Search

BACKGROUND Predicting the outcomes of individual participants for treatment interventions appears central for making mental healthcare more tailored and effective. Machine Learning (ML) has been proven to be able to make such predictions with notable accuracy. However, little work has been done to investigate the performance of such ML-based predictions within digital mental health (DMH) interventions. Using such data from real world settings could provide more realistic estimates of predictive performance in practice. OBJECTIVE This study evaluates the performance of ML in predicting treatment response in a DMH intervention designed for treating depression and anxiety. METHODS Several algorithms were trained based on the data of 970 participants to predict significant reduction in depression and anxiety symptoms, by using clinical and sociodemographic variables. As a Random Forest Classifier (RF) performed best over cross-validation, it was used to predict the outcomes of 279 new participants. RESULTS The RF achieved an accuracy of 0.71 for the test set (base-rate: 0.67, AUC: 0.60, P = .001, balanced accuracy: 0.60). Additionally, predicted non-responders showed less average reduction of their PHQ-9 (-2.7, P = .004) and GAD-7 values (-3.7, P < .001) compared to responders. Besides pre-treatment PHQ and GAD-7 values, the self-reported motivation, type of referral into the program (self versus healthcare provider) as well as Work Productivity and Activity Impairment Questionnaire (WPAI) items contributed most to the predictions. CONCLUSIONS The RF achieved an accuracy of 0.71 for the test set (base-rate: 0.67, AUC: 0.60, P = .001, balanced accuracy: 0.60). Additionally, predicted non-responders showed less average reduction of their PHQ-9 (-2.7, P = .004) and GAD-7 values (-3.7, P < .001) compared to responders. Besides pre-treatment PHQ and GAD-7 values, the self-reported motivation, type of referral into the program (self versus healthcare provider) as well as Work Productivity and Activity Impairment Questionnaire (WPAI) items contributed most to the predictions. CLINICALTRIAL

BACKGROUND Digital mental health interventions may help middle-aged and older adults with depression overcome barriers to accessing traditional care, but few studies have investigated their use in this population. OBJECTIVE This pilot study examines the feasibility, acceptability, and potential efficacy of the Meru Health Program, an 8-week mobile app–delivered intervention. METHODS A total of 20 community-dwelling middle-aged and older adults (age: mean 61.7 years, SD 11.3) with elevated depressive symptoms participated in a single-arm pilot study investigating the Meru Health Program, an app-delivered intervention supported by remote therapists. The program primarily uses mindfulness and cognitive behavioral skills to target depressive symptoms. A semistructured interview was completed at the baseline to establish current psychiatric diagnoses. Depressive symptoms were measured using the Patient Health Questionnaire and Patient-Reported Outcomes Measurement Information System (PROMIS) depression measures. Anxiety symptoms were measured using the Generalized Anxiety Disorder Scale and the PROMIS Anxiety measure. User experience and acceptability were examined through surveys and qualitative interviews. RESULTS In total, 90% (18/20) of the participants completed the program, with 75% (15/20) completing at least 7 of the 8 introductory weekly lessons. On average, participants completed 60 minutes of practice and exchanged 5 messages with their therapists every week. The app was rated as helpful by 89% (17/19) participants. Significant decreases in depressive (P=.03) and anxiety symptom measures (P=.01) were found; 45% (9/20) of participants showed clinically significant improvement in either depressive symptoms or anxiety symptoms. CONCLUSIONS The findings suggest that the commercially available Meru Health Program may be feasible, acceptable, and potentially beneficial to middle-aged and older adults. Although larger controlled trials are needed to demonstrate efficacy, these findings suggest that digital health interventions may benefit adults of all ages.

UNSTRUCTURED Abstract Depression is a burdensome and costly disease. Treatment is not sought by over half of depressed patients, and many who suffer remain depressed despite treatment. Furthermore, there is no single treatment efficacious for all patients, with optimal outcomes precluded by access, adherence, and patient satisfaction issues. The recent proliferation of telehealth solutions has increased access to care, especially during the COVID pandemic, but problems with several of its traditional types of delivery models still exist. Rather than the provision of traditional episodic mental health care, creative mental health solutions that can provide continuous care with frequent patient-provider interactions are urgently needed. This Viewpoint explores how digital health solutions enable the provision of continuous types of remote care to provide relief for some of the access and capacity problems exacerbated by requirements for face-to-face types of care.

BACKGROUND Depression is one of the most common mental health disorders and severely impacts one’s physical, psychological, and social functioning. To address access barriers to care, we developed Ascend —a smartphone-delivered, therapist-supported, 8-week intervention based on several evidence-based psychological treatments for depression and anxiety. A previous feasibility study with 102 adults with elevated depression reported that Ascend is associated with a postintervention reduction in depression symptoms. OBJECTIVE We aimed to examine whether Ascend is associated with a reduction in symptoms of anxiety, and importantly, whether reductions in symptoms of depression and anxiety are maintained up to 12 months postintervention. METHODS We assessed whether the previously reported, end-of-treatment improvements seen in the 102 adults with elevated symptoms of depression extended up to 12 months posttreatment for depression symptoms (measured by the Patient Health Questionnaire-9 [PHQ-9]) and up to 6 months posttreatment for anxiety symptoms (added to the intervention later and measured using the Generalized Anxiety Disorder-7 [GAD-7] scale). We used linear mixed effects models with Tukey contrasts to compare time points and reported intention-to-treat statistics with a sensitivity analysis. RESULTS The intervention was associated with reductions in symptoms of depression that were maintained 12 months after the program (6.67-point reduction in PHQ-9 score, 95% CI 5.59-7.75; P CONCLUSIONS There is limited evidence on whether outcomes associated with smartphone-based interventions for common mental health problems are maintained posttreatment. Participants who enrolled in Ascend experienced clinically significant reductions in symptoms of depression and anxiety that were maintained for up to 1 year and 6 months after the intervention, respectively. Future randomized trials are warranted to test Ascend as a scalable solution to the treatment of depression and anxiety.

BACKGROUND Depression is a very common condition that impairs functioning and is often untreated. More than 60% of the treatments for depressive disorder are administered in primary care settings by care providers who lack the time and expertise to treat depression. To address this issue, we developed Ascend, a therapist-supported, mobile phone–delivered 8-week intervention administered at the Meru Health Online Clinic in Finland. OBJECTIVE We conducted two pilot studies to examine the feasibility of the Ascend intervention, specifically, dropout rates, daily practice, weekly group chat use, and changes in depression symptoms. We also explored whether daily practice and weekly group chat use were associated with changes in depression symptoms. METHODS A total of 117 Finnish adults with elevated depressive symptoms enrolled in Ascend, a program that included daily cognitive behavioral and mindfulness meditation exercises delivered through a mobile phone app, anonymous group chat with other users, and chat/phone access to a licensed therapist. Eight weekly themes were delivered in a fixed, sequential format. Depression symptoms were measured at baseline, every second week during the intervention, immediately after the intervention, and 4 weeks after completion of the intervention. Data were analyzed using intent-to-treat repeated-measures analysis of variance and linear regression models. RESULTS For studies 1 and 2, we observed dropout rates of 27% and 15%, respectively, decreasing daily practice and group chat use, and decreased depression symptoms from baseline to immediately and 4 weeks after the intervention (P CONCLUSIONS This therapist-supported, mobile phone–delivered treatment for depression is feasible and associated with reduced depression symptoms. Design features that enhance daily practice and group chat use are areas of future investigation. Validation of these results using a controlled study design is needed to establish the evidence base for the Ascend intervention.