Although Alzheimer's disease affects tens of millions of people around the world, it is still difficult to detect at an early stage. But researchers who address the possibilities of artificial intelligence in medicine have found that technology can help early diagnosis of treacherous diseases. The California team recently published a report on its study in Radiology Magazine and demonstrated how once the neural network was able to accurately diagnose Alzheimer's disease in a limited number of patients based on brain imaging visualizations performed years before The patients in question were actually diagnosed by a doctor.
The team uses brain images (FDG-PET images) to train and test your neuronal network. In FDG, images of the blood's blood from the patient are injected with a type of radioactive glucose, and then their body tissue, including the brain, is pushed to the surface. Scientists and doctors can then use PET to detect the metabolic activity of this tissue, depending on the size of FDG.
The FDG-PET method is used to diagnose Alzheimer's disease, and patients who present the disease usually exhibit lower levels of metabolic activity in certain 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 disease can lead to similar results in exploration.
Therefore, the equipment uses 2,109 FDG-PET images of 1002 patients, training their neuronal network in 90% and testing it in the remaining 10%. He also tests with a single set of 40 patients scanned between 2006 and 2016, and compares the results of artificial intelligence to those of a group of specialists who analyze the same data.
With a separate set of test data, Artificial Intelligence is able to diagnose patients with Alzheimer's with 100% accuracy and 82% accuracy who do not suffer from treacherous diseases. You can also make forecasts on average more than six years ahead. In comparison, the group of doctors who analyzed the same scanned images identified patients with Alzheimer's disease in 57% of cases and those without the disease (91%). However, the differences between human performance and the machine are not so noticeable when it comes to diagnosing a 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.