Scientists have developed an artificially intelligent tool able to predict in four cases out of five whether people with early signs of dementia will remain stable or develop Alzheimer’s disease. 

The team from the University of Cambridge says this approach could reduce the need for invasive and costly diagnostic tests and improve treatment outcomes. 

The main cause of dementia is Alzheimer’s disease, which accounts for 60-80% of cases. 

Although early detection is crucial – because this is when treatments are likely to be most effective – early diagnosis and prognosis may not be accurate without the use of positron emission tomography (PET) or lumbar punctures, which are expensive, invasive, and not always available. 

As a result, up to a third of patients may be misdiagnosed and others diagnosed too late for treatment to be effective. 

A team led by scientists from Cambridge’s Department of Psychology has developed a machine learning model able to predict whether and how fast an individual with mild memory and thinking problems will progress to developing Alzheimer’s. 

The algorithm distinguishes people with stable, mild cognitive impairment from those who progressed to Alzheimer’s disease within three years.  

It was able to correctly identify individuals who went on to develop Alzheimer’s in 82% of cases and correctly identify those who didn’t in 81% of cases. 

The algorithm was around three times more accurate than the standard clinical markers, such as grey matter atrophy or cognitive scores, or clinical diagnosis. 

The university’s Dr Ben Underwood said that memory problems are common as we get older. 

“In clinic, I see how uncertainty about whether these might be the first signs of dementia can cause a lot of worry for people and their families, as well as being frustrating for doctors who would much prefer to give definitive answers. 

“The fact that we might be able to reduce this uncertainty with information we already have is exciting and is likely to become even more important as new treatments emerge.” 

Senior author Professor Zoe Kourtzi added, "This has the potential to significantly improve patient well-being, showing us which people need closest care, while removing the anxiety for those patients we predict will remain stable. 

“At a time of intense pressure on healthcare resources, this will also help remove the need for unnecessary invasive and costly diagnostic tests.” 

Related reading: Cambridge, Medical Express