AI Predicts Your Risk of Alzheimer’s with 99% Accuracy
An artificial intelligence (AI) system has been developed that can identify early signs of Alzheimer’s disease (AD) with over 99 percent accuracy. By evaluating brain scans of older adults, the algorithm can pick out subtle changes that often occur before diagnosis, allowing doctors to treat high-risk individuals early.
In the journal Diagnostics, the study authors describe how AI successfully recognizes signs of Mild Cognitive Impairment, considered an intermediate stage between normal aging and the expected cognitive decline associated with Alzheimer’s. Although MCI typically does not produce obvious symptoms, it is associated with changes in certain brain regions that can be detected on functioning magnetic resonance imaging (MRI) scans.
However, manually searching for these changes is difficult. And doctors don’t always notice them when looking at scans. By retargeting an existing neural network called ResNet18, the researchers created an AI model that could identify HBB with greater reliability.
Study author Rytis Maskeliunas said in a statement; “Modern signal processing allows image processing to be delegated to the machine, which can complete it quickly and accurately enough. “Of course we wouldn’t dare suggest that a medical professional should trust any algorithm 100 percent.”
Artificial intelligence that can identify early signs of Alzheimer’s disease (AD) with over 99 percent accuracy
To create their AI, the researchers trained the neural network on 51,443 brain scans from 138 people. These images were divided into six different categories, ranging from healthy brains to various degrees of MCI and fully developed Alzheimer’s. A further 27,310 images were then used to validate the algorithm, which could identify early HBB with 99.99 percent accuracy and late HBB with 99.95 percent accuracy.
The proposed model outperformed other known models in terms of accuracy, sensitivity, and specificity, the authors said. In addition, their claims are more reliable and accurate than current diagnostic tools for future Alzheimer’s risk.
More importantly, the researchers stress that MCI does not always lead to Alzheimer’s and that people who show signs of these brain changes may not necessarily continue to progress. However, identifying MCI improves the ability of healthcare professionals to assess a patient’s Alzheimer’s risk, potentially allowing for earlier screening and intervention.
Explaining how the algorithm can be used in practice, Maskeliunas explained that after the computer algorithm selects the potentially affected cases, the specialist can examine them more closely, and eventually everyone benefits as the diagnosis and treatment reach the patient much faster.