Thursday , July 7 2022

AI recognizes Alzheimer's for years before diagnosis


Burning human brains with PET

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

BerlinIn the fight against Alzheimer's disease, early detection is particularly important. If an incurable dementia is still detectable early, it can at least slow down their drug therapy.

"If we diagnose Alzheimer's only when clear symptoms appear, loss of brain volume is so great that it is usually too late for effective action," explains Jo Ho Hohn.

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

The researchers focused their development on subtle metabolic changes in the brain that were caused by the onset of this disease. Such changes can be visualized using the imaging technique known as positron emission tomography (PET).

Seven factors favoring Alzheimer's

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

The researchers trained their artificial intelligence using data from Alzheimer's Neuroimaging Initiative (ADNI). Among other things, this collection of data contains thousands of PET images of Alzheimer's patients in very early stages of the disease. 90 percent of these recordings, the researchers trained the algorithm, and the remaining 10 percent to control success.

For the final test, the AU had to finally analyze 40 images that had not been delivered to her before. The result describes the son as follows: "The algorithm was able to reliably detect every case, which later came to the appearance of Alzheimer's disease."

In addition to the strike rate of 100 percent, doctors suddenly impressed the early identification of cases. On average, the system recognized symptoms more than six years before the actual diagnosis of the disease. "We were thrilled with this result," says Sin. However, the doctor also knows that the series of tests is still relatively small, and additional tests must confirm the result.

Nevertheless, he sees in his algorithm the potential for an important tool in Alzheimer's treatment: "If we can detect a disease earlier, researchers will be given the opportunity to find better ways to slow down or even stop the disease process."

Source link