Artificial Intelligence
AI Predicts Alzheimer’s Disease from a Single Brain Scan
AI can spot Alzheimer’s Disease with high accuracy from MRI data.
Posted August 26, 2022 Reviewed by Kaja Perina
Alzheimer’s disease (AD) is the most common type of dementia and a progressive neurodegenerative disease that destroys brain cells over time. A new study shows how artificial intelligence (AI) machine learning can be used in the development of a biomarker based on a magnetic resonance imaging (MRI) scan for Alzheimer’s disease.
“In this study, we develop a method that uses magnetic resonance imaging data to identify differences in the brain between people with and without Alzheimer’s disease, including before obvious shrinkage of the brain occurs,” wrote the study authors. “This method could be used to help diagnose patients with Alzheimer’s Disease.”
There are 47 million people living with Alzheimer’s disease globally, and by 2030 this number is expected to increase to 76 million according to the Alzheimer’s Association. In the U.S. alone, there are 5.8 million Americans with Alzheimer’s disease, of which two-thirds are women according to a report by AARP and the Women’s Alzheimer’s Movement (WAM). By 2050, the number of Americans living with Alzheimer’s disease is projected to reach 16 million according to the Harvard NeuroDiscovery Center at Harvard Medical School.
Although there is no known cure for Alzheimer’s disease, there are treatments available that may help with some of the symptoms. The earlier the stage when diagnosed, the more time a patient has to seek treatment to manage the symptoms and get support.
The symptoms of Alzheimer’s disease vary depending on the stage of the disease. In the early stage of the disease, short-term memory loss is common. Over time, the ability to perform various functions is impaired, affecting motivation, focus, executive functioning, decision-making, problem-solving, judgment, and the ability to multitask. In the later stages of the disease, people with AD forget how to perform basic daily tasks and are eventually dependent on caregivers for survival.
The neuropsychiatric symptoms associated with Alzheimer’s disease may include depression, social withdrawal, psychosis, wandering, apathy, agitation, distrust in others, disinhibition, and delusions.
“In these last 40 years, improved computational power and storage capacity have led to numerous advances in developing non-invasive and low-cost structural biomarkers for AD that combine neuroimaging approaches, in particular structural MRI, with machine learning,” the researchers wrote.
The databases used for this study include the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database, the Open Access Series of Imaging Studied (OASIS) consortium, and the Imperial Memory Centre (IMC) based in London, United Kingdom.
Magnetic resonance imaging scans were subdivided into 115 sub-regions of which there were 45 regions in the brain’s white matter, and 70 regions in the subcortical areas. Over 650 diverse features such as wavelet, intensity, texture, shape, and size were assigned to each region for assessment.
The researchers tailored an AI classifier algorithm used for predicting cancer and trained it to spot changes in the features in the brain that can predict the presence of Alzheimer’s disease. Then the algorithm was tested on brain scans data from more than 80 patients at Imperial College Healthcare NHS Trust who were being evaluated for AD, as well as data from the Alzheimer’s Disease Neuroimaging Initiative from over 400 early and late-stage Alzheimer’s disease patients, a control group of those without Alzheimer’s disease, as well as those with other brain disorders such as Parkinson’s disease and frontotemporal dementia.
What sets this study apart is that not only did the AI algorithm perform with 98 percent accuracy in its predictions, but also it does not require further sampling nor additional patient testing in order to be integrated into clinical decision support systems according to the scientists. Furthermore, the AI algorithm was able to identify changes in the areas brain that were not previously associated Alzheimer’s disease.
“Interestingly, the algorithm also selects regions not commonly related to AD, such as the cerebellum and the ventral diencephalon,” the scientists reported. “Together with a few studies reported in the literature, this outcome challenges the traditional view that white matter bundles in the cerebellum or in the ventral diencephalon are not affected by AD, possibly highlighting new therapeutic opportunities.”
Copyright © 2022 Cami Rosso All rights reserved.
