Scientists are constantly discovering new ways this exciting technology can be used to improve our health and extend lifespans, whether that’s software to detect skin cancer or a program that can pick the most viable embryo option for IVF treatment. Now, researchers are using AI scans to detect Alzheimer’s almost a decade earlier than doctors making a diagnosis based on symptoms alone.
Alzheimer’s is the most common form of dementia, affecting over 5 million Americans. It’s a progressive, neurodegenerative disease – patients might start off by feeling a little more forgetful or confused than usual, but their symptoms will worsen over time. Although there isn’t a known cure, drugs and lifestyle changes can be effective at slowing down and reducing symptoms when the disease has been discovered early.
In a study, published earlier this month, researchers developed a machine-learning algorithm to detect Alzheimer’s in brain scans 86 percent of the time. Even more impressively, it identified changes in the brain that showed mild cognitive impairment (MCI) 84 percent of the time.
Nicola Amoroso, Marianna La Rocco, and colleagues from the University of Bari, Italy, taught AI software to tell the difference between healthy and unhealthy brains using MRI scans from the Alzheimer’s Disease Neuroimaging Initiative. Each scan was split into several small sections, which were analyzed for neuronal connectivity. The researchers discovered that the algorithm was most effective at analyzing brain regions of 2,250 to 3,200 cubic millimeters – which just so happens to be the same size as anatomical structures associated with the disease (e.g. the amygdala and hippocampus), La Rocca told New Scientist.
Then it was time to test how well the AI could detect Alzheimer’s and MCI in a new batch of brain scans. In total, 148 scans (52 healthy, 48 with Alzheimer’s, and 48 with MCI) were used. Those with MCI developed Alzheimer’s between two-and-a-half and nine years after the scan was taken.
The algorithm’s high success rate showed it was able to pick up changes in the brain’s structure that predicted the development of Alzheimer’s up to nine years before symptoms emerged. It might be able to identify these changes even earlier, but the researcher’s only tested it on individual’s who developed Alzheimer symptoms within nine years.
Right now, there are cerebrospinal fluid analyses and brain imaging using radioactive tracers that can also detect early markers of Alzheimers and help identify people at a high risk of developing the disease. However, these are invasive, expensive, and not even available, meaning this new procedure makes for a fantastic alternative.
It is believed that by 2050, over 115 million people will develop Alzheimer’s, so finding affordable and accurate methods of diagnosing the disease early on when treatment and lifestyle changes are at their most effective is essential. The researchers hope that similar algorithms can be built to work on other degenerative diseases, such as Parkinson’s.