Scientists Develop Facial Recognition Tool to Detect Stroke
MarkNtel Advisors - Market Research Company
MarkNtel Advisors| Market Research Company | Syndicate & Custom Research | Consulting Services
Paramedics may find new smartphone software useful since it can quickly determine whether a patient has had a stroke. The tool's creators claimed that its 82% accuracy rate comes from its usage of artificial intelligence (AI) to analyze facial symmetry and muscular movements to identify strokes.
According to them, disorientation, lack of control over muscular movement, trouble speaking, and a reduction in facial expressions are all indicators that someone may have had a stroke.?The trial findings of the application were presented by the research team in a report that was published in the Computer Methods and Programs in Biomedicine journal.
“One of the main characteristics of stroke victims is that their facial muscles usually become unilateral, resulting in the behavior of one side of the face being different from the other,” said lead author Guilherme Camargo de Oliveira from the Royal Melbourne Institute of Technology (RMIT), Australia.
“The key to detection in our situation is that we have the image processing and artificial intelligence technologies to determine whether the asymmetry of the grin has changed,” said de Oliveira.
领英推荐
The researchers found that the smartphone tool had an 82% accuracy rating for identifying strokes, which is a success rate that is comparable to paramedics. The researchers used video recordings of the facial expressions of 11 healthy individuals and 14 stroke survivors for the study. According to the researchers, early diagnosis of stroke is essential since prompt treatment lowers the chance of long-term impairment and saves lives.
“Research shows that around 13% of strokes go undetected in emergency rooms and community hospitals and that undiagnosed strokes affect 65% of patients who do not have a recorded neurological assessment,” said corresponding author Dinesh Kumar, a professor at 澳大利亚皇家墨尔本理工大学 .
“In smaller regional centers, this rate may be considerably higher. Real-time, user-friendly diagnostic technologies are desperately needed, as many strokes happen at home and first responders frequently offer initial care in non-ideal conditions,” said Kumar.