Doctors have often found it difficult to detect the presence of Alzheimer’s disease in a person’s brain, especially in the early stages. We’re talking about a horrible disease that affects about half of people aged at least 85 years old.
According to SciTechDaily.com, researchers led by Professor Eric Aboagye from Imperial’s Department of Surgery and Cancer came up with a new method of detecting Alzheimer’s disease. Their idea consists of using machine learning technology to tell if someone has developed the condition even at an early stage. Contrary to what you may have heard about MRI (magnetic resonance imaging) scans telling that a person has Alzheimer’s or not, that is indeed a possibility, but it’s not entirely accurate. Cognitive and memory tests are also used by doctors in trying to diagnose the presence of the most common form of dementia in a patient’s brain, but these are also not 100 percent reliable.
A revolutionizing new way to detect Alzheimer’s disease
The new technique implies the use of a single MRI scan that’s being taken on a standard 1.5 Tesla machine.
The new method was put to the test for 400 patients that suffer from Alzheimer’s in different stages of the disease. Over 80 patients who were already undergoing tests for diagnosing Alzheimer’s were also tested.
In an overwhelming 98 percent of cases, the researchers were able to determine accurately which of the patients suffer from the most common form of dementia and which ones of them do not. The machine learning system was even able to detect different levels of the disease’s progress.
Dr. Paresh Malhotra is a consultant neurologist at Imperial College Healthcare NHS Trust, and he’s also working at Imperial’s Department of Brain Sciences. The scientist said, as SciTechDaily quotes:
Although neuroradiologists already interpret MRI scans to help diagnose Alzheimer’s, there are likely to be features of the scans that aren’t visible, even to specialists. Using an algorithm able to select texture and subtle structural features in the brain that are affected by Alzheimer’s could really enhance the information we can gain from standard imaging techniques.
Even though the medical world currently has no cure for Alzheimer’s, telling for sure that a person has the disease at an early stage can be very helpful.
The new research was published in the Nature Portfolio Journal, Communications Medicine.