New Delhi: A new smartphone application may come in handy for paramedics as it will detect in a matter of seconds whether a patient has suffered a stroke or not.
The developers of the device, which has an accuracy of 82 percent, said it uses artificial intelligence (AI) to analyze facial symmetry and muscle movements to detect strokes.
He said signs that a person has had a stroke can include confusion, loss of control over muscle movement, impaired speech and decreased facial expressions.
The research team shared testing results of the application in a study, which was published in the journal Computer Methods and Programs in Biomedicine.
Lead author Guilherme Camargo de Oliveira, of the Royal Melbourne Institute of Medical Sciences, said: "One of the key parameters that affects people who have had a stroke is that their facial muscles typically become unilateral, so one sided facial movement. It is different from the other side." Technology (RMIT), Australia.
"We've got (AI) tools and image processing tools that can detect if there's a change in the asymmetry of the smile - that's the key to detection in our case," de Oliveira said.
According to the researchers, the smartphone tool has an accuracy rating of 82 percent for detecting strokes, a success rate that compares favorably to that of paramedics.
For the study, the team used video recordings of facial expressions of 14 people who had suffered a stroke and 11 healthy individuals.
Researchers said early detection of stroke is important as timely treatment reduces the risk of long-term disability and saves lives.Although the newly developed tool will not replace extensive clinical diagnostic tests for stroke, he said, it could help identify people who need treatment sooner.
"Studies indicate that approximately 13 per cent of strokes are missed in emergency departments and community hospitals, while 65 per cent of patients experience undiagnosed strokes without any documented neurological examination," said corresponding author and Professor Dinesh Kumar of RMIT.
“The rate may be even higher in smaller regional centres."Given that many strokes occur at home and initial care is often provided by first responders in non-ideal circumstances, there is an urgent need for real-time, user-friendly diagnostic tools," Kumar said.
The developers of the device, which has an accuracy of 82 percent, said it uses artificial intelligence (AI) to analyze facial symmetry and muscle movements to detect strokes.
He said signs that a person has had a stroke can include confusion, loss of control over muscle movement, impaired speech and decreased facial expressions.
The research team shared testing results of the application in a study, which was published in the journal Computer Methods and Programs in Biomedicine.
Lead author Guilherme Camargo de Oliveira, of the Royal Melbourne Institute of Medical Sciences, said: "One of the key parameters that affects people who have had a stroke is that their facial muscles typically become unilateral, so one sided facial movement. It is different from the other side." Technology (RMIT), Australia.
"We've got (AI) tools and image processing tools that can detect if there's a change in the asymmetry of the smile - that's the key to detection in our case," de Oliveira said.
According to the researchers, the smartphone tool has an accuracy rating of 82 percent for detecting strokes, a success rate that compares favorably to that of paramedics.
For the study, the team used video recordings of facial expressions of 14 people who had suffered a stroke and 11 healthy individuals.
Researchers said early detection of stroke is important as timely treatment reduces the risk of long-term disability and saves lives.Although the newly developed tool will not replace extensive clinical diagnostic tests for stroke, he said, it could help identify people who need treatment sooner.
"Studies indicate that approximately 13 per cent of strokes are missed in emergency departments and community hospitals, while 65 per cent of patients experience undiagnosed strokes without any documented neurological examination," said corresponding author and Professor Dinesh Kumar of RMIT.
“The rate may be even higher in smaller regional centres."Given that many strokes occur at home and initial care is often provided by first responders in non-ideal circumstances, there is an urgent need for real-time, user-friendly diagnostic tools," Kumar said.
