Researchers at Massachusetts General Hospital (MGH) have found a method to employ artificial intelligence to more efficiently and quickly detect Alzheimer’s disease in a new research article that appeared in PLOS ONE.
They were capable of identifying the risk of Alzheimer’s with an efficiency of 90.2% using deep learning, which has previously been proven to accurately diagnose many illnesses in data from high-quality brain magnetic resonance imaging (MRIs) obtained in a supervised study context.
“Alzheimer’s disease typically occurs in older adults, and so deep learning models often have difficulty in detecting the rarer early-onset cases,” said study co-author Matthew Leming in a press release.
“We addressed this by making the deep learning model ‘blind’ to features of the brain that it finds to be overly associated with the patient’s listed age.”
The scientists constructed an instrument specifically for the disease’s identification using brain pictures from individuals who had MRIs taken at MGH prior to 2019—including both those with and without Alzheimer’s disease.
The model was then evaluated using 26,892 MRI images from 8,456 individuals without the condition and 11,103 MRI images from 2,348 patients at risk for developing the illness.
To assure accuracy in real-world instances, the data included five datasets from various hospitals and different times, including Brigham and Women’s Hospital before and after 2019, MGH after 2019, as well as outside systems before and after 2019.
The model was extremely accurate throughout all datasets and was capable of accurately identifying the risk regardless of additional variables such as the patient’s age.
According to the Centers for Disease Control and Prevention, Alzheimer’s disease represents the most prevalent type of dementia and is described as a progressive illness starting with modest memory loss and potentially progressing to loss of communication and environmental awareness (CDC).
In Canada, there were 597,000 dementia sufferers as of 2020, and there are approximately 5.8 million Americans with Alzheimer’s disease. It is predicted that 955,900 Canadians will have dementia by the year 2030.
“Our results—with cross-site, cross-time, and cross-population generalizability—make a strong case for clinical use of this diagnostic technology,” said Leming.
Earlier this month, researchers found that by using the well-known Stable Diffusion graphic prototype, they were capable of producing high-resolution and entirely correct photographs of activity in the brain.
The researchers asserted that, in contrast to earlier studies, they did not need to train or enhance the artificial intelligence systems in the process of developing these pictures.
The study was conducted by researchers from Osaka University’s Graduate School of Frontier Biosciences. They used fMRI waves to construct feature representations or models of the picture’s contents first.
