Jennifer Huberty

Background: Adolescent mental health needs remain largely unmet, particularly among youth in geographically underserved communities. Digital peer support is a promising approach to expanding access to mental health support, yet real-world evidence on engagement patterns and clinical outcomes remains limited. Objective: The purpose of this study was to characterize engagement patterns and real-world outcomes among adolescents and young adults enrolled in a commercially available, text-based peer support platform. Methods: This retrospective observational study analyzed secondary data from 5673 adolescents and young adults enrolled in a commercially available digital peer support platform from January 29, 2023, through June 3, 2026. Engagement was operationalized as communication days per month. Standardized clinical outcome measures (Patient Health Questionnaire-9 [PHQ-9], Generalized Anxiety Disorder-7 [GAD-7], and World Health Organization-Five Well-Being Index [WHO-5]) were administered as part of routine measurement-based care. Ordinary least squares regression was used to examine predictors of engagement, and complete-case pre-post change scores were evaluated across 4 assessment windows among participants with paired assessments. Results: The sample was predominantly female (4600/5673, 81.1%) with a mean age of 16.4 (SD 2.1) years and moderate-to-severe symptom burden at baseline (PHQ-9: mean 12.6, SD 6.1; GAD-7: mean 10.7, SD 5.0; WHO-5: mean 44.8, SD 21.0). Of enrolled adolescents and young adults, 98.1% (5565/5673) had at least one recorded engagement with the platform, with a mean of 4.56 (SD 6.12) communication days per month. Female sex was a significant positive predictor of engagement intensity (β=.64, SE 0.22; P =.004). Hispanic and Latino adolescents and young adults engaged significantly more frequently than White or non-Hispanic adolescents and young adults (β=.61, SE 0.26; P =.02). Health Professional Shortage Area (HPSA) shortage score was significantly and positively associated with engagement intensity (β=.08, SE 0.02; P <.001). Baseline symptom severity was not associated with engagement intensity (β=.094, SE 0.23; P =.68). Among participants with complete baseline and follow-up data (1437/5673, 25.3%), an exploratory complete-case analysis found within-measure paired scores improved significantly from baseline to follow-up across the PHQ-9, GAD-7, and WHO-5. At last assessment, 31.9% (237/742), 36.6% (222/606), and 37.8% (168/442) of adolescents and young adults met clinically meaningful improvement thresholds on the PHQ-9, GAD-7, and WHO-5, respectively. Conclusions: Text-based peer support shows preliminary promise as a scalable approach to expanding mental health access for underserved adolescents, though clinical improvement estimates are based on the subpopulation exposed to the digital peer support platform and may not generalize to the full enrolled population. Prospective, controlled studies with more complete outcome ascertainment are needed to establish causal efficacy.

UNSTRUCTURED Digital health companies increasingly depend on scientific evidence to raise capital, secure contracts, and stand out in a crowded market, yet little has been written about how science is practiced inside these companies. In 2023 and 2024, I described the role of the industry scientist and the barriers organizations face in integrating science, drawing on experience as head of science at a single company. This viewpoint revisits those claims from a different position: leading a science consultancy that has partnered with, advised, or held discovery conversations with more than 300 digital health and wellness companies. Three earlier claims endure. Science contributes to revenue when it answers questions buyers ask, resource-efficient methods such as retrospective analyses remain the right entry point, and science succeeds when business leaders own its use. Others require revision. Not every company needs a full-time scientific executive, hiring a scientist does not by itself produce a scientific strategy, and for artificial intelligence tools that make clinical claims, the runway before prospective trials become necessary has shortened. Working across many companies also revealed patterns no single role could show. Companies rarely ask for the science they need, evidence must align with business timelines without sacrificing rigor, and some of the most valuable scientific work involves shaping claims, measurement, and product decisions rather than conducting a study. I close with implications for scientists, company leaders, investors, payers and academic training programs, and a call for formal study of how science creates value in industry.

AI-powered mental health tools are increasingly deployed to support users across multiple sessions, yet the field lacks a principled framework for how memory in these systems should be structured and applied. In most current implementations, memory functions primarily as a personalization mechanism, optimizing for conversational continuity and user engagement without distinguishing between types of information that have fundamentally different clinical relevance. We propose a framework organizing memory in AI-powered mental health systems into 4 functionally distinct types. Episodic memory captures discrete, time-bound experiences tied to specific events and context. Pattern memory, adapted from the concept of procedural memory in cognitive psychology, tracks recurring patterns in cognition, emotion, and behavior across sessions. Semantic memory captures stable, personally relevant background context about the user. State-responsive memory represents the user’s current emotional and psychological condition in real time, taking priority over the other 3 types when acute distress or risk is signaled. Each type corresponds to a distinct therapeutically relevant function, and together they are designed to support the kind of cumulative, longitudinal understanding that effective mental health care requires. We term this framework “therapeutically informed memory,” drawing on established memory systems research and applying it to the clinical requirements of AI-powered mental health support. The aim of this viewpoint paper is to give AI developers, clinicians, and mental health organizations a shared vocabulary and design framework for organizing memory around therapeutic function rather than personalization alone. This paper is intended primarily for AI product and engineering teams, clinical advisors to digital mental health companies, and researchers evaluating AI-powered mental health tools. We describe the design requirements and clinical rationale for each memory type, discuss how the types interact and how priority should be assigned across them, and use Yuna, an AI-powered digital mental health intervention developed with clinical input, as an illustrative example of how this framework can be applied in practice. We conclude with design implications for the field and identify open questions regarding memory quality metrics, outcome validation, and the ethical dimensions of persistent memory as priorities for future research.

UNSTRUCTURED AI mental health tools increasingly market a single benchmark score as evidence of safety, despite failures that range widely in severity, from cold or insufficient responses to knowingly enabling harm. We argue that safety claims should specify which severity category they address and be supported by evidence appropriate to that category. We define a systems role in a mental health crisis as a bridge to human care rather than a treatment, introduce a four-category severity ladder for the ways a system can fail that role, and describe four types of evidence, from internal testing to real-world deployment, needed to credibly support a claim. Mapping the two together shows that current practice, a single score applied uniformly across every severity, systematically understates what has actually been demonstrated about a system's most severe failures. We propose a sequenced path for generating evidence at these categories without exposing at-risk users to unvalidated systems, and argue that vendors and buyers alike need a shared standard for what a safety claim should specify before it can be trusted.

Background: Digital mental health interventions using conversational AI agents are increasingly being adopted as scalable alternatives to traditional care. Engagement is typically measured using volume-based metrics (eg, session counts and total time on a platform). However, these metrics overlook engagement patterns over time, which are not well understood in relation to mental health outcomes. Objective: The purpose of this cross-sectional study was to explore how different patterns of engagement with Mental’s AI conversational agent relate to self-reported depression and anxiety. We aimed to (1) identify and describe engagement profiles based on patterns of interaction depth and temporal consistency, (2) compare depression and anxiety symptoms across engagement profiles, and (3) explore whether engagement profiles were associated with mental health symptom severity. Methods: This cross-sectional observational study linked survey responses to back-end app usage data from 112 Mental app users who completed at least 5 sessions with the conversational AI agent. Engagement profiles were derived using median splits on interaction depth (α parameter) and temporal consistency (Gini coefficient). Depression was assessed using the Patient Health Questionnaire-8 (PHQ-8), and anxiety was assessed using the Generalized Anxiety Disorder-7 (GAD-7). One-way ANOVAs compared symptoms across profiles. Linear regression models examined associations between profiles and symptom severity, adjusting for age, gender, and total duration of use. Results: We identified 4 distinct engagement profiles based on interaction depth and temporal consistency: extended and episodic (profile 1; n=25), extended and consistent (profile 2; n=31), brief and episodic (profile 3; n=31), and brief and consistent (profile 4; n=25). Users in profile 1 (extended and episodic) reported the lowest anxiety (mean 2.68, SD 2.43) and depression (mean 3.48, SD 4.06), while profile 4 (brief and consistent) reported the highest anxiety (mean 10.00, SD 7.03) and depression (mean 10.60, SD 8.75). Significant differences were observed for anxiety ( F _3,108 =8.07, P <.001, η ²=0.18) and depression ( F _3,108 =5.47, P =.002, η ²=0.13). In adjusted models, engagement profile was significantly associated with depression ( R ²=0.16, F _7,104 =2.87, and P =.009) and anxiety ( R ²=0.21, F _7,104 =4.04, and P <.001). Compared to profile 1, users in profiles 2 and 4 reported significantly higher depression and anxiety. Profile 3 differed from profile 1 for anxiety only (β=3.11, P =.047). Conclusions: Users with longer, clustered sessions reported the lowest symptoms, whereas those with brief, evenly distributed use reported the highest symptom levels, suggesting that the structure of engagement may be associated with symptom levels in ways that aggregate usage metrics do not capture. These findings are preliminary and hypothesis-generating, highlighting the importance of considering how engagement unfolds over time and suggesting that pattern-based measurement may improve the understanding of user outcomes in AI-powered mental health care. Future work should examine the directionality of these associations and whether distinct engagement patterns reflect meaningfully different modes of interacting with AI-powered care.

BACKGROUND Adolescent mental health needs remain largely unmet, particularly among youth in geographically underserved communities. Digital peer support is a promising approach to expanding mental health support, yet real-world evidence on engagement patterns and clinical outcomes remains limited. OBJECTIVE This study aimed to: 1) describe the demographic and clinical characteristics of enrolled adolescents and young adults and patterns of platform engagement; 2) identify demographic and clinical predictors of engagement intensity; and 3) describe within-measure pre-post changes in depressive symptoms, anxiety symptoms, and well-being among adolescents and young adults with paired assessments. METHODS This retrospective observational study analyzed secondary data from 5,673 adolescents and young adults enrolled in Somethings from January 29, 2023, through June 3, 2026. Engagement was operationalized as communication days per month. Standardized clinical outcome measures (Patient Health Questionnaire-9 [PHQ-9], Generalized Anxiety Disorder-7 [GAD-7], World Health Organization-5 Well-Being Index [WHO-5]) were administered as part of routine measurement-based care. Ordinary least squares regression was used to examine predictors of engagement, and pre-post change scores were evaluated across four assessment windows. RESULTS The sample was predominantly female (81.1%, n = 4,600) with a mean age of 16.4 years and moderate-to-severe symptom burden at baseline (PHQ-9 M = 12.6; GAD-7 M = 10.7; WHO-5 M = 44.8). Of enrolled adolescents and young adults, 98.1% (n = 5,565) had at least one recorded engagement with the platform, with a mean of 4.56 communication days per month. Female sex was a significant positive predictor of engagement intensity (β = 0.64, p = .004). Hispanic and Latino adolescents and young adults also engaged significantly more frequently than White non-Hispanic adolescents and young adults (β = 0.61, p = .019). HPSA shortage score was significantly and positively associated with engagement intensity (β = 0.08, p < .001). Baseline symptom severity was not associated with engagement intensity (β = 0.04, p = .914). Within-measure paired scores improved significantly from baseline to follow-up across the PHQ-9, GAD-7, and WHO-5. At last assessment, 31.9% (n = 237/742), 36.6% (n = 222/606), and 38.0% (n = 167/442) of adolescents and young adults met clinically meaningful improvement thresholds on the PHQ-9, GAD-7, and WHO-5, respectively. CONCLUSIONS Text-based peer support shows promise as a scalable approach to expanding mental health access for underserved adolescents. Prospective, controlled studies are needed to establish causal efficacy.

Background: Gambling disorder is associated with substantial psychiatric and functional burden, yet few individuals receive treatment. Limited real-world evidence exists evaluating outcomes of virtually delivered behavioral health care for gambling disorder, particularly among clinically complex patients. Objective: The purpose of this study was to evaluate gambling symptom severity outcomes among adults with gambling disorder receiving care from Birches Health. We aimed to (1) characterize the clinical profile of adults seeking treatment for gambling disorder; (2) quantify changes in gambling symptom severity over the initial 12 weeks of treatment and examine whether baseline clinical complexity, such as gambling symptom severity, depression severity, and psychiatric comorbidities, was associated with differences in gambling symptom severity improvement over time; and (3) estimate the timing and likelihood of achieving clinically meaningful improvement in gambling symptom severity. Methods: This retrospective cohort study included 1305 adults receiving virtual behavioral health treatment for gambling disorder through Birches Health between June 2024 and April 2026. Gambling symptom severity was assessed using the Gambling Symptom Assessment Scale (G-SAS) weekly. Linear mixed-effects models evaluated changes in gambling symptom severity over 12 weeks and associations with baseline clinical characteristics. Clinically meaningful improvement was defined as a reduction of 4 or more points in the G-SAS score. Results: Participants had a mean age of 41.5 (SD 13.1) years, 65.2% (851/1305) were male, and baseline gambling symptom severity was moderate (mean G-SAS score 20.5, SD 11.83). Over half (730/1305, 56%) of participants presented with at least one psychiatric comorbidity, most commonly anxiety disorder (351/1305, 26.9%) and depressive disorder (276/1305, 21.1%). Gambling symptom severity declined significantly over the first 12 weeks of treatment, with G-SAS scores decreasing by approximately 0.099 points per day (P<.001), corresponding to an estimated 8.3-point reduction over 12 weeks. Higher baseline depressive symptom severity was associated with faster improvement in gambling symptoms (P=.01), whereas depressive disorder (P=.03) and attention-deficit/hyperactivity disorder (P=.008) diagnoses were associated with slower improvement trajectories. Among patients with routine follow-up assessments recorded during the initial 12 weeks of treatment (1071/1305, 82.1%), 71.7% (935/1305) achieved clinically meaningful improvement in gambling symptom severity, with a median time to improvement of 14 days. Conclusions: A clinically complex population of adults receiving care through a national virtual behavioral health care provider demonstrated rapid and clinically meaningful reductions in gambling symptom severity. These findings highlight the potential of specialized virtual care models to expand access to gambling treatment and support symptom improvement in routine care settings. Future research should evaluate longer-term recovery trajectories and identify factors associated with sustained improvement and ongoing engagement in care.