The artificial intelligence that can detect Alzheimer’s, autism and more mental disorders

New research published in Nature Scientific Reports claims to have found a new method to detect mental disorders through the development of a artificial intelligence. Specialists can spot some mental illness trends much faster than today.

Today, the detection and diagnosis of mental disorders is a multi-step process. In fact, in countries like USAthe process is so slow that many patients they can wait up to two years for their first appointment with a psychiatrist who specializes in the field. However, this new study, led by members of Georgia State University, could change everything.

Sergey Plis, associate professor of computer science and neuroscience at Georgia State University, mentions that he has “built artificial intelligence models to interpret large amounts of information from magnetic resonance imaging (fMRI)”. In his statement, Plis says that while fMRIs are much more comprehensive tests than a traditional blood test or MRI, “The large amount of data is much more difficult to interpret.”

Also, they are not readily available and are often much more expensive than blood tests. However, thanks to the evolution of the AI ​​model, a big change may soon be seen. something very similar to the AI ​​that allows to detect breast cancer faster.

This is how this AI works to detect mental disorders

Artificial intelligence can recognize early features of disorders such as ASD (autism spectrum disorder), schizophrenia and Alzheimer’s disease. Of course, none of the three is preventable at this time (like ASD that appears even before a child is born), but the Early diagnosis is essential for effective treatment.

But how exactly does it work? This AI is formed from scans taken with an MRI. This allows a flexible measurement of brain activity, to show the changes in the blood flow of the organs.

To train it, a database with more than 10,000 human samples. This allows the AI ​​to capture the images provided by fMRI (a test in which images of the inside of the brain are generated using strong magnetic fields) and link them to brain function.

Similarly, the AI ​​was fed from a database with 1,200 samples from different patients who had any of the aforementioned disorders.

With all this information, the AI ​​can detect certain patterns in the behavior of the brains of patients with characteristics of these mental disorders. Also, can pinpoint the exact moment in fMRI when the data is most relevant to the disorder in question.

For people with Alzheimer’s disease and schizophrenia, research has come to very positive conclusions. Unlike ASD, predicting when early symptoms of these first two begin to appear can be essential in its treatment.

In fact, Vince Calhoun, study co-author and founding director of the Georgia State TReNDS Center, said, “If we could find markers to predict Alzheimer’s risk in a 40-year-old, we might be able to do something about it.”

Secondly, schizophrenia can be detected before the structure of the brain begins to change. This step will be very important if you want to prevent this type of disorder in the future.

“Even if we know from other tests or family history that someone is at risk for a disorder like Alzheimer’s, we still cannot predict when exactly it will occur. Brain imaging could shorten that window of time, capturing relevant patterns when they appear before clinical disease manifests,” said study co-author Vince Calhoun.