These algorithms were developed by researchers working in the Department of Public Health in Japan, and are used to detect Alzheimer's disease in patients while they participate in phone conversations, and the results of this study were published in the "PLOS ONE" website.
The researchers show that despite efforts worldwide, there is still no cure for Alzheimer's disease, which affects millions of people around the world.
In this new effort, researchers have turned to machine learning as a diagnostic aid, and so scientists have turned their attention to finding new ways to predict who will develop the disease.
In this new study, researchers replaced humans who listen and analyze phone conversations with a computer that runs a machine learning algorithm.
Various machine-learning algorithms were designed to study speech patterns.
All of them were taught to recognize signs of Alzheimer's disease using audio recordings, and the researchers found that they were, on average, good and did not provide any false results.
The researchers suggest that their algorithms could be used to provide a cheaper and more accessible form of early testing for Alzheimer's disease.