Adversarial AI reveals mechanisms and treatments for disorders of consciousness.
Authors
Affiliations (20)
Affiliations (20)
- Department of Neurology, University of California, Los Angeles, Los Angeles, CA, USA. [email protected].
- Department of Psychology, University of California, Los Angeles, Los Angeles, CA, USA. [email protected].
- Research Institute, Casa Colina Hospital and Centers for Healthcare, Pomona, CA, USA.
- Department of Neurosurgery, Heersink School of Medicine, University of Alabama at Birmingham, Birmingham, AL, USA.
- Edmond and Lily Safra Center for Brain Sciences, The Hebrew University of Jerusalem, Jerusalem, Israel.
- Coma Science Group, GIGA-Research, University of Liège, Liège, Belgium.
- Department of Data Analysis, University of Ghent, Ghent, Belgium.
- Laboratory for Neurogenetics, RIKEN Center for Brain Science, Saitama, Japan.
- PRESTO, Japan Science and Technology Agency, Saitama, Japan.
- International Research Center for Neurointelligence, University of Tokyo, Tokyo, Japan.
- Department of Neurodevelopmental Disorder Genetics, Institute of Brain Science, Nagoya City University Graduate School of Medical Science, Nagoya, Japan.
- Brain Injury Research Center, Department of Neurosurgery, University of California, Los Angeles, Los Angeles, CA, USA.
- CERVO Brain Research Centre, Laval University and CIUSSS-CN, Quebec, Quebec, Canada.
- Joint International Research Unit on Neuroplasticity, University of Liège, Liège, Belgium.
- Anesthesia, Critical Care and Pain Medicine Research, Harvard Medical School, Beth Israel Deaconess Medical Center, Boston, MA, USA.
- European Foundation of Biomedical Research FERB Onlus, Milan, Italy.
- Department of Anesthesiology, Veterans Affairs Greater Los Angeles Healthcare System, Los Angeles, CA, USA.
- Department of Anesthesiology and Perioperative Medicine, University of California, Los Angeles, Los Angeles, CA, USA.
- Department of Neurological Surgery, UT Southwestern Medical Center, Dallas, TX, USA.
- Department of Psychology, University of California, Los Angeles, Los Angeles, CA, USA.
Abstract
Understanding disorders of consciousness (DOC) remains one of the most challenging problems in neuroscience, hindered by the lack of experimental models for probing mechanisms or testing interventions. Here, to address this, we introduce a generative adversarial artificial intelligence (AI) framework that pits deep neural networks-trained to detect consciousness across more than 680,000 ten-second neuroelectrophysiology samples and validated on 565 patients, healthy volunteers and animals-against interpretable, machine learning-driven neural field models. This adversarial architecture produces biologically realistic simulations of both conscious and comatose brains that recapitulate empirical neurophysiological features across humans, monkeys, rats and bats. Without explicit programming, the AI model retrodicts known DOC responses to brain stimulation and generates testable predictions about the mechanisms of unconsciousness. Two such predictions are validated here: selective disruption of the basal ganglia indirect pathway, supported by diffusion magnetic resonance imaging in 51 patients with DOC, and increased cortical inhibitory-to-inhibitory synaptic coupling, supported by RNA sequencing of resected brain tissue from 6 human patients with coma and a rat stroke model. The model also identifies high-frequency stimulation of the subthalamic nucleus as a promising intervention for DOC, supported by electrophysiological data from human patients. This work introduces an AI framework for causal inference and therapeutic discovery in consciousness research, as well as in complex systems more broadly.