Breakthrough Technology Study Sheds Light on Consciousness and Recovery After Brain Injury

Findings could trigger more personalized prognosis and targeted treatments

STONY BROOK, NY, September 9, 2025 - A new study published in Nature Communications Medicine led by neurosurgery researchers Sima Mofakham, PhD, and Chuck Mikell, MD, of the Renaissance School of Medicine (RSOM) at Stony Brook University, provides clinicians with data about the path to consciousness after traumatic brain injury (TBI) that may help pave the way for more personalized and effective patient care strategies in critical care and rehabilitation settings.

Every year, thousands of brain-injured patients are labeled as "unresponsive" in hospitals across the United States. Yet new research reveals that up to one quarter of these individuals may be conscious but just unable to show it. This disconnect, known as cognitive motor dissociation (CMD), represents one of the most urgent diagnostic blind spots in neurology and critical care.

To address this problem, Drs. Mofakham and Mikell developed a first-of-its-kind artificial intelligence (AI) tool called SeeMe, which detects signs of covert consciousness by analyzing microscopic facial movements invisible to the naked eye. Their findings suggest that SeeMe can identify signs of awareness four-to-eight days earlier than traditional clinical exams.

An illustration of SeeMe in a clinical setting: The platform implements computer vision to detect and assess patients' responsiveness to commands such as "open your eyes." Then it performs a statistical analysis to determine whether responses were followed by the patient or not. SeeMe is designed as a high-resolution, quantitative tool that is an objective measurement of the level of patient consciousness.
Credit: Sima Mofakham

The work directly addresses the central dilemma outlined in a landmark 2024 study in The New England Journal of Medicine by Bodien et al., which found that 15 to 25 percent of patients diagnosed as unresponsive in the intensive care unit (ICU) may retain high-level brain function, but standard bedside tests are not sensitive enough to detect it. This misdiagnosis delays treatment and rehabilitation for patients who may otherwise recover.

"We developed SeeMe to fill the gap between what patients can do and what clinicians can observe," says Dr. Mofakham, senior author of the study, Associate Professor and Vice Chair of Research for the Department of Neurosurgery, and an Assistant Professor in the Department of Electrical and Computer Engineering. "Just because someone can't move their limbs or speak doesn't mean they aren't conscious. Our tool uncovers those hidden physical efforts by patients to show they are conscious."

In a clinical study of 37 patients with acute brain injury and coma, SeeMe used high-resolution video and computer vision to measure involuntary facial reactions to verbal commands like "open your eyes" or "show me a smile." These subtle responses, typically undetectable by doctors or nurses, were recorded and analyzed using machine learning.

In most of this patient cohort, SeeMe detected purposeful movement up to four days before the clinical care team recognized physical movements by the patients.

"This kind of work shows the future of medicine lies at the intersection of disciplines, as we begin to see more applications of AI and engineering in medicine. With such an approach, we aim to turn complex data into tools that can help doctors make faster and better decisions for patients when every hour counts," Dr. Mofakham emphasizes.

Additionally, the patients from the study with early SeeMe-detected responses were significantly more likely to regain consciousness and show better functional outcomes at discharge.

An AI tool for the future of TBI clinical care

"This is not just a new diagnostic tool, it's a potential prognostic marker," says Dr. Mikell, neurosurgeon, co-lead investigator, and Clinical Associate Professor and Vice Chair for the Department of Neurosurgery.

"Families often ask us how long it will take for a loved one to wake up, or if they ever will. This study helps us answer those questions with more confidence, grounded in data, not just experience or instinct," explains Dr. Mikell, "We can use this information to personalize care, guide families, and optimize rehabilitation efforts."

The authors also suggest the ethical implications are profound with TBI patients and recovery. Misdiagnosis of unresponsive states can lead to inappropriate withdrawal of care, limited access to neurorehabilitation and missed windows for therapy.

The Bodien et al. study stressed the urgent need for objective tools to detect CMD at the bedside, tools that don't require expensive imaging or invasive procedures. SeeMe is one solution as it is noninvasive, inexpensive, and scalable, according to Drs. Mofakham and Mikell. The system requires only a camera and open-source software, making it viable even in resource-constrained hospitals and ICUs.

As SeeMe moves toward larger clinical trials and potential regulatory approval, the research team envisions integrating the tool into standard ICU practice, combining it with EEG and other data streams to create a multi-modal consciousness monitoring platform. They also believe that SeeMe stands as a powerful example of how AI can restore independence to patients by letting them speak without words.

The work for both studies was funded by multiple institutional seed grants that support the ongoing collaboration between the Departments of Neurosurgery and Electrical and Computer Engineering at Stony Brook University.

For more about the broader neuroscience research conducted on consciousness at the RSOM, see this link to the Mofakham Mikell Laboratory.