The prevalence of Alzheimer?s disease (AD) and AD-related dementias (ADRD) is expected to triple by 2050, contributing to decreased quality of life, increased medical care utilization, and additional burden on an already stressed primary care system. Many clinicians lack confidence to assess, diagnose and manage cognitive impairment (CI), and more than 50% of patients with CI are undiagnosed. Unfortunately, studies show that even in settings with high rates of standardized CI screening, very few patients who screen positive have documentation of any clinician follow-up action. To address these important problems, in phase 1 (R61) of this project, we will develop and validate a machine learning model (called MC-PLUS) using results from brief Mini- Cog (MC) screens completed routinely at Annual Medicare Wellness exams and electronic health record (EHR) data to identify patients at elevated risk of a future dementia diagnosis (AD/ADRD). We will also develop and validate a web-based and EHR-integrated CI clinical decision support (CI-CDS) system to engage patients and clinicians in conversation about elevated dementia risk, and to give clinicians the confidence and tools they need to diagnose and manage CI. Both MC-PLUS and the CI-CDS system will be added into an existing web-based CDS platform that has high use rates and primary care clinician satisfaction, and is already seamlessly integrated within the EHR. This CDS platform improves outcomes for patients with chronic diseases such as diabetes and high cardiovascular risk as shown in published studies. We will systematically validate the CI-CDS system with expert champions prior to conducting a pilot test at one primary care clinic. After milestones for success are demonstrated, we will begin phase 2 (R33), a large pragmatic trial with 30 primary care clinics randomized to receive CI-CDS or usual care (UC). We will evaluate change in clinician confidence in CI detection and care management in CI-CDS compared to UC clinics. If successful, the CI-CDS system will improve rates of new CI diagnosis and narrow existing sociodemographic disparities in adults with elevated dementia risk identified by MC-PLUS at index visit in CI-CDS compared to UC clinics. We will evaluate the impact of the intervention on care management and care plans using EHR data and chart audits. We will assess determinants of clinician actions in response to the CDS system using behavior change theory and technology acceptance constructs, and conduct phone surveys of patient and caregiver dyads to evaluate intervention effects on feelings of preparedness for decision making and distress. The CI-CDS system is immediately scalable to large numbers of patients through the existing non-commercialized CDS platform already in use for millions of patients in care systems spanning 14 states. The CDS system implemented as described could maximize return on massive investments that have been made in EHR systems, and provide a prototype to rapidly and consistently translate evolving evidence-based CI guidelines into personalized CI care and guidance within primary care.
Most experts advocate for early detection of cognitive impairment (CI) so that patients and caregivers can be prepared for making difficult decisions and to improve quality of life, but studies show that screening alone isn?t sufficient to change clinician actions related to early detection. Using predictive modelling developed with machine learning methods and sophisticated clinical decision support (CDS) tools, it is possible to identify patients at elevated risk for CI and make it much easier for primary care to engage and support patients and caregivers in meaningful care planning. In this project, we implement and evaluate a low-cost, highly scalable CI-CDS system integrated within the electronic health record that has high potential to improve early CI detection and care and translate massive public and private sector investments in health informatics into tangible health benefits for large numbers of people.
