Artificial Intelligence (AI) can predict who will develop dementia within two years with 92 per cent accuracy, a new study has revealed.
And as well as its high degree of success in accurately telling who will go on to develop dementia, the algorithm could also help reduce the number of people who may have been wrongly diagnosed.
The study, using data from more than 15,300 patients in the United States, reveals the role of machine learning in spotting hidden patterns in data to learn who is most at risk.
Researchers from the University of Essex analysed data from people who attended a network of 30 National Alzheimer’s Coordinating Center memory clinics in the US.
The attendees did not have dementia at the start of the study, though many were experiencing problems with memory or other brain functions.
In the study timeframe between 2005 and 2015, one in ten attendees (1,568) received a new diagnosis of dementia within two years of visiting the memory clinic.
The research found that the machine learning model could predict these new dementia cases with up to 92 per cent accuracy – and far more accurately than two existing alternative research methods.
The researchers also found for the first time that around eight per cent (130) of the dementia diagnoses appeared to be made in error, as their diagnosis was subsequently reversed.
Machine learning models accurately identified more than 80 per cent of these inconsistent diagnoses. AI can not only accurately predict who will be diagnosed with dementia, found the study – which was funded by Alzheimer’s Research UK – it also has the potential to improve the accuracy of these diagnoses.
Professor David Llewellyn, an Alan Turing Fellow based at the University of Exeter, who oversaw the study, 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.”
Dr Rosa Sancho, head of research at Alzheimer’s Research UK, said: “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.
“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.”
Dr Janice Ranson, Research Fellow at the University of Exeter added “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 found that machine learning works efficiently, using patient information routinely available in clinic, such as memory and brain function, performance on cognitive tests and specific lifestyle factors.
The team now plans to conduct follow-up studies to evaluate the practical use of the machine learning method in clinics, to assess whether it can be rolled out to improve dementia diagnosis, treatment and care.
- Insight2 weeks ago
Securing a diagnosis – ‘I was relieved but broken’
- Interviews1 week ago
Living with a brain tumour could get a little bit easier
- Parkinson's3 weeks ago
Kinetikos Health – digital clinical support for Parkinson’s patients
- Insight2 weeks ago
Nutrition and maximising rehab outcomes in older adults
- MS2 weeks ago
Video: “How MS inspired my own Forrest Gump story”
- Research2 weeks ago
Robotics could be the future of stroke surgery
- Insight4 weeks ago
Re:Cognition aims to help thousands of Americans affected by neuro conditions
- Brain injury3 weeks ago
Repetitive head impacts directly linked to CTE, study reveals