(CN) — British scientists announced on Monday that they have developed a machine learning algorithm capable of determining, with 98% accuracy, whether a patient has Alzheimer’s disease by examining a single brain scan.
“Waiting for a diagnosis can be a horrific experience for patients and their families. If we could reduce the waiting time, simplify the diagnostic process and reduce some of the uncertainty, that would help a lot,” said Eric Aboagye, professor of cancer pharmacology at Imperial College London and lead researcher of the study, in a press release.
Many tests are used to diagnose Alzheimer’s disease, a type of dementia that kills brain cells and damages their connection, including brain scans done with a magnetic resonance imaging (MRI) machine.
“Although neuroradiologists already interpret MRI scans to help diagnose Alzheimer’s disease, some features of the scans are likely not visible even to specialists,” said neurologist Paresh Mahotra, a researcher at the Department of brain sciences from ImperialCollege London, in the statement. . “Using an algorithm that can pick out the texture and subtle structural features of the brain that are affected by Alzheimer’s disease could really improve the information we can get from standard imaging techniques.”
The novelty of the Aboagye team’s approach lies in the adaptation of methods that have been developed to classify cancerous tumors on MRI scans of more than 400 patients with both early and early-stage Alzheimer’s disease. late-stage, healthy brains as well as patients with Parkinson’s disease and other neurological conditions.
The data was provided by the Alzheimer’s Disease Neuroimaging Initiative, a multi-site cooperative study that aims to improve Alzheimer’s disease research. The algorithm examined each brain in terms of 115 regions, rating each according to characteristics such as size, shape and texture.
The team ‘trained’ the algorithm using these scans as inputs, teaching it the difference between regions and features that indicate Alzheimer’s disease and features that do not indicate the presence of Alzheimer’s disease. Alzheimers. By teaching it to distinguish signs of Alzheimer’s disease from red herrings, the algorithm became able to make predictions when presented with new data.
Patients who were simultaneously being tested for Alzheimer’s disease at Imperial College Healthcare NHS Trust in London, England, also offered their scans as data for research. The scientists’ new approach was able to accurately predict whether or not a patient’s CT scan showed Alzheimer’s disease in 98% of cases, and was even able to distinguish between early and late stage Alzheimer’s disease. Alzheimer’s disease in 79% of patients.
The researchers tout the simplicity of their technique and claim that it helps identify Alzheimer’s disease early in its development.
“Currently, no other simple, widely available method can predict Alzheimer’s disease with this level of accuracy, so our research is an important step forward,” Aboagye said. “Many patients who present with Alzheimer’s disease to memory clinics also have other neurological disorders, but even within this group, our system could distinguish patients with Alzheimer’s disease from those who had none.”
Early diagnoses are difficult to make with traditional methods, and although there is no cure for the disease – although new treatments, even vaccines, can reverse some of its consequences – patients warned early are better off. able to receive support, prepare their loved ones and plan the rest of their lives with the condition in mind.
“Our new approach could also identify patients at an early stage for clinical trials of new drug treatments or lifestyle changes, which is currently very difficult to do,” Aboagye continued.
The team’s algorithm also used regions of the brain that had not been examined before to diagnose the disease. The cerebellum, which coordinates physical activity, and the ventral diencephalon, which figures in sight and hearing, are two such regions.
Aboagye’s research, published Monday in the peer-reviewed open-access journal Communication Medicinewas funded by a division of the UK’s National Institute for Health and Care Research Centre.