Artificial intelligence can predict Alzheimer's disease 6 years earlier than doctors, study finds

Artificial intelligence can be used to recognize Alzheimer's disease six years before a patient would normally be diagnosed, according to a study.

Doctors used the self-learning computer to detect changes in brain scans that are too subtle for people to see.

The system was able to identify dementia in 40 patients on average six years before they were formally diagnosed.

The British AI expert Professor Noel Sharkey, of the University of Sheffield, said about the findings: "This is exactly the kind of task that requires in-depth research – finding patterns at a high level in data.

"Although the sample sizes and test sets were relatively small, the results are so promising that a much larger study would be worthwhile."

Boffins from the University of California trained the computer using over 2100 scans of 1002 patients.

The scans measure brain activity by following the uptake of a radioactive fluid that is injected into the blood.

Research has linked the development of Alzheimer's to certain changes in certain brain regions, but these can be difficult to recognize.

The Alzheimer algorithm was able to teach itself to recognize patterns in brain scans that indicate disease.

As a final test, it received a set of 40 scans from 40 patients who had never studied it before.

It proved 100 percent accurate in detecting Alzheimer's disease many years before the patient was diagnosed later.

Dr Jae Ho Sohn, who worked on the project, said: "We were very satisfied with the performance of the algorithm.

"It was able to predict every single case that developed into Alzheimer's disease."

Early detection of Alzheimer's disease could open the door to new ways to slow or even halt the progression of the disease.

Dr. Carol Routledge, of Alzheimer's Research UK, said: "The diseases that cause dementia begin in the brain for up to 20 years before symptoms begin to manifest, providing us with a vital window of opportunity to intervene before widespread use. damage occurs.

"This study emphasizes the potential of machine learning to assist in the early detection of diseases such as Alzheimer's, but the findings will need to be confirmed in much larger groups of people before we can properly assess the strength of this approach."

The research is published in the latest issue of the journal Radiology.

Click for more from The Sun.