A recent study published in Nature Communications Medicine, led by Sima Mofakham and Chuck Mikell, MD, from the Renaissance School of Medicine at Stony Brook University, offers new data on how patients regain consciousness after traumatic brain injury (TBI). The findings could help clinicians provide more tailored care for brain-injured patients.
Each year, many patients with severe brain injuries are classified as “unresponsive” in hospitals across the United States. However, research indicates that up to a quarter of these individuals may be conscious but unable to physically show it. This issue is known as cognitive motor dissociation (CMD) and is considered a significant diagnostic challenge in neurology and critical care.
To address this gap, Mofakham and Mikell developed an artificial intelligence tool called SeeMe. The system detects signs of covert consciousness by analyzing tiny facial movements that cannot be seen by the naked eye. According to their research, SeeMe can identify awareness in patients four to eight days earlier than standard clinical exams.
The study builds on previous work published in The New England Journal of Medicine by Bodien et al., which reported that 15 to 25 percent of ICU patients diagnosed as unresponsive may actually have high-level brain function undetected by current bedside tests. This misdiagnosis can delay necessary treatment and rehabilitation for those who might otherwise recover.
“We developed SeeMe to fill the gap between what patients can do and what clinicians can observe,” said Mofakham, senior author of the study, associate professor and vice chair of research for the Department of Neurosurgery, and assistant professor in the Department of Electrical and Computer Engineering in the College of Engineering and Applied Sciences. “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 trial involving 37 coma patients with acute brain injury, SeeMe used high-resolution video along with computer vision technology to measure involuntary facial reactions when given verbal commands such as “open your eyes” or “show me a smile.” These subtle responses were analyzed using machine learning techniques.
SeeMe was able to detect purposeful movement up to four days before medical staff noticed any physical response from most patients in the study group.
“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,” Mofakham said.
Patients whose early responses were detected by SeeMe were also more likely to regain consciousness and achieve better functional outcomes upon discharge.
“This is not just a new diagnostic tool, it’s a potential prognostic marker,” said 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,” explained Mikell. “We can use this information to personalize care, guide families, and optimize rehabilitation efforts.”
The authors highlight ethical concerns related to TBI patient recovery. Incorrectly diagnosing someone as unresponsive could lead to premature withdrawal of care or missed opportunities for therapy.
The Bodien et al. study emphasized an urgent need for objective bedside tools that do not require expensive imaging or invasive procedures. According to Mofakham and Mikell, SeeMe addresses this need since it is noninvasive, cost-effective, scalable, requires only a camera and open-source software—making it suitable even for hospitals with limited resources.
As development continues toward larger clinical trials and possible regulatory approval for SeeMe, researchers plan its integration into routine ICU practice alongside EEGs and other monitoring methods. They believe tools like SeeMe demonstrate how AI can give voice back to patients who cannot communicate through traditional means.
Funding for this research came from institutional seed grants supporting collaboration between Stony Brook University’s Departments of Neurosurgery and Electrical & Computer Engineering.
