Two different machine learning algorithms described in Artificial Intelligence in Medicine and the Journal of the American Geriatrics Society accurately identified patients with Alzheimer's disease and related dementia from structured and unstructured EHR data, providing a scalable, inexpensive screening method, says lead researcher Malaz Boustani. Both a natural language processing algorithm and a random forest model based on decision trees accurately predicted the onset of dementia, and medical notes proved to be the most valuable data source for identifying high-risk patients.
Algorithms analyze EHR data to predict Alzheimer's
Sign up for SNMMI SmartBrief
Nuclear medicine and molecular imaging news
Get the intelligence you need: news and information that is changing your industry today, hand-curated by our professional editors from thousands of sources and delivered straight to your inbox.