Predictive Analytics and Peer-Driven Intervention for Guideline-based Care for Sleep Apnea

University Of Arizona, Tucson AZ

Investigators

Linked publications & trials

Abstract

Obstructive sleep apnea (OSA) affects 12% of the US population and is associated with cardiovascular disease, reduced health-related quality of life (HR-QOL), increased all-cause mortality. However, nearly 80% of patients with OSA remain undiagnosed [QUALITY GAP #1]. Moreover, adequate adherence to continuous positive airway pressure (CPAP) therapy can improve HR-QOL and mood but the beneficial effects on cardiovascular outcomes are limited by poor CPAP adherence with nearly 54% of patients being non-adherent to CPAP therapy [QUALITY GAP #2]. The American Academy of Sleep Medicine (AASM) released evidence- based clinical practice guidelines and quality metrics for the improved diagnosis and treatment of OSA, but these have not been implemented in underserved populations. The overarching aim of this proposal is to institute a multi-level strategy with interventions aimed at both providers and patients in order to improve guideline based care for OSA in populations with health disparities. Specifically, in order to address the under- diagnosis of OSA, we will implement an electronic health record (EHR) based predictive analytics system that is similar to recently implemented early warning system that triggers guideline-based treatment of sepsis in hospitalized patients. The proposed EHR-based alert with reflex order sets will enable primary care physicians (PCPs) to adopt the AASM guidelines for diagnosing OSA. In approximately 220,000 patients we have found that lower neighborhood income is associated with lower CPAP adherence. Considering the time and access- related barriers in the PCP office, we believe that such health disparities in CPAP adherence need to be addressed by culturally-competent peer educators with OSA serving as ?peer-buddies?. In a recent study we found that CPAP adherence can be improved by a peer-driven intervention through an interactive voice response system (PDI-IVR). Whether PDI-IVR can improve adherence in underserved populations in low resource clinics is unclear. Specific Aim #1: To test an EHR-based tool to alert primary care physicians of the potential for OSA in order to improve the diagnosis of OSA in low resource clinics. Specific Aim #2: To test a peer-driven intervention with interactive voice response (PDI-IVR) system to improve treatment adherence in populations with health disparities. Specific Aim #3: To evaluate the dissemination and implementation of a multi-level intervention strategy aimed at improving the diagnosis and treatment of OSA in populations with health disparities. We are proposing a RCT that recruits 102 providers, 362 patients, and 50 experienced peer-buddies in an underserved population with an excess burden of sleep disorders (Medicaid and dual- eligible Medicare beneficiaries in Pima county, Arizona) that is aimed at addressing the health disparities in the diagnosis and treatment of OSA. We will use a systems-level intervention (EHR-based tool) that targets providers and a patient-level educational intervention (PDI-IVR system) that targets patients in order to increase delivery of guideline-based care to populations with health disparities and promote health equity.