Patient-provider matching, engagement, and outcomes of a digital mental health treatment platform: real-world retrospective cohort study (Preprint)

BACKGROUND Despite recent advancements in mental health care over the past several decades, few interventions have been able to move the needle past the typical modest engagement and effectiveness rates. Technology-enabled mental health platforms that incorporate user-driven patient-provider matching may offer a novel way to personalize and optimize outcomes. We conducted the current study because little is known about the engagement and preliminary levels of clinical effectiveness of these newer types of mental health platforms and whether patient self-selection of their provider characteristics might be associated with each of these outcomes. OBJECTIVE The objective of this real-world, retrospective cohort study was to determine the levels of engagement and clinical outcomes associated with the use of a technology-enabled mental health platform that allows patients to select preferred provider characteristics and to evaluate whether the selection of a provider characteristics was associated with differential patterns of outcomes. METHODS Data from two cohorts of adult Grow Therapy patients aged 18 or older who had elevated depressive and/or anxiety symptoms at baseline provided data for the study analyses (Patient Health Questionnaire-9 [PHQ-9] > 9 and/or Generalized Anxiety Disorder-7 [GAD-7] > 9) . Engagement with the platform was measured in terms of number of provider visits and studied on an intent-to-treat basis. Clinical outcomes were quantified for patients with at least 2 provider visits according to changes in symptom assessments between the first and last provider visits and coded for meeting criteria for a minimum clinically important difference (i.e., a decline of at least 5 points on the PHQ-9 or at least 4 points on the GAD-7). Patient selections of a provider specialty or a provider identity characteristic prior to the first visit were studied as moderators. Patient characteristics were compared for those with versus without at least 2 provider visits to gauge the generalizability of the findings to all patients presenting for care. RESULTS The sample consisted of 159,448 patients with elevated depressive symptoms and 167,356 patients with elevated anxiety symptoms at baseline. Findings suggest that enrolled patients found the platform engaging and preliminarily effective (58.9% and 63.0% of the elevated depressive and anxiety symptom cohorts experienced a minimal clinically important difference in symptoms, respectively). Although relatively few patients selected a provider characteristic prior to enrollment, those selecting a provider specialty experienced significantly better outcomes while engaging significantly less frequently and those selecting a provider identity engaged significantly more frequently than those who did not, respectively. CONCLUSIONS Although additional, more rigorous studies of the platform are needed, this real world study demonstrated that a technology-enabled mental health platform that allows patients to select preferred provider characteristics can be engaging and may be preliminarily effective.