Telehealth Focused Rural Health Research Center Cooperative Agreement - Telehealth Research Center HRSA-25-045 Rural communities, which span 97% of U.S. land and house nearly 20% of the population, face significant healthcare challenges including limited access to specialty care, higher mortality rates, and fragmented service delivery. These challenges are often augmented by under-resourced systems, workforce shortages, and “place-neutral” health policies that fail to account for geographic variations in healthcare access. Despite the growth of telehealth, barriers persist—especially for older adults, Medicaid recipients, individuals with disabilities, and those in remote areas. Existing research has not sufficiently explored how to tailor telehealth policy, delivery, and outcomes to the unique needs of rural populations. The Center for Telehealth Research and Policy (C-TRaP) proposes a novel, future-focused approach to address these gaps by leveraging advanced Machine Learning (ML) and Artificial Intelligence (AI) methodologies to evaluate, optimize, and inform rural telehealth delivery. C-TRaP is a multidisciplinary, multi-institutional initiative led by the University of Missouri (MU), Michigan State University (MSU), and the University of Mississippi (UM)—three flagship institutions located in states with substantial rural populations. Our mission is to produce real-world, actionable insights that support generalizable, data-driven healthcare policy and practice. C-TRaP will conduct five interrelated studies using Medicaid claims, remote patient monitoring (RPM) data, and the Project ECHO (Extension for Community Healthcare Outcomes) platform. Collectively, these studies aim to: - Evaluate remote patient monitoring (RPM) effectiveness in reducing 30-day hospital readmissions for congestive heart failure (CHF) patients in rural settings, with a goal of demonstrating a 40% reduction by tailoring interventions to rural-specific needs. - Assess telehealth utilization trends among rural Medicaid beneficiaries before and after COVID-19 policy changes to determine sustained adoption and inform future state and federal policy modifications. - Analyze and quantify Project ECHO participation needed to make meaningful clinical practice transformations and improve decision-making for chronic pain management using generative AI and multimodal language models from recorded ECHO sessions and Medicaid claims data. - Understand telehealth adoption dynamics through mixed-method analysis of healthcare leaders and administrators across 34 North American ECHO hubs to identify drivers and barriers to early innovation uptake. - Develop and test a privacy-preserving federated learning (FL) data repository for Project ECHO, enabling decentralized AI model training and secure, compliant data sharing without moving raw data—supporting a scalable, secure, and interoperable tele-mentoring infrastructure. C-TRaP’s unique integration of ML/AI, federated data science, and implementation research fills a critical void in the literature by going beyond descriptive analysis to develop predictive, secure, and generalizable tools. By working in geographically diverse and predominantly rural regions—including Missouri, Illinois, Oklahoma, Wisconsin, and multiple ECHO sites across the U.S.—our findings will be highly generalizable. Importantly, this work will provide foundational evidence to inform sustainable telehealth policy, improve care delivery models, and advance health equity for rural populations.
