Columbia professor confronts healthcare inequality in time of COVID-19
Kai Ruggeri’s research has one overriding objective: to improve the well-being of populations by confronting inequality. He is a behavioral scientist at Columbia who uses data science to design interventions and recommend policies that help the most vulnerable and disadvantaged populations overcome inequalities.
As an assistant professor in the Department of Health Policy and Management at Columbia’s Mailman School of Public Health, Ruggeri focuses on population level behaviors such as the way people make financial choices and use health care. While his work involves entire populations, much of his focus is on how to address inequalities in access and outcomes, particularly among the most disadvantaged. Such inequities have become even more apparent with the outbreak of Covid-19, as higher rates of infection and death among people of color demonstrate the racial character of inequality in America’s health care system.
“You can tie just about every major issue to inequalities,” says Ruggeri, who is an affiliate of the Data Science Institute. “Some are flaws or biases in the system; some are unfortunate circumstances; pretty much all are harmful. The aim is to raise the floor, shift the mean up, and eliminate ceilings. If you do this, you see entire populations improving. This starts with those who need it most, but everyone benefits from it.”
One of Ruggeri’s projects is using data science to eliminate inequality and increase health care access in undeserved communities in Brooklyn, the Bronx, Manhattan, and Queens. The project, called Nudging New York, is supported by a Data Science Institute Seed Fund grant. He is collaborating on the project with the Community Healthcare Network (CHN), a federally qualified health clinic that provides care to disadvantaged New Yorkers.
Federally funded health care centers like CHN provide medical care to more than 20 million Americans who live in impoverished areas. Yet in many of those areas, nearly half of the patients who make medical appointments at the centers don’t show up–not because they don’t want to, but they encounter major barriers. Data show that patient no-show appointments, and the missed opportunities for needed medical care, place an enormous health burden on disadvantaged communities. No-shows, for example, increase the likelihood that patients will visit emergency rooms and be hospitalized for conditions that could have been treated at clinics. As such, even small decreases in no-show rates at clinics would improve the health of vulnerable populations while reducing the nation’s medical costs.
Ruggeri recently published a paper about the Nudging New York research in BMC Health Services Research, which is owned by Springer Nature. In the paper, his team details how it is uses big data and Bayesian machine learning techniques to understand what prevents many of the 80,000 CHN patients from making their medical appointments. The team also discusses several system wide and behavioral interventions and policies that would help them keep their appointments. They also explore common barriers to patient care, such as transportation, childcare, translation services, and inconvenient appointment times.
Once the team has evaluated patients’ behavioral and environmental data, as well as data from emergency departments at partner hospitals, it will use a technique known as “nudges” to help patients keep appointments. Nudges are behavioral interventions that encourage optimal choices. They can be applied in a variety of ways, such as providing more information to patients, or more emphatically stressing the importance of attending regular checkups. What is most important is that the nudges are personalized, as the most effective interventions are those that address the specific needs of individuals, Ruggeri says.
“By evaluating sources of clinical, behavioral, and environmental data, and then matching the most effective interventions to the right groups of patients, we hope to reduce no-shows and avoidable visits to emergency departments,” he says. “In implementing Bayesian machine learning methods to better understand patterns of behavior in these groups, we will design nudges that increase health care access for the most vulnerable New Yorkers. If we do it right, the methods we create can be used at community clinics across the U.S. to radically improve health care while significantly reducing cost. While we focus on New York, this work has the potential to have impact in rural and urban communities around the country.”
CHN is also playing a major role in combating Covid-19. It has transitioned to offering telemedicine to its clients, given the lock down, while also serving as a Covid-19 testing site. Ruggeri’s team has adapted its research to help the network contend with the coronavirus, which data show disproportionately affects communities of color.
“We are working with the network on a number of initiatives, ranging from optimizing telemedicine arrangements to tracking individuals unable to attend sessions to see if we can formulate interventions to support those who need care but face barriers to getting it,” he says. “CHN is contributing in critical ways in this pandemic, and we are grateful for support from the Data Science Institute to allow us to design behavioral interventions and maximize the use of data to help the network deliver care.”
Along with being an affiliate of DSI, Ruggeri belongs to two of the institute’s centers: Financial and Business Analytics and Health Analytics. Education, financial stability, health, and national security are the fundamental factors that enable populations to flourish, which is why he says he joined both centers. In the past, researchers could focus on one or two of these factors, but with more data and modern technological resources, “we can now see how all these factors interact.”
“And knowing this, we can make use of all the data and new technology to drive better outcomes for those who need it most,” Ruggeri says. “The Data Science Institute gave me a great opportunity to dive headfirst into this work early in my time at Columbia, and the support they gave to me to move ahead with my research is something I hope will have even greater impact in the near future. My goal is to create better outcomes in well-being across all communities–it’s what gets me up in the mornings–and data science is helping me to achieve that goal.”