Scientists have developed an artificially intelligent tool that can predict in four out of five cases whether people with early signs of dementia will remain stable or develop Alzheimer’s disease.
The University of Cambridge team says this approach could reduce the need for invasive and expensive diagnostic tests and improve treatment outcomes.
The main cause of dementia is Alzheimer’s disease, which accounts for 60-80% of cases.
Although early diagnosis is critical, as this is when treatments are 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 may be 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 that can predict whether and how quickly an individual with mild memory and thinking problems will progress to developing Alzheimer’s.
The algorithm distinguishes people with mild, stable cognitive impairment from those who have progressed to Alzheimer’s disease within three years.
It was able to correctly identify individuals who developed Alzheimer’s 82% of the time and correctly identify those who did not develop it 81% of the time.
The algorithm was about three times more accurate than standard clinical markers, such as gray matter atrophy, cognitive scores or clinical diagnosis.
