JMIR Publications

ABSTRACT

Background:

Mental health providers face a significant administrative burden from documentation, which can contribute to burnout and reduce time spent on direct patient care. Although AI-powered scribes have shown promise in general medical settings, their utility has not been explored in the specific context of mental healthcare.

Objective:

This study describes the development and a preliminary evaluation of Talkspace's Smart Notes, a generative AI tool designed to assist mental health providers with documentation.

Methods:

Smart Notes was developed using a HIPAA-compliant, Azure OpenAI infrastructure to securely generate session summaries from individual therapy sessions. The tool was rolled out to Talkspace providers in a phased approach, and its use required provider and client consent as well as a mandatory review and edit by the provider. We conducted a one-year evaluation of the feature, examining provider usage, productivity (weekly working hours and session completion rates), provider-rated note quality, and provider feedback and satisfaction.

Results:

Over one year, 162 full-time and 1,366 contract providers used Smart Notes to generate over 286,000 clinical notes. Use of the feature was high and stable, with nearly all full-time providers (94%) and a majority of contract providers (72%) using it weekly for eligible individual therapy sessions after the full launch. Both full-time and contract providers demonstrated a significant increase in weekly sessions completed after the introduction of Smart Notes, with no change in working hours. Provider-rated note quality was overwhelmingly positive, with over 98% of feedback ratings being a "thumbs up." An internal audit of a random sample of notes confirmed the positive impact on note quality. Qualitative feedback from providers was also largely positive, praising the tool for saving time and easing administrative burden.

Conclusions:

Our findings suggest that AI-powered documentation tools, such as Smart Notes, are a feasible and effective solution for addressing the documentation burden faced by mental health providers. The high adoption rate, positive impact on productivity, and strong provider feedback indicate that such tools can enhance clinical efficiency and support provider well-being without compromising note quality. This study provides crucial preliminary evidence for the utility of AI in a previously unexamined mental healthcare context, highlighting a promising path for future research and development in digital mental health.