Although Alzheimer's disease affects tens of millions of people around the world, it is difficult to detect it at an early stage. But scientists dealing with artificial intelligence in medicine have found that technology can help diagnose early disease. The California team recently published a report on its Radiology Magazine research and demonstrated how the nerve network was able to accurately determine the extent of Alzheimer's disease in patients based on visualization of brain imaging carried out years before the number of doctors in those patients.
The team uses brain imaging (FDG-PET Imaging) to excite and test their neural network. In FDG, the patient's circulatory images are injected with a radioactive glucose type and then his body tissue, including the brain, pushes it onto the surface. Scientists and doctors may then use PET scan to identify the metabolism of this tissue depending on how much FDG is taken.
The FDG-PET method is used to diagnose Alzheimer's disease, and patients with a disease usually exhibit lower metabolic activity in certain parts of the brain. However, experts need to analyze these images when finding evidence of the disease and this becomes extremely difficult because moderate cognitive impairment and Alzheimer's disease can lead to similar results in scanning.
That's why the team uses 2,109 FDG-PET images of 1002 patients. Practice 90% of their neural network and test the remaining 10%. He also carries out tests with one in 40 patients scanned in 2006 and 2016, and then compares artificial intelligence with a group of experts analyzing the same data.
With separate test data, Artificial Intelligence is able to diagnose Alzheimer's patients with 100% accuracy and 82% accuracy for those without a fraudulent disease. He can also make forecasts for more than six years on average. For comparison, 57% and 91% of patients with Alzheimer's disease were diagnosed with the same scanned image. However, differences in machine and human performance are not as noticeable as they are diagnosed with mild cognitive impairment 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 training data.