BI 218 Chris Rozell: Brain Stimulation and AI for Mental Disorders

20 snips

Aug 13, 2025

Chris Rozell leads the Structured Information for Precision Neuroengineering Lab at Georgia Tech and is the inaugural director of the Institute for Neuroscience, Neurotechnology, and Society. He discusses groundbreaking methods using deep brain stimulation and AI to treat treatment-resistant depression. Chris highlights how neural signals can predict treatment effectiveness and the importance of personalized care in mental health. Their conversation delves into the evolving techniques in neuromodulation and the necessity of interdisciplinary research to enhance future therapies.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

INSIGHT

Objective Measures To Support Psychiatry

Psychiatry lacks objective biomarkers that clinicians can trust in real time.
Rozell stresses that objective brain measures could supplement clinicians' judgment and inform treatment adjustments.

ADVICE

Favor Human-In-The-Loop For Slow Recoveries

Use slow, human-in-the-loop adjustments rather than immediate automatic changes when disease recovery is slow.
Provide clinicians with decision support tools before attempting fully autonomous closed-loop DBS.

INSIGHT

Short-Term Effects Differ From Long-Term Recovery

Acute electrophysiological effects of stimulation can differ from long-term recovery signatures.
Longitudinal recordings revealed an initial beta suppression followed by beta increases that correlate with stable recovery.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

Support the show to get full episodes, full archive, and join the Discord community.

We are in an exciting time in the cross-fertilization of the neurotech industry and the cognitive sciences. My guest today is Chris Rozell, who sits in that space that connects neurotech and brain research. Chris runs the Structured Information for Precision Neuroengineering Lab at Georgia Tech University, and he was just named the inaugural director of Georgia Tech’s Institute for Neuroscience, Neurotechnology, and Society. I think this is the first time on brain inspired we've discussed stimulating brains to treat mental disorders. I think. Today we talk about Chris's work establishing a biomarker from brain recordings of patients with treatment resistant depression, a specific form of depression. These are patients who have deep brain stimulation electrodes implanted in an effort to treat their depression. Chris and his team used that stimulation in conjunction with brain recordings and machine learning tools to predict how effective the treatment will be under what circumstances, and so on, to help psychiatrists better treat their patients. We'll get into the details and surrounding issues. Toward the end we also talk about Chris's unique background and path and approach, and why he thinks interdisciplinary research is so important. He's one of the most genuinely well intentioned people I've met, and I hope you're inspired by his research and his story.

Structured Information for Precision Neuroengineering Lab.
Twitter: @crozSciTech.
Related papers
- Cingulate dynamics track depression recovery with deep brain stimulation.
Story Collider: Wired Lives

0:00 - Intro 3:20 - Overview of the study 17:11 - Closed and open loop stimulation 19:34 - Predicting recovery 28:45 - Control knob for treatment 39:04 - Historical and modern brain stimulation 49:07 - Treatment resistant depression 53:44 - Control nodes complex systems 1:01:06 - Explainable generative AI for a biomarker 1:16:40 - Where are we and what are the obstacles? 1:21:32 - Interface Neuro 1:24:55 - Why Chris cares

Read the transcript.