Monday , April 12 2021

AI recognizes Alzheimer's disease for years before diagnosis



Recording Human Brain by PET

Thousands of PET images of Alzheimer's patients at an early stage used researchers to teach their AI. (Photo: Radiological Society of North America)

BerlinIn the fight against Alzheimer's disease, early detection is especially important. If the still incurable dementia is discovered early, it can at least slow down its path to medication.

"If we diagnose Alzheimer's disease only when clear symptoms occur, the loss of brain volume is so great that it's usually late for effective intervention," explains Jae Ho Sohn.

Together with her team at the University of California in San Francisco, the physician has developed a new tool for early detection of Alzheimer's disease: an adaptive algorithm that reliably predicts dementia years before the diagnosis of a doctor.

Researchers have focused their development on subtle metabolic changes in the brain that are caused by the onset of the disease. Such changes can be visualized by the technique of recording known as Positron Emission Tomography (PET).

Seven factors that favor Alzheimer's disease

However, traces in the early stages of the disease are so weak that they are difficult to recognize even for experienced doctors. "People find it easier to find specific biomarkers of the disease," explains Sohn. "But metabolic changes are much more subtle processes."

Researchers trained their artificial intelligence using data from Alzheimer's disease neuroimaging initiative (ADNI). Among other things, this data collection contains thousands of PET images of Alzheimer's patients at very early stages of the disease. 90 percent of these footage, the researchers used to train the algorithm, and the remaining 10 percent to control the success.

For the final test, AI is finally analyzing 40 images that had not been submitted to her until then. The result is described by the son as follows: "The algorithm could reliably detect any case that later came to the onset of Alzheimer's disease."

At a rate of 100 percent, physicians impressed primarily on early identification of cases. On average, the system recognized the symptoms more than six years before the actual diagnosis of the disease. "We were thrilled with that result," says Sin. However, the doctor also knows that the test series is still relatively small, and further tests must confirm the result.

However, in his algorithm he sees the potential of an important tool in treating Alzheimer's disease: "If we detect the disease earlier, it will allow researchers to find better ways to slow down or even stop the disease process."


Source link