Although Alzheimer's disease affects tens of millions of people around the world, it is still difficult to locate at an early stage. But researchers who deal with the potential of artificial intelligence in medicine have discovered that technology can help in timely diagnosis of suspect disease. The California team recently published a report on its study in Radiology magazine and showed that just having been trained in the nervous network managed to accurately diagnose Alzheimer's disease in a limited number of patients based on visual brain imaging carried out years before these patients diagnosed by a doctor.
The team uses brain imaging (FDG-PET imaging) to educate and test their nervous network. In the FDG, the patient's blood circulation images are injected with a radioactive type of glucose, and then the body's tissue, including the brain, pushes him to the surface. Scientists and doctors can then use PET scan to perceive the metabolic activity of this tissue, depending on how much FDG is taken.
The FDG-PET method is used to diagnose Alzheimer's disease, while patients with the disease usually have lower levels of metabolic activity in some parts of the brain. However, experts should 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 scan results.
As a result, the team uses 2.109 FDG-PET images from 1002 patients, training their nervous network at 90% and examining it with the remaining 10%. It also carries out trials with a single set of 40 patients scanned between 2006 and 2016, then compares the findings of artificial intelligence with those of a team of experts who analyze the same data.
With a separate set of test data, Artificial Intelligence is able to diagnose Alzheimer's patients with 100% accuracy and with 82% accuracy those who do not suffer from insidious disease. It can also make forecasts on average more than six years ahead. By comparison, the group of doctors who examined the same scanned images identified patients with Alzheimer's disease in 57% of cases and those without the disease – 91%. However, the differences in machine and human performance are not as noticeable in the diagnosis of mild cognitive dysfunction not characteristic of Alzheimer's disease.
Researchers note that their research has several limitations, including a small number of test data and limited training data types.