AI programme spots Alzheimer’s years before confirmed diagnosis
Artificial intelligence could hold the key to identifying patients with hidden early signs of dementia.
Artificial intelligence (AI) can be used to spot early signs of Alzheimer’s disease years before a patient would normally be diagnosed, research has shown.
Scientists conducting a small pilot study trained a self-learning computer programme to recognise tell-tale features in brain scans too subtle for humans to see.
The system was able to detect the beginnings of Alzheimer’s in 40 patients an average of more than six years before they were formerly diagnosed.
Your beautiful, complex brain is fragile and requires constant upkeep, like a garden. What happens when things go wrong? Alan Titchmarsh explains. pic.twitter.com/n3cTDPcm1t— AlzheimersResearchUK 🍊 (@AlzResearchUK) November 6, 2018
British AI expert Professor Noel Sharkey, from the University of Sheffield, said of the US findings: “This is exactly the sort of task that deep learning is cut out for – finding high level patterns in data.
“Although the sample sizes and test sets were relatively small, the result are so promising that a much larger study would be worthwhile.”
The American researchers trained the “deep learning algorithm” using more than 2,100 PET (positron emission tomography) scans from 1,002 patients.
PET scans measure metabolic activity in the brain by tracking the uptake of a radioactive glucose compound injected into the blood.
Research has linked the development of Alzheimer’s to changes in metabolism in certain brain regions, but these can be difficult to spot.
“Deep learning” AI involves a computer programme acquiring knowledge by example, in much the same way as humans do.
We were very pleased with the algorithm's performance. It was able to predict every single case that advanced to Alzheimer's disease Dr Jae Ho Sohn
Through deep learning, the Alzheimer’s algorithm was able to teach itself to recognise metabolic patterns in brain scans that indicated disease.
As a final test, the algorithm was given a set of 40 scans from 40 patients it had never studied before.
It proved to be 100% accurate at detecting Alzheimer’s disease an average of more than six years prior to a patient’s final diagnosis.
Dr Jae Ho Sohn, a member of the team from the University of California at San Francisco, said: “We were very pleased with the algorithm’s performance. It was able to predict every single case that advanced to Alzheimer’s disease.”
Early detection of Alzheimer’s could open the door to new ways of slowing down or even halting progression of the disease.
The research is published in the latest issue of the journal Radiology.
Dr Carol Routledge, from the charity Alzheimer’s Research UK, said: “The diseases that cause dementia begin in the brain up to 20 years before any symptoms start to show, presenting a vital window of opportunity for us to intervene before widespread damage occurs.
“This study highlights the potential of machine learning to assist with the early detection of diseases like Alzheimer’s, but the findings will need to be confirmed in much larger groups of people before we can properly assess the power of this approach.”