Although Alzheimer's disease affects dozens of millions of people around the world, it is still difficult to detect at an early stage. But researchers dealing with the possibilities of artificial intelligence in medicine have discovered that technology can help in early diagnosis of abused diseases. The California group recently published a report on its study in Radiology and showed that it had been trained for some time that the neural network could accurately determine Alzheimer's disease in a limited number of patients based on brain visualizations that were performed several years ago by patients diagnosed by a physician.
The team uses brain imaging (FDG-PET imaging) to train and test their neural network. In FDG, patient blood images are injected with a radioactive type of glucose, and then his body tissue, including the brain, is pushed to the surface. Scientists and doctors can then use PET scans to sense the metabolic activity of this tissue, depending on how much FDG is taken.
The FDG-PET method is used to diagnose Alzheimer's disease, in patients with a disease usually show lower levels of metabolic activity in certain parts of the brain. Experts, however, need to analyze these images to find evidence of illness, and this becomes very difficult because moderate cognitive impairment and Alzheimer's disease can lead to similar scanning results.
Therefore, the team uses 2,109 FDG-PET images of 1002 patients, enabling their neural network to 90% and testing for the remaining 10%. It also launches tests with a single set of 40 patients scanned between 2006 and 2016 and then compares artificial intelligence findings with those of a group of experts who analyze the same data.
With a separate set of test data, artificial intelligence can diagnose Alzheimer's patients with 100% accuracy and 82% accuracy for those who do not suffer from traitors. It can also predict an average of more than six years in advance. For comparison, a group of doctors who looked at the same scanned images identified patients with Alzheimer's disease in 57% of cases and those without illness – in 91%. However, differences in machine and human performance are not so noticeable when it comes to diagnosing a mild cognitive disorder that is not typical of Alzheimer's disease.
Researchers point out that their research has several limitations, including a small amount of test data and limited types of training data.