NEW YORK, Nov. 8 (Xinhua) -- A new artificial intelligence (AI) system developed by U.S. researchers may be capable of detecting the early signs of Alzheimer's disease six years before doctors can make an actual diagnosis.

Scientists at the University of California, San Francisco trained their AI how to detect markers of metabolic changes in patients' brains that are imperceptible to the human eye so as to predict the development of Alzheimer's.

From their study of 2,109 images from 1,002 patients who had already been diagnosed, the researchers found the AI was able to spot Alzheimer's in images taken on an average of six years before diagnosis with 100% accuracy.

These findings were published in Radiology.

Alzheimer's is one of the most difficult brain disorders and affects about 48 million people worldwide. The number is expected to increase with the aging population. There is not yet any effective cure for the disease, and most people have only four to eight years left to live by the time they are diagnosed.

Significant brain damage from Alzheimer's disease can occur years before any symptoms such as memory loss and cognitive decline appear. The earlier an Alzheimer's patient can start medications, the better. So early detection is their best hope.

Though it will be some time before the new system is publicly available, the researchers have high hopes for the AI's potential.

"If we diagnose Alzheimer's disease when all the symptoms have manifested, the brain volume loss is so significant that it's too late to intervene," said study co-author Dr. Jae Ho Sohn.

"If we can detect it earlier, that's an opportunity for investigators to potentially find better ways to slow down or even halt the disease process," he added.