Menu

Nominate your Able2UK heroes and losers

Want to nominate somebody as an Able2UK Hero or Loser?  Tweet us @Able2UK with #Able2Hero or #Able2Loser with your suggestions!

Algorithm may detect early signs of Alzheimer’s

picture of a brain inside a person's skull
picture of a brain inside a person's skull Image credit: newsweek.com

For years research has tried to detect Alzheimers in its early stages, now scientists at Kaunas University of Technology (KTU) believe they are one step closer to diagnose the disease quicker leading to potential treatment to slow the illness down.

Incipient Alzheimer’s disease (AD) develops from Mild cognitive impairment (MCI) which is picked up in functional MRI (fMRI) scans, but they are difficult to spot.

Not all cases of MCI lead to Alzheimer’s, but in a majority of cases patients with the condition will go on to develop the disease.

If a person is diagnosed with early stages of AD they have a greater chance benefitting from treatment.

Scientists at KTU have developed a deep learning algorithm that successfully detected MCI in a small study.

Chief researcher Dr. Dr. Rytis Maskeliūnas told Medical News Today: “Medical professionals all over the world attempt to raise awareness of an early Alzheimer’s diagnosis, which provides the affected with a better chance of benefiting from treatment.”

A deep learning algorithm susses out how to detect patterns in data which are either too small or complicated for even the most professional scientist.

The team at KTU tweaked an existing algorithm known as ResNet 18 in order to detect MCI which turned out to be 99.99% accurate and 99.95% accurate distinguishing between late MCI and AD, and between MCI and early MCI.

When asked the likelihood of the real world accuracy of the algorithm Dr. Maskeliūnas said: “I’d say a reliable 85+% would still be of benefit for a medical professional, reducing [their] workload on the analysis of data.”

“At this stage we’re working on fine-tuning algorithms, and despite having some result on a controlled dataset gathered by others, it is very likely that we’ll still have to rework it to account for variations in real life-ish data.”

Claire Sexton, DPhil, director of scientific programs and outreach at the Alzheimer’s Association, stressed despite the findings it is still too early to speculate how affective the algorithm’s value is.

Dr Sexton said: “This is an interesting but small (25 participants with Alzheimer’s) study. As a result, we cannot draw any conclusions yet about the proposed new diagnostic technique.”

It is thought that around 5% of people living with Alzheimer’s in the UK are under 65.