NCT07110688

Novel Multimodal Neural, Physiological, and Behavioral Sensing and Machine Learning for Mental States

• Status: Recruiting
• Phase: N/A
• Study type: Interventional
• Enrollment: 90 (estimated)
• Sponsor: University of Southern California · Academic / Other
• Sex: All
• Age: 18 Years
• Healthy volunteers: Accepted

Summary

In this program, the investigators will develop novel multimodal neural-behavioral-physiological monitoring tools (software and hardware), and machine learning models for mental states within social processes and beyond. The tools consist of a multimodal skin-like wearable sensor for physiological and biochemical sensing; a conversational virtual human platform to evoke naturalistic social processes; audiovisual affect recognition software; synchronization tools; and machine learning methods to model the multimodal data. The investigators will demonstrate the tools in healthy subjects without neural recordings and in patients with drug-resistant epilepsy who already have intracranial EEG (iEEG) electrodes implanted based on clinical criteria for standard monitoring to localize seizures, which is unrelated to our study.

Conditions

• No Condition
• Study Mental State in Healthy Populations and Drug-resistant Epilepsy Patients With Existing iEEG

Interventions

Type	Name	Description
BEHAVIORAL	Virtual human social interaction	The participants will perform a social interaction with the virtual human agent platform to assess mental states.
BEHAVIORAL	Cold pressor test	Healthy participants will immerse one hand in cold water for less than 3 minutes, while physiological data will be collected by the new wearable sensor from the other hand.

Timeline

• Start date: 2024-08-01
• Primary completion: 2028-11-30
• Completion: 2028-11-30
• First posted: 2025-08-07
• Last updated: 2025-10-01

Locations

2 sites across 1 country: United States