A facial scanner for mobile phones that could help doctors detect strokes in seconds. Biomedical engineers from RMIT University (Royal Melbourne Institute of Technology) and São Paulo State University have developed this software powered by artificial intelligence. As described, this method significantly exceeds the sensitivity and speed of current technologies.

The study was led by researcher Guilherme Camargo de Oliveira from RMIT University and São Paulo State University, under the supervision of team leader Professor Dinesh Kumar.

“Early detection of stroke is crucial, as prompt treatment can significantly improve recovery outcomes, reduce the risk of long-term disability and save lives.”

The main purpose of the tool is to detect early whether the patient is in the post-stroke stage in order to provide information as quickly as possible.

According to them, the tool has an 82% accuracy rate in detecting strokes, although it was by no means developed to replace full diagnostic tests.

How to get there? With facial recognition and artificial intelligence algorithms. Researchers highlight the difficulty in detecting strokes, as sometimes the symptoms are very subtle. The models analyzed by this tool are related to the recognition of facial expressions, facial symmetry and the analysis of specific muscle movements known as action units.

First developed in the 1970s, the Facial Action Coding System (FACS) provides a detailed framework for analyzing facial expressions by classifying facial movements based on the contraction or relaxation of facial muscles.

“One of the main parameters that affects people who have had a stroke is that the facial muscles often become unilateral, so one side of the face behaves differently from the other.”

The goal is to develop an app for mobile phones that can detect not only these patterns but also other neurological conditions that affect facial expression (which is key to making the tool even more sensitive).

Image | RMIT University

At Xataka | Your Fitbit will talk to you. Google is improving its AI to focus on health