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.

Home health monitoring technologies promise to improve care and reduce costs, yet they are limited by the need for adherence to self-monitoring, usage of an app, or application of a wearable. While implantable sensors overcome the adherence barrier, they are expensive and require invasive procedures. Here, we describe a non-invasive, 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 demix weight and respiratory signals when the bed is shared by a partner or a pet. Validation studies during overnight clinical sleep studies exhibit quantitative equivalence to commercial sensors and allow discrimination of obstructive and central sleep apneas. In-home studies discriminate atrial fibrillation from normal sinus rhythm. To demonstrate real-world feasibility, we performed 3 months of continuous in-home monitoring in a patient with heart failure as he awaited and recovered from coronary artery bypass surgery. By overcoming the adherence barrier, Bedscales has the potential to create a multidimensional picture of chronic disease, learn signatures of impending hospitalization, and enable optimization of care in the home.

Periodic breathing (PB), including its subtype Cheyne-Stokes respiration, is a pattern of sleep-disordered breathing marked by cyclic modulations in tidal volume and respiratory rate. PB is commonly identified in patients with chronic heart failure (CHF), and portends a worse prognosis. Due to the impracticality of existing monitoring methods, no longitudinal data exist on whether individual patients may experience prognostically significant fluctuations in PB. Here, we present a novel tool enabling long-term in-home investigation of PB. By passively capturing respirations during sleep via mechanical sensors placed under the legs of a bed, the need for patient compliance is circumvented. PB events were identified by computing an amplitude modulation index, and features including respiratory rate, cycle length, and hyperpnea duration were extracted. To demonstrate viability for longitudinal studies, devices were installed in the homes of 25 CHF patients to continuously record respirations, 9 of whom were found to exhibit PB. In an illustrative case, ~15,000 cycles of PB were captured over 3 months in a patient discharged after hospitalization for heart failure with reduced ejection fraction. Bedscales documented the patient’s worsening tachypnea accompanied by changes in PB parameters (shortened cycle and hyperpnea durations). A chest X-ray showed evidence of pneumonia and antibiotics were prescribed, after which tachypnea improved and trends of PB parameters reversed. This case highlights the potential utility of Bedscales in detecting subtle deviations from an individual’s baseline respiratory signatures; future work is needed to assess the predictive power of these parameters. Taken together, these results demonstrate the feasibility of Bedscales as a low-cost, scalable tool for longitudinal population-level studies of PB in relation to chronic diseases such as CHF. Future research could examine whether such data might predict exacerbations and direct early intervention to prevent rehospitalization.