Key points are not available for this paper at this time.
BACKGROUND Limited access to quality mental health treatment harms health and quality of life while costing individuals and organizations millions in increased medical spending and reduced productivity at work. Too few qualified professionals, inconsistent quality, inaccessibility, and stigma thwart traditional solutions. Innovations must be scalable, science-based, and timely. OBJECTIVE Limited access to quality mental health treatment harms health and quality of life while costing individuals and organizations millions in increased medical spending and reduced productivity at work. Too few qualified professionals, inconsistent quality, inaccessibility, and stigma thwart traditional solutions. Innovations must be scalable, science-based, and timely. METHODS We report analysis of coaches' response times to member messages, sentiment shift negative or positive (-1 to +1), machine learning-identified conversation topics, motivational interviewing adherence, and pre-post reductions in member-reported unhealthy days, distress, and presenteeism. The sample consisted of 38 members over a 4-month period who had at least four conversations over a minimum of 14 days. The results describe the innovative solution and illustrate the value delivered to members and organizations. RESULTS Data reported includes response time (median 95%), as well as pre-post reductions in unhealthy days (25%), and presenteeism (23%). CONCLUSIONS There are opportunities to utilize this emerging model of mental health care to address problems associated with traditional models that make them difficult to access and resource-heavy. This study provides data that describes and demonstrates a proof of concept for an innovative technology-enabled service that addresses the problems of scalability, access, quality, and stigma that have long challenged traditional mental health services. CLINICALTRIAL N/A
Wilbourne et al. (Fri,) studied this question.