With artificial intelligence we will know who will develop dementia in 2 years


What a British study reveals through artificial intelligence for predicting dementia

British artificial intelligence system can accurately predict, specifically 92% which people with memory problems will eventually develop dementia within the next two years. This is another indication that artificial intelligence has enormous potential to make it possible to diagnose various diseases at an earlier stage. The goal is not only to diagnose impending dementia more early, but also reduce the number of people misdiagnosed with dementia.

His researchers University of Exeter, led by Professor David Lewellin, who published the article in the American Medical Journal JAMA Network Open used data from 15,307 people with an average age 72 years and memory problems (of which 1,568 were diagnosed with Alzheimer’s or other forms of dementia within the next two years) to “train” the new machine learning algorithm to identify precursors symptoms of dementia.

The “Smart” system he learned to discern hidden clues in the data, which the human eye, even of a neurologist or other specialist, is unable to recognize. In addition, 130 diagnoses (8% of the total) turned out to be wrong, as they were subsequently overturned. Of these false positive cases of dementia, the algorithm was able to correctly diagnose that 84% actually had nothing to do with dementia. Therefore, the system can not only distinguish who may develop neurodegeneration in the brain in the future, but also improve the accuracy of the diagnosis, so as not to diagnosed as a patient someone who is not. “We are now able to teach computers to accurately predict who is going to develop dementia within the next two years.

“We are also pleased to see that the machine learning method we have developed is capable of identifying patients who may have been misdiagnosed,” said Lewellin. The new system is to be further studied to evaluate its practical utility and confirm that it can clinically improve the diagnosis and treatment of dementia.

It is undoubtedly a great application for the prediction of the disease and certainly encouraging as it paves the way for further research around the factors that can cause memory problems and repressive processes after the onset of the disease.

See also: K. Mitsotakis and Mareva in an exhibition at the Gallery of the Municipality of Athens


Leave A Reply

Your email address will not be published.