Yes, Artificial Intelligence can accurately predict with 92% accuracy which people will develop dementia within two years.
A new study suggests that artificial intelligence can accurately predict which people who attend memory clinics would develop dementia within two years with 92 percent accuracy.
Using data from over 15,300 individuals in the United States, the University of Exeter discovered that a type of artificial intelligence known as machine learning can effectively predict who would get dementia.
The method works by detecting hidden patterns in data and determining who is most vulnerable. The study, which was financed by Alzheimer’s Research UK and published in JAMA Network Open, also revealed that the algorithm could help reduce the number of people who have been wrongly diagnosed with dementia.
The researchers looked at data from participants who went to a network of 30 memory clinics run by the National Alzheimer’s Coordinating Center in the United States. The participants did not have dementia at the outset of the trial, although many of them had memory or other cognitive issues.
Between 2005 and 2015, one out of every ten attendees (1,568) got a new dementia diagnosis within two years of visiting the memory clinic. According to the findings, the machine learning model could reliably predict these new dementia cases with up to 92 percent accuracy — significantly better than two other research approaches.
The researchers also discovered, for the first time, that around 8% (130) of dementia diagnoses looked to be made in error, as their diagnosis was later reversed. More than 80% of these contradictory diagnoses were correctly detected by machine learning algorithms. Not only can artificial intelligence anticipate who will be diagnosed with dementia, but it also has the potential to increase the accuracy of these diagnoses.
“We’re now able to teach computers to accurately predict who will go on to develop dementia within two years,” said Professor David Llewellyn, an Alan Turing Fellow based at the University of Exeter, who directed the project, adding, “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.”
Dr Janice Ranson, Research Fellow at the University of Exeter said “We know that dementia is a highly feared condition. Embedding machine learning in memory clinics could help ensure diagnosis is far more accurate, reducing the unnecessary distress that a wrong diagnosis could cause.”
The researchers discovered that machine learning works effectively by utilizing patient information that is commonly available in clinics, such as memory and brain function, performance on cognitive tests, and certain lifestyle characteristics. The team now intends to undertake follow-up research to investigate whether the machine learning technology can be used in clinics to improve dementia diagnosis, treatment, and care.
“Artificial intelligence has huge potential for improving early detection of the diseases that cause dementia and could revolutionise the diagnosis process for people concerned about themselves or a loved one showing symptoms,” said Dr Rosa Sancho, Head of Research at Alzheimer’s Research UK.
“This technique is a significant improvement over existing alternative approaches and could give doctors a basis for recommending life-style changes and identifying people who might benefit from support or in-depth assessments.”
Source: JAMA Network Open
Image Credit: Getty
You were reading: Can AI predict who will develop dementia in the future?