A team of biomedical engineers from RMIT University has created a New facial detection tool for smart phones that helps paramedics and emergency medical technicians identify a ictus in secondsThis tool represents a significant improvement over current technologies that can lead to faster and more accurate diagnoses.
Strokes, which affect millions of people worldwide, occur when the blood supply to a part of the brain is interrupted or reducedpreventing brain tissue from receiving oxygen and nutrients. Even a few minutes of delay can result in permanent damage to brain cells. In Spain alone, between 110,000 to 120,000 people suffer a stroke each yearof which 50% are left with disabling sequelae or die, according to the Spanish Society of Neurology.
The PhD researcher Guilherme Camargo de Oliveirafrom RMIT University and São Paulo State University, under the supervision of team leader Professor Dinesh Kumarhave led the research. “Early detection of stroke is critical, as Prompt treatment can significantly improve recovery outcomesreduce the risk of long-term disability and save lives,” Kumar said.
With a precision of 82% in stroke detection, the smartphone tool It is not intended to replace comprehensive clinical diagnostic testing.but it can help identify people who need treatment much sooner. “Our facial detection tool has a success rate in detecting strokes that compares favorably with that of paramedics“, Kumar says.
Stroke symptoms include confusion, partial or complete loss of movement control, speech problems and decreased facial expressions. According to Kumar, “Studies indicate that almost 13% of strokes are not detected in emergency departments and community hospitalswhile 65% of patients without a documented neurological examination experience an undiagnosed stroke.”
The team of biomedical engineers from RMIT University developed the artificial intelligence capabilities of this technology and has published its results in the journal Computer Methods and Programs in Biomedicine. This innovative tool uses the power of facial expression recognition to detect strokes by analyzing facial symmetry and specific muscle movementsknown as units of action.
He Facial Action Coding System (FACS)initially developed in the 1970s, categorizes facial movements by the contraction or relaxation of facial muscles, providing a detailed framework for analyzing facial expressions. “One of the key parameters that affects people with stroke is that their facial muscles typically become unilateral, so one side of the face behaves differently than the other side of the face”, says de Oliveira. “We have the AI tools and the image processing tools that can detect if there is any change in the asymmetry of the smilethat is key to detection in our case.”
The study used video recordings of facial expression examinations. 14 people with stroke and 11 healthy controlsThis facial detection tool has the potential to substantially improve initial medical response, especially in situations where time is of the essence.
The team plans to develop the tool for smartphones in an application in collaboration with healthcare providers so that it can detect other neurological conditions that affect facial expressions“We want to be as sensitive and specific as possible. We are now working towards an AI tool with additional data and where we will consider other diseases as well,” Kumar notes. Collaboration with healthcare providers will be crucial to integrate this application into existing emergency response protocols and provide healthcare teams with an effective means for early detection of stroke.