The machine learning algorithm predicted new dementia cases with up to 92% accuracy, significantly more precise than two existing alternative research methods, the team found.

 

Dementia misdiagnoses

 

The researchers also found for the first time that around 8% (130) of the dementia diagnoses appeared to be made in error, as the diagnosis was later reversed.

 

Machine-learning models accurately identified more than 80% of these inconsistent diagnoses, according to the study, published in JAMA Network Open.

 

AI can not only accurately predict who will be diagnosed with dementia, but has the potential to improve the accuracy of the diagnoses, the research suggests.

 

There are over 55 million people worldwide living with dementia in 2020, according to Alzheimer's Disease International.

 

And the organisation believes this number will almost double every 20 years, reaching 78 million in 2030 and 139 million in 2050.

 

Machine learning uses patient information routinely available in the clinics, such as memory and brain function, performance on cognitive tests and specific lifestyle factors.

 

Professor David Llewellyn, an Alan Turing fellow based at the University of Exeter, said: "We're now able to teach computers to accurately predict who will go on to develop dementia within two years.

 

"We're also excited to learn that our machine-learning approach was able to identify patients who may have been misdiagnosed.

 

"This has the potential to reduce the guesswork in clinical practice and significantly improve the diagnostic pathway, helping families access the support they need as swiftly and as accurately as possible."

 

The future of diagnosing dementia

 

Researchers hope to continue their research to understand the practical use of AI technology within clinics.

 

"Artificial intelligence has huge potential for improving early detection of the diseases," said Dr Rosa Sancho, head of research at Alzheimer's Research UK.

 

"[This] could revolutionise the diagnosis process for people concerned about themselves or a loved one showing symptoms," she added.