Framework for Digital Health Phenotypes in Heart Failure: From Wearable Devices to New Sensor Technologies

Abstract

Consider these 2 scenarios: Two individuals with heart failure (HF) have recently established with your clinic and followed for medical management and risk stratification. One is a 62-year-old man with nonischemic cardiomyopathy due to viral myocarditis, an ejection fraction (EF) of 40%, occasional rate-limiting dyspnea, and comorbidities of atrial fibrillation and hypertension. The other is a 75-year-old woman with ischemic cardiomyopathy, an EF of 35%, a prior hospitalization 6 months ago, and persistent symptoms of edema and orthopnea. Both have expressed interest in remote patient monitoring (RPM) with wearable and digital health devices that are commercially available such as a smartwatch-ECG, weight scales, and blood pressure monitoring technologies. While there is enthusiasm from both patients and their clinical teams to engage in a technology-driven approach to care, important questions arise such as "What are the patient requirements for participation in digital health programs?", "Can we anticipate improvements in HF status and lower the risk of future HF events including hospitalizations?", "Do the same type of devices in different patients provide accurate information on physiologic changes toward individualized risk assessments?", and "What are the systematic approaches to integrate digital health workflows and datasets from RPM into clinical HF programs?". Given the importance of such questions, embracing new technologies, as a core competency of a modern health care system requires a deeper understanding of how effective digital health programs can be designed to meet the needs of patients and their clinical teams. In this review, we propose a new framework of "Digital Phenotypes in HF" for how new devices and sensors and their respective datasets can be used to guide treatment and to predict disease trajectories within the heterogeneity of HF. Our objectives are to generate a systematic approach to evaluate digital health devices as they relate to the next phase of RPM in HF, to critically analyze the literature, and to apply the lessons learned from digital devices through present-day, real-world evidence examples.

Keywords: Analytics; Clinical decision support; Digital health; Remote Patient monitoring; Sensors; Wearable.