 Personalized Patient data and behavioral nudges to improve adherence to chronic cardiovascular medications
 Biography Overview Abstract Our objective in this project is to employ population level pharmacy data and delivery of nudges via cell phone text messaging and artificially intelligent (AI) interactive chat bot to improve medication adherence and patient outcomes in 3 integrated healthcare delivery systems (HCS): University of Colorado Health System (UCHealth), VA Eastern Colorado Health Care System (VA), and Denver Health Medical Center (DH). We will identify patients with chronic cardiovascular (CV) conditions taking medications to treat hypertension, atrial fibrillation, coronary artery disease, diabetes and/or hyperlipidemia. We will leverage pharmacy refill data to identify episodes of non-adherence through gaps in medication refills and randomize individuals to 1 of 4 study arms when they have a first refill gap: 1) usual care; 2) generic text message reminder; 3) tailored and engaging text messages optimized to facilitate behavior change; or 4) optimized text messages plus a pre- programmed AI interactive chat bot designed to support identification and resolution of barriers to medication refill and adherence. In the UG3 phase (year 1), we will develop and program a theoretically informed technology-based (a) text message library and (b) chat bot content library using multiple and iterative N of 1 within subject studies to optimize content for a range of diverse patients. These outcomes will inform a pilot intervention to demonstrate feasibility of delivering the intervention and preliminary effects in all 3 HCS. We will also engage patient, provider and health systems stakeholders in designing, refining, and implementing the pilot intervention. In the UH3 phase (years 2-5), we will conduct a pragmatic patient-level randomized intervention across 3 HCS to improve adherence to chronic CV medications. We will evaluate the intervention using a mixed methods approach and apply the RE-AIM (reach, effectiveness, adoption, implementation, and maintenance) framework. In addition, we will assess the context and implementation processes to inform local tailoring, adaptations and modifications, and eventual expansion of the intervention.
Time
|