Although Alzheimer's disease affects tens of millions of people around the world, it is still difficult to detect at an early stage. However, researchers dealing with the possibilities of artificial intelligence in medicine have discovered that technology can help in the early diagnosis of betrayal. The California team recently published a report on their study in the journal Radiology and demonstrated how, after training, the neural network was able to accurately diagnose Alzheimer's disease in a limited number of patients based on visualization of brain imaging done many years before the patients under study. they are diagnosed by a doctor.
The team uses brain imaging (FDG-PET imaging) to train and test their neural network. In FDG images of the patient's bloodstream are injected with a radioactive type of glucose, and then his body tissue, including the brain, shifts it towards the surface. Researchers and physicians can then use a PET scan to detect the metabolic activity of this tissue, depending on how much FDG is taken.
The FDG-PET method is used to diagnose Alzheimer's disease, and patients with disease usually show a lower level of metabolic activity in some parts of the brain. Experts, however, have to analyze these images to find evidence of the disease, and this becomes very difficult because moderate cognitive impairment and Alzheimer's can lead to similar results in scanning.
Therefore, the team uses 2,109 FDG-PET images from 1002 patients, training their neural network at 90% and testing it on the remaining 10%. It also tests with one set of 40 patients scanned in 2006-2016, and then compares the findings of artificial intelligence with the results of a group of specialists who analyze the same data.
Thanks to a separate set of test data, artificial intelligence is able to diagnose patients with Alzheimer's disease with 100% accuracy and with 82% accuracy of those who do not suffer from treacherous diseases. It can also predict on average more than six years earlier. For comparison, a group of doctors who viewed the same scanned images identified patients with Alzheimer's disease in 57% of cases and those without this disease – in 91%. However, the differences in the performance of machines and people are not as noticeable when it comes to diagnosing mild cognitive impairment that is not typical of Alzheimer's disease.
Researchers note that their research has several limitations, including a small amount of test data and limited types of training data.