An automated remote monitoring program for COVID-19


Early in the pandemic, we knew that for every patient hospitalized with COVID-19, there were likely 25 or more sheltering at home.

We needed a way to monitor these patients effectively so that clinical declines could be identified early and escalated appropriately. Without close monitoring, there was concern that patients with mild cases may present to the emergency department unnecessarily – putting themselves at risk for unnecessary exposure and Penn Medicine at risk of being overwhelmed by a surge.


COVID Watch is an automated remote monitoring program that enables patients who are confirmed or likely to have COVID-19 but not sick enough to need hospitalization to be monitored at home.

Penn Medicine clinicians enroll patients in the program directly from the electronic medical record. From there, Way to Health utilizes twice-daily automated texts to remotely monitor patients – assessing how they are feeling and if they are having trouble breathing. When concerning cases arise, protocols for escalation to telemedicine or hands-on care are enacted. The program is available in English and Spanish. 

You can learn more about the design, implementation, and outcomes of the first 3,000 patients in COVID Watch in this NEJM Catalyst piece. One of the most exciting aspects of the process was the speed at which it moved. We leveraged the structure of BreatheBetterTogether, an ongoing program designed to monitor patients with COPD to build version one, utilized Way to Health to conduct remote monitoring, and relied on Penn Medicine OnDemand for the clinical infrastructure needed to manage and respond to escalations. As a result, less than two weeks after our initial meeting, we enrolled our first patient. And two weeks after that, we scaled the program system-wide. 


COVID Watch improves care delivery and patient outcomes, reduces the burden on clinical staff, and decreases costs for the health system.
More than 18,500 patients were enrolled in COVID Watch during its first year in operation – 84 percent of them “watched over” using text messages alone. For the 16 percent of patients who needed extra help, the median response time for escalations was 14 minutes. Patients in the program reported that it was reassuring to know that Penn Medicine was checking in to see how they were doing, and the automation of the platform made it incredibly efficient to staff and reduced reliance on physicians. Over that first year, COVID Watch saved the health system approximately $8 million, mainly in the form of reduced use of nurses and other health care personnel.
Based on the success of COVID Watch, we launched several spinoff programs, including COVID Pulse, which monitors the sickest patients using a pulse oximeter, and Pregnancy Watch and Cancer Watch, which are tailored to the specific needs of those patient populations. And, in August 2020, the team was awarded a $2.5 million PCORI grant to evaluate the program, with particular focus on whether it reduces disparities in care experienced by Black and Latinx patients. This study will take place between 2020 and 2022. Results will be shared here when available.
Beyond the pandemic, the COVID Watch model can be adapted to manage other clinical conditions, such as hypertension, diabetes, or heart failure, where frequent human contact might be supplemented or partially replaced with automation.
Phase 3: How we work

Anna Morgan, MD
Doreen Lam
Nancy Bonalumi, RN
Susan McGinley, CRNP
Andrew Parambath
Bill Hanson, MD
PJ Brennan, MD
Kevin Volpp, MD, PhD
Nina O'Connor, MD
Ann Huffenberger, RN, DBA
Susan Day, MD, MPH

Innovation leads

Neda Khan
David Asch, MD, MBA
Mohan Balachandran, MA, MS
David Do, MD
Krisda Chaiyachati, MD, MPH, MSHP
Christianne Sevinc, MPH
Kathleen Lee, MD


Publication-of-the-Year Award, AcademyHealth