Using Data Science To Center Patient Perspectives in Mechanism Discovery

Including patient perspectives when developing new therapy interventions is crucial because it can help to understand response heterogeneity and promote engagement. Yet, analyzing patient interview data is difficult and time-consuming. This study aims to explore the potential for natural language processing and deep learning to analyze patient interviews and identify potential ways in which therapy leads to psychological change. This study will recruit participants from an existing clinical service that offers a 16-week online group therapy model (and adjunct individual therapy sessions) called Program for Alleviating and Resolving Trauma and Stress (PARTS) based on a therapy called Internal Family Systems (IFS). The investigators will use a mixed methods approach, applying natural language processing and deep learning to develop models that identify potential mechanisms of change. These models will be based on patient perspectives of psychological change, as expressed in interviews, and be compared to models based on clinical measures.

NCT Number	NCT06233968
Lead Sponsor	Cambridge Health Alliance Collaborators: Foundation for Self Leadership
Conditions	Posttraumatic Stress Disorder, Complex Post-Traumatic Stress Disorder
Enrollment	33 participants
Start Date	2024-03-19
Primary Completion	2025-05-05 (estimated)
Study Completion	2026-12-05 (estimated)
Updated on ClinicalTrials.gov	2025-06-25