Abstract
The COVID-19 pandemic has accelerated the adoption of innovative healthcare methods, including remote patient monitoring. In the setting of limited healthcare resources, outpatient management of individuals newly diagnosed with COVID-19 was commonly implemented, some taking advantage of various personal health technologies, but only rarely using a multi-parameter chest-patch for continuous monitoring. Here we describe the development and validation of a COVID-19 decompensation index (CDI) model based on chest patch-derived continuous sensor data to predict COVID-19 hospitalizations in outpatient-managed COVID-19 positive individuals, achieving an overall AUC of the ROC Curve of 0.84 on 308 event negative participants, and 22 event positive participants, out of an overall study cohort of 400 participants. We retrospectively compare the performance of CDI to standard of care modalities, finding that the machine learning model outperforms the standard of care modalities in terms of both numbers of events identified and with a lower false alarm rate. While only a pilot phase study, the CDI represents a promising application of machine learning within a continuous remote patient monitoring system.
Highlights
To date, more than 130 million people have been infected with SARS-CoV-2[1]
Effective continuous remote patient monitoring (CRPM) capabilities are critical to assuring patient safety while conserving scarce resources of both hospital beds and health care professionals
We show that through the use of a multi-parameter sensor patch in the outpatient setting that we were able to develop a machine learning based COVID-19 decompensation index (CDI) model that has the potential to significantly improve the lead time and accuracy of identifying individuals requiring hospitalization due to progressive COVID-19, relative to what is routinely done in current remote monitoring programs
Summary
More than 130 million people have been infected with SARS-CoV-2 (the virus that causes COVID-19)[1]. RPM in the context of COVID-19 has included intermittent monitoring (point measurements while the patient is awake) to assess oxygen saturation (pulse oximeter) and temperature (thermometer)[14,15]. These varying definitions contribute to inconsistent findings when characterizing the case definition of COVID-19 While both intermittent temperature and SpO2 monitoring may be incrementally beneficial, measuring other physiological features such as heart rate or respiration rate, combined with patient ambulation, may provide greater insight into physiologic changes. If a clinical team member observed a participant’s physiology deteriorating (decompensation), participants were encouraged to return to seek care Using this labeled data as the ground truth for decompensation, various features were engineered related to participants’ activity and cardiovascular system to predict a decompensation event. The overall area under the curve (AUC) of the receiver operating
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
