Analysis of Weekly Narratives Using Natural Language Processing in Patients Undergoing Residential Rehabilitation: A Hybrid Approach for the Dynamic Assessment of Clinical Processes

What this Trial Is About

This research follows adult men undergoing residential rehabilitation for severe substance use disorders at a specialized center in Mexico. It aims to analyze weekly written narratives and biweekly psychological questionnaires to identify emotional, cognitive, and behavioral patterns linked to clinical changes during treatment. The study uses natural language processing and machine learning to develop a dynamic representation of clinical risk that may help detect early signs of psychological worsening or improvement. Participants receive the center's standard residential rehabilitation program, which includes group therapy, individual counseling, occupational activities, 12-step facilitation, and relapse prevention education. They provide weekly written narratives in Spanish and complete validated self-report instruments every two weeks, including the Generalized Anxiety Disorder-7, Environmental Reward Observation Scale, Automatic Thoughts Questionnaire-8, and Behavioral Activation for Depression Scale. Data collection continues for up to 20 weeks during their residential stay. Throughout the study, participants' narratives and questionnaire responses are collected digitally as part of routine monitoring. Researchers evaluate changes in negative automatic thoughts as the primary outcome, along with anxiety symptoms, environmental reward, behavioral activation, emotional intensity, and craving intensity. The study monitors participants for up to 20 weeks and uses advanced machine learning models to analyze longitudinal data while participants continue standard care without treatment modifications.

NLP Analysis of Weekly Narratives for Dynamic Clinical Assessment in SUD