The performance of artificial intelligence for dementia prediction is at the core of the University of Exeter study

Being able to predict who will suffer from dementia with precision thanks to artificial intelligence. This is the research topic of a team of researchers from the University of Exeter in the UK. The results of their study were published on JAMA Network Open and show how they developed machine learning algorithms that can predict the incidence of dementia over 2 years. Data from more than 15,000 US patients were integrated, showing that the AI ​​systems were very efficient and that 92% of the results were correct.

Among patients in clinics that treat memory disorders like Alzheimer’s disease, for example, those with dementia at the start of treatment are a minority. The challenge for clinicians is identifying patients who are at risk of developing dementia. So far, they have relied on mild cognitive impairment (MCI) during the initial evaluation to decide on an appropriate follow-up for an upcoming dementia.

Machine learning makes it possible to exploit complex masses of data. These algorithms can integrate information not normally used by clinics, such as advanced neuroimaging, genetic testing, and cerebrospinal fluid biomarkers, etc. On the other hand, researchers and specialists benefit from this clinical application.

Algorithms with 92% accuracy

The Exeter researchers’ study looked at the possibility that machine learning algorithms predict dementia at 2 years and compare these predictions with existing models. To do this, they used data from 15,307 patients without dementia at the beginning of the study, treated in 30 clinics that treated memory disorders of the US National Alzheimer’s Coordinating Center between 2005 and 2015.

They then implemented four ML algorithms: logistic regression (LR), support vector machine (SVM), random forest (RF), and gradient-driven tree (XGB) to classify patients according to whether or not they were likely to develop dementia.

1,568 of these patients were diagnosed with dementia 2 years after their first visit in those 10 years, or about 10%, which machine learning algorithms that require only 6 variables predicted with an accuracy of up to 92%. These models even made it possible to reveal 80% of the diagnostic errors, which according to the researchers were of the order of 8% (130 cases corrected after finding the error).

Professor David Llewellyn, the Alan Turing Fellow of the University of Exeter, said:

“Now we can teach computers to accurately predict who will develop dementia two years from now. We are also excited to learn that our machine learning approach has helped identify patients who may have been misdiagnosed.

This offers an opportunity to reduce the guesswork in clinical practice and dramatically improve the diagnostic process, helping families access the support they need as quickly and accurately as possible. “

The conclusion of this study is that the ML models are more reliable in their prediction of dementia incidents at 2 years than other existing models. On the other hand, six key dementia risk factors identified in this study have the potential to improve clinical practice and decision-making. Dr Janice Ranson, a researcher at the University of Exeter School of Medicine, said:

“We know that dementia is a very feared disease […] Incorporating machine learning into memory clinics could help ensure that diagnosis is much more accurate, reducing unnecessary distress that a misdiagnosis could cause.

References: Performance of Machine Learning Algorithms to Predict Progression to Dementia in Memory Clinic Patients, Charlotte James, Janice M. Ranson, Richard Everson, David J. Llewellyn – JAMA Netw Open. 2021; 4 (12): e2136553. doi: 10.1001 / jamanetworkopen.2021.36553

PHP Script, Elementor Pro Weadown, WordPress Theme, Fs Poster Plugin Nulled, Newspaper – News & WooCommerce WordPress Theme, Wordfence Premium Nulled, Dokan Pro Nulled, Plugins, Elementor Pro Weadown, Astra Pro Nulled, Premium Addons for Elementor, Yoast Nulled, Flatsome Nulled, Woocommerce Custom Product Ad, Wpml Nulled,Woodmart Theme Nulled, PW WooCommerce Gift Cards Pro Nulled, Avada 7.4 Nulled, Newspaper 11.2, Jannah Nulled, Jnews 8.1.0 Nulled, WP Reset Pro, Woodmart Theme Nulled, Business Consulting Nulled, Rank Math Seo Pro Weadown, Slider Revolution Nulled, Consulting 6.1.4 Nulled, WeaPlay, Nulledfire

Back to top button