GenAI-DBT: Evaluating a DBT-Informed Generative AI Platform for Mindfulness Skills Training: A Pilot Randomized Study
Jingchen Ye, Yujia Chen, Leyang Han, Siyuan Wang, Mark Zachary Rosenthal, Yucheng Jin
Abstract
We evaluated the feasibility, acceptability, and engagement of three digital formats for dialectical behavior therapy (DBT) mindfulness skills training. In a 30-day randomized pilot study, 45 university students were assigned to GenAI-DBT, a general-purpose large language model chatbot (Chatbot), or a static web resource (Web). Forty-two completed the study, and nine completed follow-up interviews. Usability scores were within acceptable ranges across conditions, with no significant between-group differences. GenAI-DBT showed the highest observed participant-week adherence (71.4%, vs. 53.3% for Web and 42.3% for Chatbot), a descriptive difference. Mindful Attention Awareness Scale and Difficulties in Emotion Regulation Scale scores showed no significant time-by-group interactions, and session-level self-reported mood changes did not differ significantly across conditions. GenAI-DBT showed a larger positive change in linguistic valence than Chatbot (4.28 vs. 1.59, P = .02, Cohen's d = 0.99). Interviewees valued contextualized, scenario-based practice and identified response latency, repetition, and limited personalization as areas for improvement. The findings support the feasibility and acceptability of DBT-informed conversational AI for skills practice and motivate further evaluation in larger, more clinically relevant samples. Clinical efficacy remains to be established.
Create a lesson
Related papers
Introducing ReTiNA-Cinema: Real-Time Neuro-Augmented Cinema via Generative AI
Antoine Bellemare-Pepin, Philipp Thölke, Yann Harel et al.
Rethinking Utility in Differentially Private Visualization: A Channel-Centric Perspective
Jing Yang, Sarayu Pacca, Zhaocong Yang et al.
Presenting Your Figures: Data-informed Animated Transitions Across Scientific Figure Panels
Lu Ying, Can Liu, Yuxiao Yang et al.
Ground Truth Bias in AI-Assisted Medical Annotation: A Crossover Study Using an Independent Radiologist Reference Standard
Márton Baltay, Tamás Ilcsik, Márton Borbély
Embodied Human-Data Interaction
Niklas Elmqvist
From Reliance to Overreliance: Taxonomizing and Detecting Relational Risks in AI Companionship
Viet Cuong Nguyen, Fiona Li, Chang Wan et al.