Hypnosis-Based Machine Learning Biomarker Study

This study seeks to contribute to the growing body of literature on hypnosis by providing robust, data-driven insights into the physiological mechanisms underlying trance states. The integration of electroencephalogram (EEG) and other wearable-derived physiological data will offer a comprehensive assessment of the changes that occur during a standardized hypnosis protocol: the Harvard Group Scale of Hypnotic Susceptibility (HGSHS:A). The results of this study are intended to facilitate derivation and validation of an Artificial Intelligence/Machine Learning (AI/ML)-based monitor that quantifies a patient's instantaneous emotional/arousal state along the spectrum that spans anxiety through states of calmness and trance. Future investigations will explore the ability of using such an interactive virtual system as a component of a closed-loop adaptive device to create optimal states of non-pharmacological sedation using personalized audiovisual content to allay anxiety and discomfort during medical procedures, such as percutaneous biopsies.