Charlotte hospitals analyze social determinants of health to cut ER visits
When Charlotte, North Carolina, experienced an unexpected increase in the Hispanic immigrant community, among the consequences of this influx was an increase in preventable emergency room visits at local hospitals.
It’s a common situation: Immigrants lacking insurance often show up at emergency rooms for what amounts to primary care. So if the health of the Charlotte population was going to be effectively managed, something had to be done about this ER emergency.
“One of the projects we’re working on is better understanding healthcare access for the Hispanic immigrant population,” explained Michael Dulin, MD, director of the academy for population health innovation at the University of North Carolina at Charlotte. “We had this new Hispanic immigrant population move into the Charlotte area pretty rapidly, and we had not really planned for that at the health system level, how to address their primary care needs. So we used data from the health system to build models to study where in the community the immigrants were settling, and where we could engage the immigrants early on.”
[Are EHRs getting better? Readers rank vendors higher than last year in new survey]
Dulin and his colleagues have built a Big Data analysis model that includes the following information: utilization of the emergency department for primary care and preventable illness; immigrant status; patient ethnicity; patient time in the community; low health literacy among patients; levels of violent crime for geographic areas; and other health indicators and social determinants of health.
“We identified hotspots in our community that most needed improved access to primary care,” Dulin explained. “We used that analysis to work with the immigrant community to build new methods for engaging them with the health system. So now we do primary care in partnership with the school system within immigrant areas, access to primary care on Saturdays at schools. With that plan implemented we have decreased access to the emergency room for primary care purposes and increased utilization of primary care.”
Dulin added that a key component overlapping both public health and population health is the social determinants that can drive health outcomes.
To make that happen, though, healthcare organizations first must understand which consumers within their populations have certain social determinants of health.
The next step at the health system level is to create connections that align patients with appropriate resources to address those social determinants and improve overall health outcomes, Dulin added.
“If you are not paying attention to social determinants and their health outcomes downstream, they can lead to worse health outcomes and make it difficult to move into value-based healthcare,” he said. “That does not mean health systems have to directly address social determinants, but they can partner with public health departments to help better manage connections of their patients into other resources that do address social determinants. And analytics is the foundation of that work.”
Related stories ahead of Big Data & Analytics Forum in Boston, Oct. 24-25.
⇒ Big Data: Healthcare must move beyond the hype
⇒ Tips for reading Big Data results correctly
⇒ Small hospital makes minor investment in analytics and reaps big rewards
⇒ MIT professor's quick primer on two types of machine learning for healthcare
⇒ Must-haves for machine learning to thrive in healthcare