AI-guided digital intervention with physiological monitoring reduces intrusive memories after experimental trauma.

Abstract

Trauma prevalence is vast globally. Evidence-based digital treatments can help, but most require human guidance. Human guides provide tailored instructions and responsiveness to internal states, but limit scalability. Might generative AI and neurotechnology provide a scalable alternative? Here we provide a first test of ANTIDOTE, combining AI guidance and pupillometry to automatically deliver and monitor the Imagery Competing Task Intervention (ICTI). ICTI is a digital intervention developed by our group to reduce intrusive memories after psychological trauma, previously delivered with human guidance. One hundred healthy volunteers were exposed to videos of traumatic events and randomized to an intervention or active control condition. As predicted, intervention participants reported significantly fewer intrusive memories over the following week. Post hoc assessments confirmed the AI guide delivered the intervention successfully. Pupil size tracked intervention engagement and was associated with symptom reduction, providing a candidate biomarker. These findings suggest a path towards developing AI-guided digital interventions with scalability potential.