TherapyTrainer: Using AI to train therapists in written exposure therapy

Though evidence-based treatments are effective, existing dissemination efforts are expensive and difficult to scale. Novel solutions— especially those that offer active learning strategies, repeat skill practice and personalized feedback to therapists — are needed to fill this gap. To address this, we developed TherapyTrainer, which uses large language models (LLMs) to allow therapists to practice delivering written exposure therapy (WET) for PTSD to AI-Patients while receiving expert feedback from an AI-Consultant. Here present initial feasibility, acceptability, and usability data for TherapyTrainer gathered from therapists, supervisors, and WET experts across iterative rounds of development. In phase 1, we rapidly prototyped and developed TherapyTrainer in response to feedback from WET clinicians and experts (n = 4). In phase 2, mixed methods data from therapists who just completed a WET workshop (n = 14) indicated that the AI-Patient interactions felt realistic and increased therapists’ sense of being prepared to use WET with patients. In phase 3, therapists (n = 6) completed structured user testing interviews in order to identify key issues impacting usability for subsequent rounds of development. AI and large language models hold potential to provide ongoing support to therapists in a cost-effective and scalable manner in order to close the research-practice gap.