Innovations in artificial intelligence (AI) are being developed that could drastically reduce the time it takes for doctors to diagnose a patient with Alzheimer's Disease.
New research has been carried out by the Radiology & Biomedical Imaging Department at the University of California in San Francisco (UCSF) that has used self-learning computer software to recognise features in brain scans that are too subtle for human doctors to see.
The results of the study showed that AI-supported insights could help doctors to diagnose the early signs of Alzheimer's Disease in patients up to six years sooner that has previously been the case.
"Differences in the pattern of glucose uptake in the brain are very subtle and diffuse," said study co-author Dr Jae Ho Sohn. "People are good at finding specific biomarkers of disease, but metabolic changes represent a more global and subtle process."
The use of AI to show signs of changes in metabolism in the brain has the potential to be a major breakthrough in early diagnosis for the disease, with the researchers training the deep learning algorithm via more than 2,100 PET (positron emission tomography) scans from 1,002 patients.
As a test, the algorithm was given 40 scans from 40 patients it had never studied before. It proved to be 100 per cent effective in its ability to diagnose Alzheimer's Disease an average of more than six years prior to a patient's final diagnosis in these cases.
"We were very pleased with the algorithm's performance," Dr Sohn concluded. "It was able to predict every single case that advanced to Alzheimer's Disease."
Responding to the research, Dr Carol Routledge, from the charity Alzheimer's Research UK, stated: "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."
She added that the changes in brain chemistry that highlight the early signs of Alzheimer's Disease can begin in patients up to 20 years prior to the full onset of this debilitating condition. It is therefore highly beneficial to be able to detect these changes much sooner, ultimately helping to deliver improved treatment options and outcomes for patients.
Professor Noel Sharkey, emeritus professor of artificial intelligence and robotics at the University of Sheffield, told Science Media Centre: "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 results are so promising that a much larger study would be worthwhile."
Future research is now set to include training the deep learning algorithm to look for patterns associated with the accumulation of beta-amyloid and tau proteins, abnormal protein clumps and tangles in the brain that are further markers specific to Alzheimer's Disease.
Full details of the UCSF study have been published in the November edition of the journal Radiology.