Artificial intelligence predicts Alzheimer's disease 6 years earlier than doctors, according to a study.



[ad_1]

A study shows that artificial intelligence can be used to detect Alzheimer's disease six years before the patient is normally diagnosed.

Doctors have used the self-learning computer to detect changes in subtle brain scans so that humans can see them.

The system was able to identify dementia in 40 patients on average six years before the formal diagnosis.

Professor Noel Sharkey, of the University of Sheffield, a British specialist in artificial intelligence, said about the findings: "This is exactly the kind of task that requires deep learning – searching for data models of high level.

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

The Boffins of the University of California trained the computer with the help of more than 2100 scans out of 1,002 patients.

Scans measure brain activity by monitoring the absorption of a radioactive liquid injected into the bloodstream.

Research has linked the development of Alzheimer's disease to particular changes in certain areas of the brain, but these can be difficult to detect.

The Alzheimer's algorithm has been able to self-learn to recognize patterns of brain analysis indicating a disease.

As a final test, he was administered a series of 40 examinations of 40 patients he had never studied before.

The detection of Alzheimer's disease has been 100% accurate for many years before the patient is diagnosed later.

Dr. Jae Ho Sohn, who worked on the project, said, "We are very pleased with the performance of the algorithm.

"It has been possible to predict every case that has progressed to Alzheimer's disease."

Early detection of Alzheimer's disease could pave the way for new ways to slow down or even stop the progression of the disease.

your health

Dr. Carol Routledge, of Alzheimer's Research UK, said: "The diseases that cause dementia appear in the brain until 20 years before the onset of symptoms, representing a window of opportunity vital to us, before widespread damage does occur.

"This study highlights the potential of machine learning to aid in early detection of diseases such as Alzheimer's disease, but the results will need to be confirmed by much larger groups of people before we can properly evaluate the power of this approach. "

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

Click for more The Sun.

[ad_2]
Source link