Madrid
Updated:
Save
A team of British researchers has demonstrated the effectiveness of a new technique for the early diagnosis of Alzheimer’s disease that combines a single image obtained with a brain scanner together with a machine learning system. This new technique has already been tested on more than 400 patients in the United Kingdom and has managed to detect Alzheimer’s in 98% of cases.
The research uses machine learning technology to look at structural features of the brain, including in regions that had not previously been associated with Alzheimer’s.
Although there is no cure for Alzheimer’s disease, getting a quick diagnosis at an early stage helps patients. It allows them to access help and support, receive treatment to control their symptoms, and plan for the future.
Being able to accurately identify patients early in the disease will also help researchers understand the brain changes that trigger the disease and support the development and testing of new treatments.
The research is published in the journal Nature Communications Medicine.
Although most people with Alzheimer’s disease develop it after the age of 65, people younger than this age can also develop it. The most common symptoms of dementia are memory loss and difficulties with thinking, problem solving, and language.
A number of tests are currently used to diagnose Alzheimer’s disease, including cognitive and memory tests and brain scans. The scans are used to check whether there are protein deposits in the brain and whether the hippocampus, the area of the brain linked to memory, has shrunk. All of these tests can take several weeks, both to organize and process.
The new method requires only one of them: an MRI of the brain performed on a standard 1.5-Tesla machine, usually found in most hospitals.
The researchers adapted a developed algorithm to classify cancer tumors and applied it to the brain. They divided the brain into 115 regions and assigned 660 features different, such as size, shape, and texture, to assess each region. They then trained the algorithm to identify where changes in these characteristics could accurately predict the existence of Alzheimer’s disease.
Using data from the IAlzheimer’s disease neuroimaging initiative The team tested their method on brain scans of 420 patients with early and late-stage Alzheimer’s, healthy controls, and patients with other neurological conditions, such as frontotemporal dementia and Parkinson’s disease. They also tested it with data from more than 80 patients undergoing Alzheimer’s diagnostic tests at Imperial College Healthcare NHS Trust.
They found that in 98% of cases, the MRI-based machine learning system could accurately predict whether or not the patient had Alzheimer’s disease. It was also able to distinguish between early-stage and late-stage Alzheimer’s with fairly high accuracy, in 79% of patients.
‘Currently, no other simple and widely available method can predict Alzheimer’s disease with this level of accuracy, so our research marks an important step forward. Many of the patients who come to memory clinics with Alzheimer’s disease also have other neurological conditions, but even within this group our system was able to distinguish patients who had Alzheimer’s from those who did not.” Eric Aboagyewho led the investigation.
“Waiting for a diagnosis can be a horrible experience for patients and their families. If we could reduce the waiting time, simplify the diagnosis and reduce the uncertainty, it would be of great help. Our new approach could also identify patients early for clinical trials of new drug treatments or lifestyle changes, something that is currently very difficult to do,” she adds.
The new system detected changes in areas of the brain that until now had not been associated with Alzheimer’s disease, such as the cerebellum (the part of the brain that coordinates and regulates physical activity) and the ventral diencephalon (linked to the senses, sight and ear). This opens new avenues of research in these areas and their relationship to Alzheimer’s disease.
See them
comments