United kingdom – machine learning algorithm machine learning It can determine whether a person has Alzheimer’s disease (AD) based on an MRI scan with 98% accuracy, according to a study published online June 20 in Telecommunications .
“Currently, there is no other simple and widely available method that can diagnose Alzheimer’s disease with this level of accuracy, so our research is an important step forward,” the department said in a statement. Professor Eric Aboage of Imperial College London, who conducted the research.
He added, “Many patients who come in for memory counseling with Alzheimer’s also have other neurological disorders, but even within this group our system can distinguish between Alzheimer’s patients and those without.”
A powerful and repeatable tool
To develop the algorithm, Professor Abu Aji and his colleagues divided the brain into 115 regions and assigned them 660 different properties, such as size, shape and texture. They trained the algorithm to pinpoint exactly where changes in this characteristic might correspond to Alzheimer’s disease.
Using data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), the team tested their algorithm on brain MRI scans of more than 400 patients with late-stage Alzheimer’s disease. Dementia and Parkinson’s disease.
They also tested it using data from more than 80 patients who underwent Alzheimer’s diagnostic tests at the Imperial College Healthcare NHS Trust.
In 98% of cases, an MRI-based machine learning tool alone can accurately predict whether a person has Alzheimer’s disease, bypassing traditional measurements of hippocampal volume and hippocampal beta-amyloid protein in cerebrospinal fluid (CSF). It can also distinguish between early and advanced stages of Alzheimer’s disease in 79% of patients.
The tool was found to be “robust and reproducible across MRI scans, demonstrating potential for application in clinical practice in the future,” the researchers wrote.
“Most patients have to undergo a full series of tests before getting a diagnosis, and this tool can enable faster diagnosis and reduce patient anxiety. Of course, a specialist may be able to use this information to improve and adjust the diagnosis.”
The algorithm also detected changes in areas of the brain that were not previously associated with Alzheimer’s disease, including the cerebellum and ventricular cerebrum. Professor Abu Aji noted that this “opens up possibilities for researchers” to take a closer look at these areas and see how they might be linked to dementia.
“Although neuroradiologists are already interpreting MRIs to help diagnose Alzheimer’s disease, it is possible that some features of the scans will not be visible even to specialists,” he explained. Professor Paresh MalhotraCo-Investigator (Imperial College London) in the press release.
Professor Malhotra added: “Using an algorithm that can learn about the exact structure and characteristics of the brain that are affected by Alzheimer’s disease could improve the insights we can get from standard imaging techniques.”
You need to repeat the experience
Talking about Medscape Medical NewsThe Dr.. Cyrus A. pleaseThe study shows that “new computational analyzes of structural or T1-weighted images can identify Alzheimer’s disease with a high degree of accuracy,” said assistant professor of radiology and neuroscience at Washington University in St. Louis, Missouri.
However, Dr. Raji concluded that “transition into clinical practice will require replication of these findings as well as programs optimized for the clinical environment.”
This research was funded in part by Imperial College London NIHR Center for Biomedical Research and the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Prs Aboagye, Malhotra and Raji reported no financial related relationship.
The article originally appeared on Medscape.com Where Can a Single Brain Scan Accurately Diagnose Alzheimer’s? Translated by Aude Lecrubier.
Follow Medscape in French at Twitter.
Follow theheart.org | Medscape Heart on Twitter.
Receive our specialized newsletters.
#Alzheimers #disease #artificial #intelligence #accurate #diagnosis #based #magnetic #resonance #imaging #brain