A screening tool embedded in the electronic health record can help detect older primary care patients at risk of having undiagnosed dementia, according to a real-world validation study conducted in two large US health systems.
“Strong performance” of eRADAR in both health systems indicates the tool may be useful for identifying patients at risk of undiagnosed dementia in a wide range of health care settings,” R. Yates Coley, PhD, with Kaiser Permanente Washington Health Research Institute, Seattle , told Medscape Medical News.
Coley presented the study results at the Alzheimer’s Association International Conference (AAIC) 2022. The study was also published online in the Journal of General Internal Medicine.
Hidden Dementia Common, Risky
About 6.2 million adults in the US are currently living with dementia, yet only about half have received a diagnosis, putting them as risk for unmet medical and supportive care needs as well as safety issues such as car accidents.
“There is a need for low-cost strategies that can be implemented on a large scale to target older adults who may benefit from dementia screening. Our tool meets this need — eRADAR uses routinely collected clinical data to identify people at risk of having undiagnosed dementia ,” Coley said.
eRADAR stands for EHR Risk of Alzheimer’s and Dementia Assessment Rule. It uses 31 clinical factors routinely collected in the EHR including dementia-related symptoms, healthcare utilization patterns, medications, and dementia risk factors to determine risk of undiagnosed dementia.
Participants in the validation study included 129,315 members of Kaiser Permanente Washington (KPWA), an integrated health system providing insurance coverage and medical care, and 13,444 primary care patients at University of California San Francisco Health (UCSF), an academic medical system.
All participants were aged 65 years or older with no prior EHR documentation of dementia diagnosis. The researchers gauged performance of eRADAR scores for predicting EHR documentation of dementia diagnosis within 12 months.
A total of 7631 dementia diagnoses were observed at KPWA (11.1 per 1000 person-years) and 216 at UCSF (4.6 per 1000 person-years).
eRADAR showed “strong external validity” for detecting undiagnosed dementia, with an area under the curve of 0.84 (95% CI, 0.84 to 0.85) at KPWA and 0.79 (95% CI, 0.76 to 0.82) at UCSF, the researchers report in their paper.
Using the 90th percentile as the cut point for identifying high-risk patients, eRADAR sensitivity was 54% (95% CI, 53% to 56%) at KPWA and 44% (95% CI, 38% to 51%) at UCSF.
Ongoing Validation, Testing
“Our findings affirm the generalizability of eRADAR from a research sample to real-world clinical populations,” the authors write.
They add it is important to note that for this large-scale validation study, it was not feasible to conduct universal cognitive screening. As an alternative, they evaluate how well the eRADAR model predicted future dementia diagnoses in the EHR.
The research team is now offering a pragmatic randomized trial at KPWA UCSF to evaluate the impact to cognitive assessments identified to be at high-risk of undiagnosed dementia.
“We will be examing dementia diagnosis rates and other healthcare utilization as well as to understand qualitative research factors that can facilitate effective implementation of the eRADAR tool into clinical routine practice,” said Coley.
Reached for comment, Chris Weber, PhD, Alzheimer’s Association director of global science initiatives, said eRADAR “may provide healthcare providers another tool to identify individuals with symptoms of dementia who may need further testing, and underscores the importance of an early and accurate diagnosis.” “
“It may also help identify potential participants for clinical trials. More research is needed to validate this measure in a diverse population,” Weber said.
This research was supported by the National Institutes of Health, National Institute on Aging. Coley and Weber have disclosed no relevant financial relationships.
Alzheimer’s Association International Conference (AAIC) 2022. Presented August 4, 2022.
J Gen Intern Med. Published online July 29, 2022. Abstract
For more Medscape Psychiatry news, join us on Facebook and Twitter.