Mild cognitive impairment (MCI) is often an early sign of Alzheimer’s disease, and though it usually has no clear symptoms early on, it can sometimes be identified with brain scans – known as functional magnetic resonance imaging (FMRI) – even before symptoms appear.
However, identifying MCI with FMRI is both time consuming and expensive.
Now researchers have used deep learning technology – a type of artificial intelligence – that could potentially speed up the process, and they are able to detect MCI with better than 99% accuracy.
The research involved using a deep learning model to classify thousands of images of the brains of 138 subjects with various stages of MCI. The model was able to identify MCI accurately in more than 99% of cases.
Alzheimer’s is a debilitating, progressive disease that has no cure.
Approximately 24 million people currently have Alzheimer’s disease, and that number is expected to double every 20 years.
It’s widely accepted that early diagnosis means the patient is more likely to benefit from treatment.
The aim is for the algorithm to be developed into software that could analyse data from vulnerable groups, such as the over 65s, those with a history of brain injury or those with high blood pressure.
The software could be used to pick up anomalies that could enable earlier diagnoses of Alzheimer’s.
The researchers say the algorithm should not be relied upon alone for a diagnosis, but it can provide useful information quickly and affordably, meaning the patient can have a diagnosis and treatment more quickly.
“Of course, we don’t dare to suggest that a medical professional should ever rely on any algorithm 100%”, said Maskeliūnas.
“Think of a machine as a robot capable of doing the most tedious task of sorting the data and searching for features.
“In this scenario, after the computer algorithm selects potentially affected cases, the specialist can look into them more closely, and at the end, everybody benefits as the diagnosis and the treatment reaches the patient much faster.”
While there is still no cure for Alzheimer’s, this research is another promising step on the road to better treatments.
