There is a technology to detect cases of multiple sclerosis. Just look 10 seconds at a “target”

The movement of our eyes can be a way of analyzing and detecting various diseases of the human being, namely neurological diseases. But now an American company C. Light Technologies wants to make it easier for doctors to make the task faster, with a technology that can be used to diagnose multiple sclerosis (MS).

As a neurological disease, MS has several effects on the body, with a huge impact on the patient. Disorders of vision and difficulties in locomotion and balance, even inability to control functions such as that of the intestines, are some consequences of the pathology, which is progressively disabling.

But how does the AI ​​company want to improve the diagnosis of this disease? With the system he developed, the goal is for patients to fix their eyes on a target point for ten seconds, while the technology records a video and predicts the person's neurological disorders. While other technologies observe the movement of the pupil, it analyzes the retina.

Now the company has more demanding goals for the future, wanting to diagnose other neurological diseases, such as Alzheimer's disease and amyotrophic lateral sclerosis, for example. Until then, the system can help doctors to diagnose MS more quickly or to assess the effects of a particular drug. The company's founder explains the importance of this system, cited by The Engadget.

"We use AI combined with eye tracking to create a fingerprint of neurological health, with unprecedented speed and sensitivity," says Zachary Helft.

Artificial intelligence has been used to improve the diagnosis of various diseases. But this month went even further, creating a drug to treat patients suffering from obsessive compulsive disorder and who will enter the clinical trials phase in March this year in Japan.

In the area of ​​breast cancer, the AI ​​system acquired by Google, DeepMind, has been able to detect breast cancers more accurately than medical teams. The technology has developed a model that has managed to reduce the number of false positive cases by 5.7% and false negative cases by 9.4%, during a test phase in some North American hospitals.