personalized level are especially vulnerable to confounding effects that arise in a cyclic fashion. For quick acting medications, effects can be confounded by circadian rhythms and daily routines. Using the time-of-the-day as a surrogate for these confounders and the performance measurements as captured on a smartphone, we propose a personalized statistical approach to disentangle putative treatment and “time-of-the-day” effects, that leverages conditional independence relations spanned by causal graphical models involving the treatment, time-of-the-day, and outcome variables. Our approach is based on conditional independence tests implemented via standard and temporal linear regression models. Using synthetic data, we investigate when and how residual autocorrelation can affect the standard tests, and how time series modeling (namely, ARIMA and robust regression via HAC covariance matrix estimators) can remedy these issues. In particular, our simulations illustrate that when patients perform their activities in a paired fashion, positive autocorrelation can lead to conservative results for the standard regression approach (i.e., lead to deflated true positive detection), whereas negative autocorrelation can lead to anticonservative behavior (i.e., lead to inflated false positive detection). The adoption of time series methods, on the other hand, leads to well controlled type I error rates. We illustrate the application of our methodology with data from a Parkinson’s disease mobile health study.

Background: Suboptimal adherence to data collection procedures or a study intervention is often the cause of a failed clinical trial. Data from connected sensors, including wearables, referred to here as biometric monitoring technologies (BioMeTs), are capable of capturing adherence to both digital therapeutics and digital data collection procedures, thereby providing the opportunity to identify the determinants of adherence and thereafter, methods to maximize adherence. Objective: We aim to describe the methods and definitions by which adherence has been captured and reported using BioMeTs in recent years. Identifying key gaps allowed us to make recommendations regarding minimum reporting requirements and consistency of definitions for BioMeT-based adherence data. Methods: We conducted a systematic review of studies published between 2014 and 2019, which deployed a BioMeT outside the clinical or laboratory setting for which a quantitative, nonsurrogate, sensor-based measurement of adherence was reported. After systematically screening the manuscripts for eligibility, we extracted details regarding study design, participants, the BioMeT or BioMeTs used, and the definition and units of adherence. The primary definitions of adherence were categorized as a continuous variable based on duration (highest resolution), a continuous variable based on the number of measurements completed, or a categorical variable (lowest resolution). Results: Our PubMed search terms identified 940 manuscripts; 100 (10.6%) met our eligibility criteria and contained descriptions of 110 BioMeTs. During literature screening, we found that 30% (53/177) of the studies that used a BioMeT outside of the clinical or laboratory setting failed to report a sensor-based, nonsurrogate, quantitative measurement of adherence. We identified 37 unique definitions of adherence reported for the 110 BioMeTs and observed that uniformity of adherence definitions was associated with the resolution of the data reported. When adherence was reported as a continuous time-based variable, the same definition of adherence was adopted for 92% (46/50) of the tools. However, when adherence data were simplified to a categorical variable, we observed 25 unique definitions of adherence reported for 37 tools. Conclusions: We recommend that quantitative, nonsurrogate, sensor-based adherence data be reported for all BioMeTs when feasible; a clear description of the sensor or sensors used to capture adherence data, the algorithm or algorithms that convert sample-level measurements to a metric of adherence, and the analytic validation data demonstrating that BioMeT-generated adherence is an accurate and reliable measurement of actual use be provided when available; and primary adherence data be reported as a continuous variable followed by categorical definitions if needed, and that the categories adopted are supported by clinical validation data and/or consistent with previous reports.

The internet is frequently the first point of contact for people seeking support for their mental health symptoms. Digital interventions designed to be deployed through the internet have significant promise to reach diverse populations who may not have access to, or are not yet engaged in, treatment and deliver evidence-based resources to address symptoms. The liminal nature of online interactions requires designing to prioritize needs detection, intervention potency, and efficiency. Real-world implementation, data privacy and safety are equally important and can involve transparent partnerships with stakeholders in industry and non-profit organizations. This commentary highlights challenges and opportunities for research in this space, grounded in learnings from multiple research projects and teams aligned with this effort.