Study Shows How AI Can Predict Who Will Develop Dementia

A new large-scale study has concluded that artificial intelligence (AI) can predict which people who attend memory clinics will develop dementia within two years. The AI can make this prediction with a 92 percent accuracy rate.

The study relied on data from over 15,300 patients in the United States, and the research was carried out by the University of Exeter. 

Identifying Hidden Patterns 

The technique first identifies hidden patterns in the data before learning who is most at risk. The algorithm can also help reduce the number of people who may have been falsely diagnosed with dementia. 

The study was published in JAMA Network Open and funded by Alzheimer’s Research UK. 

The researchers analyzed the data from people who attended a network of 30 National Alzheimer’s Coordinating Center memory clinics in the US. The attendees, which didn’t have dementia at the start of the study, were experiencing various problems related to memory and brain function. 

The study took place between 2005 and 2015, and one in ten participants received a new diagnosis of dementia within two years of visiting the memory clinic. The machine learning model, with its 92 percent accuracy, was far more accurate at predicting these cases than two other existing research methods. 

Reversing Wrongful Diagnosis 

Another brand new finding from the study was that around eight percent of the dementia diagnoses appeared to be an error, with the diagnosis eventually being reversed. Out of these inconsistent diagnoses, the machine learning algorithm was able to accurately identify over 80 percent of them. 

Professor David Llewellyn is an Alan Turing Fellow based at the University of Exeter. He oversaw the new study. 

“We're now able to teach computers to accurately predict who will go on to develop dementia within two years,” Prof. Llewellyn said “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 is Research Fellow at the university.

“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,” Dr. Ranson said. 

The team will now look to carry out follow-up studies to evaluate the practical use of the machine learning method in clinics. 

Dr. Rosa Sancho is Head of Research at Alzheimer’s Research UK. 

“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,” Sancho said. “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.”