In-home wearable system to detect early-stage decompensation in heart failure patients - Project Summary/Abstract
In the U.S., heart failure (HF) affects over 6 million people and is one of the most common causes of
hospitalization. New technologies are needed to enable in-home monitoring to guide and treatment changes for
patients at risk of developing Acute Decompensated HF (ADHF). Early detection of decompensated HF often
relies on monitoring weight gain, but weight alone does not accurately gauge the fluid accumulation that predicts
worsening of HF. A device that can measure vital signs (including heart rates and respiratory rates), intrathoracic
fluid status (using thoracic bioimpedance), and heart rhythm, may allow for more accurate identification of the
early stages of acute decompensation in chronic HF patients. The multidisciplinary team from the University of
Massachusetts (UMass) Amherst, UMass Medical School, and the University of Connecticut proposes to develop
a novel device for in-home monitoring of HF patients who are at risk of decompensation. The central hypothesis
is that an innovative bioimpedance and electrocardiogram monitor with re-usable, non-wetted, and flexible
bioimpedance electrodes embedded in a wearable vest, used in conjunction with a smartphone and cloud server,
will continuously collect, transmit, and monitor key physiologic data. Devices running decision-support algorithms
will analyze these data to identify patients with an emergent HF decompensation that may be mitigated with
prompt medical attention. A Bioimpedance and Electrocardiogram Device (BED) attached to the back of the vest
collects 5 minutes of data once a day from the vest electrodes, calculates bioimpedance, and has fault-
tolerant assessment circuits to enable reliable data collection. Collected data consisting of heart rhythm, some
vital signs, intrathoracic fluid accumulation measurements, and information about the data reliability will be sent
to a smartphone from the BED via Bluetooth-Low-Energy (BLE) wireless communication. This data, together
with the patient's weight, and symptoms and signs noted in the application, such as shortness of breath or lower
leg swelling, will be recorded by patients and be sent to a cloud server via 4/5G/WiFi mobile networks. These
data will be used to develop a robust clinical decision support algorithm that accurately detects early ADHF. This
project aims to: A1.1) develop a wearable vest with reusable carbon-black and polydimethylsiloxane (CB/PDMS)
electrodes that capture 3-channel bioimpedance and electrocardiogram data; A1.2) develop a BED with fault-
tolerant circuit; A1.3) develop a smartphone application, to include a machine learning algorithm that uses the
collected physiological information for autonomous early ADHF detection; A2.1) establish a cloud infrastructure
that allows for the collection of the aforementioned data from the in-home setting along with associated data
reliability monitoring; and A2.2) evaluate the performance and usability of the system in a prospectively recruited
cohort study of patients with known HF. The clinical study will target a diverse HF population that are at high risk
for ADHF. A successful project will result in the design, testing, and clinical evaluation of a prototype telehealth
monitoring system to collect real-time data about cardiac risk factors for people with HF.
