- Duke Medicine announced that it will integrate geographic data into its electronic health record data to allow physicians to predict diagnoses in real time within a given population.
- The system uses an automated geocoding system based on postal codes and census data to create a socioeconomic assessment of a patient or group of patients.
- Researchers are also developing models to track food-borne illness outbreaks in real time.
This initiative should come as no surprise. Across the industry, payers, providers and other stakeholders have started looking to nontraditional data sources as the pathway to population health—and risk assessment. Brad Sitler, the principal industry consultant at the SAS Center of Health Analytics and Insights, told Healthcare Dive that creating a population database that is predictive of patient outcomes is dependent on leveraging nontraditional data: Socioeconomic data combined with EMR data and payer data. And Bill Davenhall, who is a health and human services expert, recently gave a TED Talk asserting that providing physicians with accurate geographic and environmental data on patients can significantly improve outcomes.
According to Sohayla Pruitt, head of the initiative and a senior geospatial scientist at Duke, "[O]nce you know how geography is influencing events and what they have in common, you can project that to other places where you should be paying attention because they have similar probability."
Want to read more? You may be interested in this story about 5 TED Talks that every healthcare exec needs to watch or this story about using data to predict risk in Medicare Shared Savings Program populations.