Researchers have created a complex algorithm that analyses MRI scans and notes structural changes to the brain caused by the disease, with accuracy of more than 80 per cent.AI algorithms can make predictions without being explicitly programmed so can learn to spot tell-tale signs of diseases that are not fully understood by scientists.
The latest exciting breakthrough news in AI was made by Marianna La Rocca of the University of Bari in Italy. Her algorithm was trained on 38 scans from patients with Alzheimer’s and on 29 from healthy people.
AI could tell the difference in the brains of healthy subjects and those with Alzheimer’s with 86 per cent accuracy.
It could also distinguish healthy patients from those with MCI who went on to develop Alzheimer’s with 84 per cent accuracy.
Alzheimer’s and other forms of dementia affect about 850,000 people in Britain and have replaced heart disease as the leading cause of death in England and Wales.
There is no cure at present but early diagnosis means patients can get treatment sooner and have longer to make care arrangements.
Doctors already use MRI scans to look for changes characteristic of Alzheimer’s but scientists believe artificial intelligence could help specialists to diagnose the conditions before changes are clearly visible.
Researchers believe the new technology could be used by doctors to predict Alzheimer’s and other diseases within a decade.
Dr La Rocca told New Scientist that AI-based testing would also be cheaper and more comfortable than invasive techniques, which look for “sticky” plaques and tangles of protein in the brain that have been linked to the disease.
AI could be used for more widespread screening of patients where there are concerns about possible Alzheimer’s.
Doug Brown, director of research at the Alzheimer’s Society, told The Times: “This study is the latest in a promising area of research, using technology to identify signs of dementia that may otherwise be incredibly hard to detect, even by experts.
“Early diagnosis for dementia is essential to ensure that people receive the treatment and support they need, so any technology that could aid with this is a really exciting prospect.
“At this stage though, the software is not accurate enough to be relied upon — further research is needed before it could be put into practice in the healthcare system.”
For more news on AI, keep reading iTMunch.