Skip to content

Researchers Couple An Algorithm With Brain Scans To Detect Alzheimer’s Disease Early

    news 15 July feature

    Brain News

    Researchers at the Imperial College London, the UK, explored how machine learning technology can help diagnose Alzheimer’s disease early. The study is published in the journal Communications Medicine.

    The Study

    The researchers adapted an algorithm used in classifying cancer tumors. They further divided the brain into 115 regions. Then, they allocated 660 different features (like size, shape, texture, etc.) to assess each region. They trained the algorithm to identify the changes in these features and accurately predict Alzheimer’s disease at an early age.

    The researchers coupled the algorithm with MRI brain scans and implemented it on:

    • Potential patients undergoing diagnostic cognitive tests for Alzheimer’s disease
    • Alzheimer’s patients who were in their early and later stages of the memory disorder
    • Healthy participants
    • Patients with other neurological conditions (like dementia, Parkinson’s disease, etc.)

    The Findings

    The results revealed that such algorithm-powered single-brain scans can help identify Alzheimer’s disease at an early stage even when it can be very difficult to diagnose.

    The researchers are enthusiastic that the findings of the study can help cut down the large raft of expensive and time-consuming medical tests used to diagnose Alzheimer’s disease.

    One of the lead researchers, Professor Eric Aboagye, elaborated: “If we could cut down the amount of time they have to wait, make diagnosis a simpler process, and reduce some of the uncertainty, that would help a great deal. Our new approach could also identify early-stage patients for clinical trials of new drug treatments or lifestyle changes, which is currently very hard to do.

    To Know More You May Refer To

    Imperial College London. (2022, June 20). Single brain scan can diagnose Alzheimer’s disease. ScienceDaily. Retrieved July 10, 2022 from www.sciencedaily.com/releases/2022/06/220620100827.htm