Acceptability and Effectiveness of Artificial Intelligence Therapy for Anxiety and Depression (Youper): Longitudinal Observational Study

Abstract

Background Youper is a widely used, commercially available mobile app that uses artificial intelligence therapy for the treatment of anxiety and depression. Objective Our study examined the acceptability and effectiveness of Youper. Further, we tested the cumulative regulation hypothesis, which posits that cumulative emotion regulation successes with repeated intervention engagement will predict longer-term anxiety and depression symptom reduction. Methods We examined data from paying Youper users (N=4517) who allowed their data to be used for research. To characterize the acceptability of Youper, we asked users to rate the app on a 5-star scale and measured retention statistics for users’ first 4 weeks of subscription. To examine effectiveness, we examined longitudinal measures of anxiety and depression symptoms. To test the cumulative regulation hypothesis, we used the proportion of successful emotion regulation attempts to predict symptom reduction. Results Youper users rated the app highly (mean 4.36 stars, SD 0.84), and 42.66% (1927/4517) of users were retained by week 4. Symptoms decreased in the first 2 weeks of app use (anxiety: d=0.57; depression: d=0.46). Anxiety improvements were maintained in the subsequent 2 weeks, but depression symptoms increased slightly with a very small effect size (d=0.05). A higher proportion of successful emotion regulation attempts significantly predicted greater anxiety and depression symptom reduction. Conclusions Youper is a low-cost, completely self-guided treatment that is accessible to users who may not otherwise access mental health care. Our findings demonstrate the acceptability and effectiveness of Youper as a treatment for anxiety and depression symptoms and support continued study of Youper in a randomized clinical trial.

Efficacy and Conflicts of Interest in Randomized Controlled Trials Evaluating Headspace and Calm Apps: Systematic Review

“…In contrast, when apps are used in naturalistic settings, users are free to choose the content that they want to access. Additionally, engagement with apps tends to be higher in trials, as investigators can promote engagement through financial incentives, and participants in research trials may feel committed to participating fully in the study [ 44 ]. Thus, findings from randomized trials may not fully generalize to app usage in real-world settings.…”

Digital Mental Health Amid COVID-19

“…Rapid psychological screening and tracking showed promise during COVID-19 through digital phenotyping of a telehealth platform service coupled with analysis by machine learning trained models [46]. A longitudinal observational study verified the acceptability and effectiveness of AI therapy for anxiety and depression [49]. A systematic review of the effectiveness and acceptance of technology-based psychological interventions in people with diagnosed depression found mostly positive impacts from stand-alone interventions, blended treatments, or in collaborative care trials [50].…”

Mental Health Intent Recognition for Arabic-Speaking Patients Using the Mini International Neuropsychiatric Interview (MINI) and BERT Model

“…Youper [ 22 ] is a chatbot software developed in 2016 as an AI tool to help users recognize, monitor, and process their emotions and thoughts. Cognitive behavioral therapy (CBT), recognition and engagement therapy (ACT), and mindfulness can enhance mood and sleep habits and alleviate anxiety, stress, and depression symptoms.…”