University of Sourthern California


Big Data and Public Health

Public health administrators are tasked with identifying cost-effective strategies for managing their programs, often with limited resources and budgets, all while improving both the quality of and access to care for their patients.

Investments in growing availability and accessibility of data, as well as business intelligence capabilities that are gaining traction in other sectors, make it possible to take advantage of predictive analytics techniques. A move more towards evidence-based decision-making can be especially valuable in public health.

Image via.

How Can Predictive Analytics Help?

Predictive analytics refers to a range of methods that are used to anticipate an outcome — or more broadly speaking, it analyzes patterns in historical data to predict future outcomes. For example, a public health program may use predictive analytics to anticipate how individuals may respond to program changes, particularly ones centered on education. With the information gained from predictive analytics, public health administrators can then identify who is most likely to benefit from a change and determine the most effective ways to improve the accessibility of the program, as well as its scope.

The Chicago Example

The Harvard Business Review recently published “How Cities Are Using Analytics to Improve Public Health” and looked at the Chicago Department of Public Health (CDPH) as an example. The CDPH partnered with the Department of Innovation and Technology to engage with local partners to “identify various data related to food establishments and their locations – building code violations, sourcing of food, registered complaints, lighting in the alley behind the food establishment, near-by construction, social media reports, sanitation code violations, neighborhood population density, complaint histories of other establishments with the same owner and more.”

Using this data, they constructed models that calculated a score for every food establishment, with higher scores correlating with an increased risk of critical public health violations. This new method is meant to augment manual inspections, not replace them, but using the data-based scores they can better identify higher risk establishments and prioritize their efforts accordingly.

Another example from Chicago is the city’s partnership with the Eric & Wendy Schmidt Data Science for Social Good Fellowship at University of Chicago (DSSG) to develop a model to improve their lead inspection program. Using data from home inspection records, assessor value, past history of blood lead level testing, census data and other factors, researchers are using analytics to better predict which homes are more likely to have lead-based paints – a serious health risk, particularly for children who are exposed to them. Predictive analytics allow the city to proactively allocate resources to priority areas rather than waiting to respond to reports.


The Master of Public Health Online at Keck School of Medicine of University of Southern California offers students a unique opportunity to be on the cutting-edge of technology to help them meet modern public health challenges.