Stanford Psychiatry awarded grant for research to combine artificial intelligence with direct recordings from inside the brain to identify various human mood states
February 5, 2024
We are pleased to announce that Stanford Psychiatry’s Corey Keller, Assistant Professor of Psychiatry and Behavioral Sciences, has received a grant from the National Institute of Mental Health to research the behavioral and neuronal correlates of human mood states. Dr. Keller is joined by co-principal investigator Josef Parvizi, Professor of Neurology and, by courtesy, of Neurosurgery, at Stanford University School of Medicine. The study team also includes co-investigators, Scott Linderman, Assistant Professor of Statistics and, by courtesy, Electrical Engineering and Computer Science at Stanford University, and Yuhao (Danny) Huang, resident in the Department of Neurosurgery at Stanford.
Current standard-of-care clinical scales present several challenges — including recency bias and underutilization — and they are not validated for acute mood monitoring. Easy to obtain, continuous, and objective measures of internal mood are required to optimize mental health treatments — especially in the context of the ongoing shift to remote care.
The study team hypothesizes that video-derived audio-facial behaviors have discrete neural representations in the limbic network and can provide a critical set of reliable longitudinal estimates of mood at low cost across home and clinic settings. Using simultaneous video-derived audio-facial features, invasive brain recordings, and frequent assessments of mood, they will build a longitudinal mood prediction model, and identify neural correlates of audio-facial dynamics using synchronized intracranial EEG under spontaneous and task settings. They will also examine the causal influence of limbic activity on audio-facial features and internal mood.
“The result of this study is a mood-decoding model based on audio-facial behavioral features that are causally linked to limbic activity and mood. This model will allow for objective, passive, longitudinal, remotely-enabled, and low-resource measurements of internal mood,” write Dr. Keller and Dr. Parvizi. “Use of the model could significantly advance psychiatric care, from acute mood tracking to optimize rapidly-acting interventions such as psychedelics and neurostimulation, to longitudinal telehealth-enabled monitoring for suicide-risk monitoring, treatment-dose optimization, and relapse prediction. Across inpatient, outpatient, and at-home settings, this model can deliver important real-time mood and electrophysiological insights to both patients and providers.”
The overarching goal of Dr. Keller’s team In the Laboratory for Personalized Neurotherapeutics is to understand the fundamental principles of human brain plasticity and build trans-diagnostic real-time monitoring platforms for personalized neurotherapeutics. Recent publications related to this work include “Effects of transcranial magnetic stimulation on the human brain recorded with intracranial electrocorticography” published in Molecular Psychiatry and “Personalized Repetitive Transcranial Magnetic Stimulation for Depression” published in the journal Biological Psychiatry: Cognitive Neuroscience and Neuroimaging.
In Dr. Parvizi’s lab, The Laboratory of Behavioral and Cognitive Neuroscience, they examine the electrophysiological principles of human brain function. A publication related to this work, “Causal mapping of human brain function,” was recently published in the journal Nature Reviews Neuroscience.