RecruitingNot ApplicableNCT07189715

Optimization of Imagery Rescripting Research Using Generative Artificial Intelligence

A Randomized Controlled Pilot Study on AI-Based Imagery Rescripting for Childhood Criticism Memories

Sponsor

University of Social Sciences and Humanities, Warsaw

Enrollment

80 participants

Start Date

Jun 1, 2025

Study Type

INTERVENTIONAL

Conditions

Rumination Generalized Anxiety Fear of Failure

Summary

This pilot randomized controlled trial will investigate the feasibility and effectiveness of using generative artificial intelligence to create personalized therapeutic scripts for imagery rescripting (ImRs). Eighty participants will listen to autobiographical scenarios based on their own memories of childhood criticism and neutral events. The scenarios will be generated by the Gemini large language model and reviewed by trained experimenters. On Day 1, all participants will be exposed to both critical and neutral scenarios and randomly assigned to either an experimental group receiving an ImRs intervention or a control group receiving no therapeutic modification. Skin conductance and subjective emotional ratings will be collected during the session, with follow-up questionnaires administered one week later. In addition, cognitive-behavioral therapists will evaluate the quality of the generated scripts. The study aims to assess emotional and physiological responses to AI-generated content, compare outcomes between groups, and explore the potential of large language models in scalable psychological interventions.

Eligibility

Min Age: 18 YearsMax Age: 35 Years

Inclusion Criteria3

Age 18-35
Score ≥ 8 on GAD-7 (Plummer et al., 2016)
Ability to recall at least two childhood memories involving parental criticism

Exclusion Criteria4

History of prolonged physical or sexual abuse
Current psychotherapy or psychopharmacology
PTSD diagnosis (DSM-5 screening)
Substance abuse (TAPS tool)

Interventions

BEHAVIORALImagery Rescripting Intervention (AI-Generated)

Participants listened to a series of personalized audio scenarios based on their childhood memories of parental criticism and neutral events. At the end of the session, one critical scenario was presented in a modified version that included a therapeutic imagery rescripting (ImRs) intervention. In this script, a therapist figure entered the scene and addressed the child's unmet needs, following the standard rescripting format. The scripts were generated using the Gemini large language model and reviewed by trained experimenters to ensure coherence and therapeutic validity. The intervention aimed to reduce distress and intrusive thoughts related to the memory.