A recent study led by Sima Mofakham, PhD, and Chuck Mikell, MD, from the Renaissance School of Medicine at Stony Brook University, presents a new artificial intelligence tool that could change how clinicians assess consciousness in patients with traumatic brain injury (TBI). The research was published in Nature Communications Medicine.
Annually, many patients with brain injuries are labeled as "unresponsive" in hospitals throughout the United States. However, recent findings indicate that up to 25 percent of these individuals may actually be conscious but unable to demonstrate it physically—a condition known as cognitive motor dissociation (CMD).
To address this diagnostic challenge, Drs. Mofakham and Mikell developed SeeMe, an AI-based system designed to detect subtle facial movements that are not visible to the naked eye. According to their study, SeeMe can identify signs of awareness four-to-eight days earlier than standard clinical exams.
The development of SeeMe is partly a response to a 2024 study published in The New England Journal of Medicine by Bodien et al., which found that between 15 and 25 percent of ICU patients diagnosed as unresponsive might retain higher-level brain function undetectable by routine bedside tests. Such misdiagnoses can delay critical treatment and rehabilitation for those who have potential for recovery.
“We developed SeeMe to fill the gap between what patients can do and what clinicians can observe,” said Dr. Mofakham, who serves as Associate Professor and Vice Chair of Research for the Department of Neurosurgery and Assistant Professor in Electrical and Computer Engineering at Stony Brook University. “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 acute brain injury patients in coma, SeeMe used high-resolution video combined with computer vision technology to analyze involuntary facial responses when verbal commands were given. These subtle reactions—such as slight attempts to open eyes or smile—were captured using machine learning algorithms.
SeeMe detected purposeful movement up to four days before these actions were recognized by hospital staff in most cases studied.
“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 said.
Patients whose early responses were identified by SeeMe had a higher likelihood of regaining consciousness and experienced better functional outcomes upon discharge.
Dr. Mikell emphasized the importance for families: “This is not just a new diagnostic tool, it’s a potential prognostic marker,” he said. “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 Dr. Mikell. “We can use this information to personalize care, guide families, and optimize rehabilitation efforts.”
The authors also highlighted ethical concerns regarding TBI diagnosis: misclassifying patients as unresponsive could result in inappropriate withdrawal of care or missed opportunities for therapy.
The Bodien et al. study called attention to the need for objective bedside tools capable of detecting CMD without expensive imaging or invasive methods; SeeMe fits this need because it is noninvasive and cost-effective—it requires only a camera paired with open-source software—making it accessible even in resource-limited settings.
As larger clinical trials are planned and regulatory review pursued, researchers hope SeeMe will become part of standard intensive care practice alongside EEG monitoring and other assessment methods.
Funding came from several institutional seed grants supporting collaboration between Stony Brook University’s Departments of Neurosurgery and Electrical & Computer Engineering.
For additional information about neuroscience research on consciousness at RSOM: