Artificial intelligence (AI) can identify Alzheimer's disease 10 years before doctors can discover the symptoms, according to new research.
A team of researchers in Italy developed an algorithm that can spot structural changes in the brain that are caused by the disease a decade before the signs become apparent.
The team from the University of Bari trained the AI by feeding in 67 MRI scans - 38 from Alzheimer's patients and 29 healthy patients - then asked it to analyse the neuronal connectivity to form an algorithm.
Following the training, the AI was then asked to process brains from 148 subjects - 52 were healthy, 48 had Alzheimer's disease and 48 had mild cognitive impairment (MCI) but were known to have developed Alzheimer's disease two and a half to nine years later.
According to the researchers, the AI diagnosed Alzheimer's disease 86 per cent of the time.
It could also tell the difference between healthy brains and those with MCI with an accuracy of 84 per cent.
Alzheimer's is a neurodegenerative disease that is the leading cause of dementia for the elderly, eventually leading to loss of memory and cognitive functions.
Although there is no cure for Alzheimer's disease, early diagnosis can allow people to start making lifestyle choices to slow the progression of the disease.
The Bari University research team now intends to extend the technique to help with the early diagnosis of neurodegenerative conditions such as Parkinson's disease.
http://www.nzherald.co.nz/technology/news/article.cfm?c_id=5&objectid=11923628
No comments:
Post a Comment