Passive longitudinal weight and cardiopulmonary monitoring in the home bed

Abstract

Home health monitoring has the potential to improve outpatient management of chronic cardiopulmonary diseases such as heart failure. However, it is often limited by the need for adherence to self-measurement, charging and self-application of wearables, or usage of apps. Here, we describe a non-contact, adherence-independent sensor, that when placed beneath the legs of a patient’s home bed, longitudinally monitors total body weight, detailed respiratory signals, and ballistocardiograms for months, without requiring any active patient participation. Accompanying algorithms separate weight and respiratory signals when the bed is shared by a partner or a pet. Validation studies demonstrate quantitative equivalence to commercial sensors during overnight sleep studies. The feasibility of detecting obstructive and central apneas, cardiopulmonary coupling, and the hemodynamic consequences of non-sustained ventricular tachycardia is also established. Real-world durability is demonstrated by 3 months of in-home monitoring in an example patient with heart failure and ischemic cardiomyopathy as he recovers from coronary artery bypass grafting surgery. BedScales is the first sensor to measure adherence-independent total body weight as well as longitudinal cardiopulmonary physiology. As such, it has the potential to create a multidimensional picture of chronic disease, learn signatures of impending hospitalization, and enable optimization of care in the home.

Nocturnal Respiratory Rate Dynamics Enable Early Recognition of Impending Hospitalizations

“…To define NRR in populations, we collected and analyzed raw waveforms from chest belt respirometers of 2,000 polysomnograms from the Sleep Heart Health Study (SHHS), a multi-center cohort study designed to study the cardiovascular and other consequences of sleep-disordered breathing (18, 19) . We performed peak-finding and derived time-averaged respiratory rate estimates at 30-second intervals (epochs) as previously described (20) . To enable visualization of the entire dataset at-a-glance, we encoded the NRR as color, which enabled the entire sleep study of a patient to be communicated as a sequence of colors assembled as a column read from top to bottom ( Fig.…”

“…Adherence-independent mechanical force measurements were continuously and automatically collected at 80Hz and transmitted hourly to a cloud environment. Respiratory waveforms were quantified using a validated pipeline similar to that used for the sleep studies above (20) . NRRs were deposited in a database that was accessible via a password and two-factor authentication-protected web or mobile app.…”

“…Additionally, NRR is an attractive biomarker because it can be measured by many different sensors. Adherenceindependent strategies can be based on strain gauges placed under the bed (20), mattress sensors (21)(22)(23)(24), or ultrawideband radar systems (25,26). For highly engaged patients, there are many wearables and smartphone apps capable of measuring respiratory rates (27)(28)(29).…”

“…To monitor the NRR, we used BedScales, a non-contact adherence independent sensor that is placed under the legs of the bed and transmits data every hour to Amazon Web Services cloud storage where it is processed in real-time through a pipeline of analytics that extract the respiratory rate (20) . The processing pipeline receives a signal from the sensors under each bed leg, performs bandpass frequency dependent filtering and combines all individual sensor signals into a composite signal using Principle Component Analysis.…”