Observational Study Designed to Detect Decompensation of Congestive Heart Failure (dCHF) Using a Non-Invasive Wearable Device

Overview

This is a prospective, observational pilot study designed to develop a mathematical algorithm capable of predicting decompensation of congestive heart failure (dCHF) using physiologic data collected from a non-invasive wearable device. Participants with a remote hemodynamic pulmonary artery pressure monitor will wear a wearable device continuously for up to 12 months. Wearable data will be analyzed in relation to the hemodynamic monitor defined sentinel events of heart failure decompensation to identify predictive signal patterns. Optional biospecimen (DNA, blood, urine) and voice sample collection will support future biomarker discovery.

Participants with chronic congestive heart failure and using a pulmonary artery pressure monitor will be enrolled and followed for a minimum of 6 months and up to 12 months. Daily pulmonary artery (PA) pressures obtained via the remote monitoring device will serve as the reference standard for identifying decompensated CHF events ("sentinel events"), defined by sustained elevations in PA diastolic pressure associated with medication changes by the clinical care team. Physiologic data from the wearable-including heart rate, heart rate variability, sleep metrics, activity levels, oxygen saturation and temperature-will be collected continuously and analyzed in the 1-7 days preceding and following sentinel events. Time-series statistical methods and machine-learning models will be used to develop a predictive algorithm for dCHF. Participants may opt in to optional biospecimen collection (cheek swab DNA, plasma, urine) and weekly voice recordings to support future research into biomarkers and digital phenotypes associated with heart failure decompensation. The wearable data are not used for clinical decision-making, and all participants continue to receive standard heart failure care.

Conditions