Automated Messaging Helps Penn Medicine Save Lives at Home

An automated messaging platform helped Penn medicine save two lives per week during the early days of the pandemic by allowing care providers to monitor patients at home.

An automated messaging platform that helped Penn Medicine monitor patients with COVID-19 at home is being credited with saving two lives per week during the early days of the pandemic.

The platform, called COVID Watch, sent AI-enhanced text messages to patients twice a day, asking about their symptoms. If patients reported worsening symptoms, they were sent follow-up questions, then called by designated clinical staff at the hospital, who could recommend hospitalization.

According to a study supported by the National Institutes of Health and the Patient-Centered Outcomes Research Institute (PCORI) and recently published in the Annals of Internal Medicine, nearly 20,000 patients have been monitored at home since the platform was launched on March 23, 2020. In the eight months after the program’s launch, only three of the 3,448 patients died within 30 days of enrollment, compared to 12 patients in a similar-sized group who weren’t in the program, and five died within 60 days, compared to 16 outside the program.

The research team, from Penn Medicine’s Perelman School of Medicine, concluded that COVID Watch reduced a patient’s chances of dying by 68 percent, and that 1.8 lives per 1,000 patients were saved over the first 30 days and 2.5 patients per 1,000 were saved at 60 days.

“Automation isn’t something that will replace human clinical care, but it is something that can extend it,” David Asch, MD, a co-author of the study and executive director of the Center for Health Care Innovation, said in a press release. “Without an automated system to help us watch over the thousands of COVID patients in our community, our doctors and nurses would have been stretched even thinner than they were. This is a promising model for the future.”

Penn Medicine’s program fits neatly into the strategy behind remote patient monitoring, or expanding care management options for patients at home instead of admitting them to a hospital or waiting for them to visit their doctor’s office or a clinic. By creating a platform that uses automated and intuitive messaging to connect with them twice a day, the health system is able to monitor them daily and take action if they’re trending downward. The platform is designed to catch patients before they become serious and require hospitalization.

To manage the program, the health system created a small team of nurses focused on tracking those patients at home. Those nurses can very easily track 1,000 patients around the clock, as well as provide support, such as helping to arrange tests and discussing the results.

“At the beginning of the pandemic, we instinctually thought patients needed extra support at home, even if they weren’t sick enough or ill yet. And if they were to get very sick, we wanted to help them get to the emergency department earlier, so COVID Watch was our solution,” Krisda Chaiyachati, MD, medical director of Penn Medicine OnDemand, an assistant professor of m and co- primary investigator of the study, said in the press release. “Our evaluation found that a small team of five or six nurses staffing the program during some of the most hectic days of the pandemic directly saved a life every three to four days.”

Researchers also noted that the platform works well across all populations, including communities that traditionally face barriers to accessing care.

“We saw a higher proportion of higher-risk patients and also low-income and Black patients enrolled in COVID Watch, but the fact that we measured a significant benefit associated with enrollment in the program is a good indicator that there truly is a treatment benefit for everyone,” M. Kit Delgado, MD, an assistant professor of emergency medicine and epidemiology, deputy director of the Penn Medicine Nudge Unit, and the study’s lead author and co-primary investigator, said in the press release. “It’s crucial that we found all major racial and ethnic groups benefited because non-white and low-income communities have had disproportionately higher infection rates, lower access to care, and higher death rates. This implies that this model of care could have reduced disparities in COVID outcomes if it was scaled up more broadly to these communities.”

Penn Medicine officials noted the platform was originally modeled to monitor at home patients living with chronic obstructive pulmonary disease (COPD), and was redesigned to handle COVID-19. Now they’ll look to see how the platform can be reconfigured to monitor other patient populations, such as those with chronic care needs.