The patient monitoring company says the technology, developed at the University of Chicago, will allow health systems to better manage patients' risk of adverse events.
Cardiac predictive analytics developed by Dana Edelson, MD, an expert in cardiac resuscitation at the University of Chicago, will be integrated into EarlySense's continuous monitoring tool, after the company acquired the technology.
Edelson is executive medical director for inpatient quality and safety at the University of Chicago Medicine and is the founder and CEO of Quant HC, which develops algorithms for real-time risk stratification of hospitalized patients.
Her analytics technology, called eCART, applies real-time data with a focus on prediction, prevention and treatment of in-hospital cardiac arrest – potentially leading to improved patient safety and even cost savings.
EarlySense's patient monitoring technology uses artificial intelligence to track real-time health data, including heart rate, breathing rate, sleep cycles, stress levels and movement. It analyzes heart and respiratory factors to predict cardiac arrest risk to provide early intervention.
The company has signed a deal for exclusive global rights to a version of the eCART score tool developed by Edelson. The new 'Lite' edition, unveiled at the 2018 ATS International Conference, will be integrated into EarlySense's products.
It is touted as the first-ever scientifically validated early warning score to use only heart rate, respiratory rate and patient age – well-suited for hospitals to use with continuous monitoring sensors.
"Risk scoring is a critically important tool but is currently limited to complex multi-parameter tests and lab systems found in EMR systems," said Avner Halperin, co-founder and CEO of EarlySense, in a statement. As he sees it, combining Edelson's approach with real time data enhances true deterioration detection and could save countless lives.
Edelson's eCART tool was designed to identify risk of health deteriorations and cardiac arrests based on more than 30 clinical data points per patient. It was developed using a data set of nearly 300,000 cases. The technology has already been proven to improve care in hospitals and help clinicians achieve better outcomes, including lower mortality rates.
"By working with EarlySense to adapt this hospital-proven predictive clinical score to be used with a streamlined set of data points, including continuously collected heart and respiratory parameters from the EarlySense bed sensors, we may be able to extend the predictive clinical score beyond the confines of the hospital and into post-acute and home environments,” Edelson said in a statement. "This in turn enables earlier intervention and prevention of patient deterioration and adverse events."