AI May Help Identify Patients With Early-Stage Dementia

The Wall Street Journal reports that scientists are exploring whether artificial intelligence (AI) can help clinicians better identify patients with early-stage dementia. Researchers and companies are currently testing machine learning for mining and extracting meaning from vast, diverse datasets. According to the U.S. National Institute on Aging's (NIA) Nina Silverberg, having more and different types of data, combined with better methods of making sense of it, means "there is definitely an opportunity now that we just didn't have before." Much of the current research involves sifting through electronic-health records to determine what combination of risk factors most accurately reflects cognitive decline in patients. One NIA-funded study published in the Journal of the American Geriatrics Society analyzed electronic records of more than 16,000 medical visits of 4,330 participants in a Kaiser Permanente Washington health system. The researchers used a model that identified 31 factors associated with cognitive decline to cite more than 1,000 visits leading to a dementia diagnosis, including nearly 500 in which cognitive changes were previously overlooked in the health system. Duke University School of Medicine Professor P. Murali Doraiswamy explains that researchers want to use AI to assist rather than replace doctors. "This isn't a battle between AI and doctors, it's about how to optimize doctors' ability to deliver better care," he says.