The brilliant invention that uses a cell phone camera to identify strokes in seconds

Cell phones have become very useful tools in different sectors due to their versatility. Thanks to various applications and programs, they can be used for work or play, but also for be able to be used in more complex environments, such as in medical centers, as is the case in EuropeThe devices found in these places are extraordinarily advanced, sometimes more so than smartphones, but that doesn’t mean phones don’t have their place when it comes to improving patient care.

We have already seen many devices that use smartphones to be more precise, more comfortable or cheaper. Now we see how artificial intelligence is able to change the way research is conducted in certain scientific fields or the way certain medical procedures are performed.

This is a topic that has been worked on for several years, as evidenced by the news published in 2018. Now, a software tool created by RMIT University in Australia would allow facilitate the identification of a stroke, such as a cerebrovascular accident, within seconds

What is a stroke?

The brain is full of blood vessels that carry blood to all its areas. Their branching and small size mean that sometimes blood carries a clot or foreign object from the body to the brain, causing a blockage which causes the watering to stop.

This is called a stroke, even though commonly called stroke or apoplexy. They can also be the cause of a stroke, caused by an external or internal cause. Essentially, it is the same as a heart attack, only located in the brain.

The fact that it occurs in this organ makes the immediate consequences different from those of other obstructions. For example, It is common to notice sudden numbness or weakness in the face., especially in the mouth, as well as other parts of the body. It is also normal to feel confused and have difficulty speaking or understanding speech, as well as walk. This causes dizziness or loss of balance, as well as headache or blurred vision.

The importance of the brain makes it essential to detect this type of event quickly, ensuring that the time dur ing which this organ is without blood supply is as short as possible. A few minutes of delay can mean the difference between permanent damage or not.

Stroke detection

A team of biomedical engineers from RMIT University has been working on this very detection of brain infarctions. use artificial intelligence functions through softwarein a publication in which they explain the use of AI for this type of medical tasks. Professor Dinesh Kumar supervises this work, led by Guilherme Camargo de Oliveira, from RMIT and the State University of São Paulo.

The professor stressed the importance of this type of tools since “early detection of a stroke is essential, as timely treatment can significantly improve recovery outcomes, reduce the risk of long-term disability and save lives.” For this, it has been developed a mobile software tool that allows paramedics to instantly determine if a patient has suffered a stroke and inform the hospital before the ambulance leaves the patient’s home.

This app has an accuracy of 82%but it is not proposed as a replacement for current techniques, but rather as an easy-to-use supplement in the early moments of the incident. Being able to identify a stroke earlier can be essential for the patient, improving their chances of recovery. This percentage is higher than that of paramedics themselves when they have to assess at the very moment whether or not a patient has had a stroke.

“Studies indicate that nearly 13% of strokes go undetected in emergency departments and hospitals, while 65% of patients without a documented neurological examination experience an undiagnosed stroke,” said Professor Kumar. In addition, It should be taken into account that sometimes the race or gender of the patient can make it difficult to detect a stroke..

How AI works

The application, which can run on conventional mobile devices, allows facial detection to be used to detect strokes using the analysis of facial symmetry and specific muscle movementsso-called action units. The Facial Action Coding System (FACS) classifies facial movements by contraction or relaxation of facial muscles, providing a detailed framework for analyzing facial expressions.

This is the analysis framework that uses the application’s artificial intelligence to compare each patient’s cases and make a diagnosis. It focuses particularly on detecting smile asymmetryone of the most notable indicators that a person is suffering from a stroke. To evaluate the AI, video recordings of facial expression scans of stroke survivors and healthy people were used.

The team’s intention is to develop the smartphone tool into an application in collaboration with other healthcare providers so that can detect other neurological conditions that affect facial expressions. Collaboration with healthcare providers will be crucial to integrate this application into existing emergency response protocols.