Artificial intelligence could be a new diagnostic tool to predict dementia

Researchers from Exeter have found that machine learning algorithms can accurately predict dementia within two years compared to existing models. Findings are published today (Tuesday 14 December) in the journal JAMA Network Open.

Scientists looked at 15,307 memory clinic attendees in the US that did not have dementia at the start of the study.

Participants attended clinics between 2005 and 2015 and were followed up two years after their first appointment.

The machine learning algorithm analysed a range of participant data to predict dementia including family history, medical history and demographics for each person.

Of the 15,307 people who took part in the study, 1,568 developed dementia within two years after their initial assessment in the clinic.

The machine learning algorithms were able to predict, with 92% accuracy, who would develop dementia within two years of their first appointment at the clinic, performing better when compared to existing methods.

Algorithms were also able to classify a high number of people that are potentially misdiagnosed with dementia within two years of their clinic visit.

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.”

You can read the full paper ‘Performance of Machine Learning Algorithms for Predicting Progression to Dementia in Memory Clinic Patients’ in JAMA Network Open

Share with your followers!

. Read more below: Click To Tweet