Online Program

How Chicago is Using Predictive Analytics to Improve Public Health

Tuesday, November 3, 2015 : 2:30 p.m. - 2:50 p.m.

Jay Bhatt, DO MPH MPA, Chicago Department of Public Health, Chicago, IL
Raed Mansour, MS, Chicago Department of Public Health, City of Chicago, Chicago, IL
The last several presidential elections have seen campaigns identify must reach voters through big data analytics in the context of micro targeting. The Chicago Department of Public Health (CDPH) is applying this methodology to health promotion. African American women carry the greatest burden when it comes to breast cancer. By targeting efforts in African American communities, there is opportunity to close disparities. CDPH has joined Civis Analytics to conduct targeted outreach to uninsured women in an effort to connect women at risk to free mammogram services using a predictive analytics model. 

To identify women most likely to be uninsured, CIVIS Analytics used open data along with proprietary data in combination with CDPH community surveillance data suggesting areas at risk for premature mortality from breast cancer. CDPH then developed direct mail appeals, encouraging them to visit Roseland Hospital state of the art mammography center for a free, quality mammogram paid for through an earlier investment made by the City of Chicago.

In the first two weeks after the microtargeting campaign, Roseland saw nearly 80 women call to set up a mammogram  Nationally, African American women have the highest breast cancer death rates of all ethnic and racial groups and are 40% more likely to die of breast cancer than white women. In Chicago, Roseland and the neighboring communities of Beverly, Washington Heights and Auburn Gresham have some of the highest rates of premature deaths due to breast cancer in the City.

This level of data mining and micro-targeting has been used successfully by both political campaigns and the private sector. This mark the first time a local public health agency has used a similar method to directly reach individuals most likely to miss screenings for a treatable cancer. We are able to get women most in need of resources to stay healthy.

Learning Areas:

Administration, management, leadership
Chronic disease management and prevention
Planning of health education strategies, interventions, and programs
Public health administration or related administration
Systems thinking models (conceptual and theoretical models), applications related to public health

Learning Objectives:
Demonstrate how to translate predictive analytics to public health problems Discuss using analytics to make smarter use of resources Define advancing innovation within constraints of government Demonstrate collaborating with partners to build public health capacity and sustainability

Keyword(s): Cancer and Women’s Health, Public Policy

Presenting author's disclosure statement:

Qualified on the content I am responsible for because: Help develop the intervention and prepare the parameters and data at CDPH
Any relevant financial relationships? No

I agree to comply with the American Public Health Association Conflict of Interest and Commercial Support Guidelines, and to disclose to the participants any off-label or experimental uses of a commercial product or service discussed in my presentation.