Testing eRADAR: A New Algorithm to Identify Dementia
Author Information
Author(s): Sascha Dublin, Leah Karliner, Yates Coley, Deborah King, Clarissa Hsu, Sei Lee, Judith Walsh, Deborah Barnes
Primary Institution: Kaiser Permanente Washington Health Research Institute
Hypothesis
Can the eRADAR algorithm effectively identify individuals with undiagnosed dementia in primary care settings?
Conclusion
The eRADAR algorithm shows high accuracy in identifying individuals at risk for undiagnosed dementia, with significant acceptance of follow-up visits.
Supporting Evidence
- The eRADAR algorithm achieved C statistics of 0.79 to 0.84 for accuracy.
- Over 590 brain health visits have been conducted to date.
- 31% of high-risk individuals accepted a brain health visit.
Takeaway
Researchers created a computer program to help doctors find people who might have dementia but don't know it yet, and many people liked the follow-up visits.
Methodology
The study used machine learning to develop the eRADAR algorithm and implemented it in primary care clinics, inviting high-risk individuals for brain health visits.
Limitations
The primary outcome of dementia diagnosis will be assessed over a 12-month follow-up, which may limit immediate conclusions.
Participant Demographics
Older adults age 65+ without a documented dementia diagnosis or medication.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website