COVID-19 highlights the acute need for non-invasive, point-of-care, remote monitoring

hemodynamic measurement solutions. Find out how CPS meets the need.

Scientific PUblications

Cutting-Edge Screening & diagnosTIC CAPABILITIES

Using machine learning, CPS can be trained to almost any standard hemodynamic measurement and methodology. 

In addition to providing objective measurements on critical heart functions, future iterations of the CPS will use these measures to automatically detect cardiac abnormalities and rapidly screen for prevalent heart conditions without the need for operator interpretation.

Proof-of-concept clinical results have been published for the automated detection of aortic stenosis and ventricular dysfunction using the CPS technology, and we're continuing to explore additional indications. These early studies provide a glimpse into the future of cardiovascular medicine, where the all-in-one CPS platform will be used to measure, screen, and diagnose an array of cardiac conditions at the point of care.


August 27, 2020

This paper compares a fully automated phonocardiogram (PCG) based wearable system with echocardiography for the early evaluation of heart failure patients. When tested on n=34 adult inpatients undergoing right heart catheterization, the system was able to identify left ventricular diastolic dysfunction with 87.5% accuracy and elevated left atrial pressure with 75% accuracy.

Criterion to diagnose diastolic dysfunction using Sensydia technology

March 24, 2020

Phonocardiogram (PCG) and electrocardiogram signals were acquired simultaneously using an automated system of acoustic sensors and electrodes in 18 subjects. Mitral E/A ratio was computed via PCG using a feature-based linear model against doppler echo.Fully-automated PCG-based E/A ratio computation represents a first step towards heart failure screening at the point of primary care.

Mitral E/A ratio computation using Sensydia technology

May 19, 2019

This paper presents an end-to-end, fully automated, non-invasive system that uses noise-subtraction, heartbeat segmentation and quality-assurance algorithms to extract physiologically-motivated features from PCG signals to diagnose Aortic Stenosis (AS). When tested on n=96 patients showing a diverse set of cardiac and non-cardiac conditions, the system was able to diagnose AS with 92% sensitivity and 95% specificity.

Aortic stenosis diagnosis using Sensydia technology