Innovative Text Messaging Plus a Nursing Team: Dramatic Covid Results Hint at Broader, Equitable Potential

Innovative Text Messaging Plus a Nursing Team: Dramatic Covid Results Hint at Broader, Equitable Potential

February 2022

At the start of the pandemic, professionals working in health systems across the US realized that if a sizable portion of the many people infected with SARS-CoV-2 went to hospitals, this would strain our resources. Instead, most people would need to manage their illness at home — and there were no good options for that scenario. They could call their primary-care providers or find an urgent care provider — either way, joining a long queue. Some would grow fearful and proceed right to an emergency department, sometimes unnecessarily. And some who really should have been hospitalized would stay away out of fear.

Enter Covid Watch, an automated monitoring system developed by M. Kit Delgado, MD, MS, and colleagues. The system uses text messages to triage people before a clinician assesses them. The team’s study found that during the pandemic’s first wave, Covid-19 outpatients who used Covid Watch were 68 percent less likely to die. In addition, all major racial and ethnic subgroups had reduced mortality rates when enrolled. This shows the system’s huge potential as an equitable model — not only for outpatient management of patients with COVID-19, but possibly also for those with other conditions where early detection of clinical declines is critical.
Using text messaging — a low-tech, widely available technology — is essential to the system’s success, Dr. Delgado says. “We didn’t rely on devices that we had to distribute; practically everyone has a cell phone. That, and the fact that it was easy to enroll, made our program accessible to a large and diverse group.” The study compared 3,488 patients who had contact with the Penn system and chose to enroll in COVID Watch with 4,377 similar patients who did not enroll.  
Effective, nimble triage enabled precise, and precisely timed, decisions, Dr. Delgado notes. Twice a day, the system initiated algorithmically guided text message conversations with patients, to assess their conditions. Initially, it escalated to a human team those patients who answered yes to the question “How are you feeling compared to 12 hours ago?” But the researchers found that in order for exactly the right patients to receive a phone call from their nursing team, they needed to follow up with a more nuanced question: “Is it harder than usual for you to breathe?”

When symptoms worsened, Covid Watch got patients to the hospital two days earlier, on average, giving them more of a fighting chance. “Patients feared going to the hospital, and yes, this system did drive people to the emergency room. But the improved survival rates speak for themselves,” Dr. Delgado comments.

The study appeared in Annals of Internal Medicine. The authors of an editorial also published in Annals praised Covid Watch as “extending a lifeline to non-hospitalized patients.”


Authors: M. Kit Delgado, MD, MS; Anna U. Morgan, MD, MSc, MSHP; David A. Asch, MD, MBA … Nandita Mitra, PhD, and Krisda H. Chaiyachati, MD, MPH, MSHP

About Us

To understand health and disease today, we need new thinking and novel science —the kind  we create when multiple disciplines work together from the ground up. That is why this department has put forward a bold vision in population-health science: a single academic home for biostatistics, epidemiology and informatics. 

© 2023 Trustees of the University of Pennsylvania. All rights reserved.. | Disclaimer

Follow Us