Communications of the ACM
AI May Help Identify Patients with Early-Stage Dementia
Researchers are studying whether artificial intelligence tools can be used to help clinicians better identify patients with early-stage dementia.
Credit: Philippe Lopez/Agence France-Presse/Getty Images
Scientists are exploring whether artificial intelligence can help clinicians better identify patients with early-stage dementia, with researchers and companies testing machine learning (ML) for mining and extracting meaning from vast, diverse datasets.
Much research involves sifting through electronic-health records to determine what combination of risk factors most accurately reflects cognitive decline.
A U.S. National Institute on Aging-funded study analyzed electronic records of more than 16,000 medical visits of 4,330 participants in a Kaiser Permanente Washington health system.
The researchers' model identified 31 factors associated with cognitive decline, flagging more than 1,000 visits leading to a dementia diagnosis.
Other studies have gauged written speech patterns for indicators of mental deterioration, and distinguished between cognitively impaired and healthy individuals; ML also has been used to forecast a patient's long-term dementia outcome, based on certain disease biomarkers.
From The Wall Street Journal
View Full Article - May Require Paid Subscription
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found