By Dr. Bechara Choucair, Commissioner, Chicago Department of Public Health

From clean water supplies to the polio vaccine, the most effective public health interventions are typically preventative interventions and policies that help stop a crisis before it starts. But predicting the next public health crisis has historically been a challenge, and even interventions like distilling water or distributing a vaccine are in many ways reactive, following an initial outbreak of some kind. Thanks to new technologies, we are piloting a new way to predict where and what that initial outbreak will be, so we can intervene and stop it before it ever begins.

Predictive analytics is a new approach that employs an array of public health data to predict who is most susceptible to birth complications or chronic diseases or where and when a virulent outbreak is most likely to occur. With this information, public health officials should be able to respond before the issue manifests itself – providing the right prenatal treatments to mitigate birth complications, providing diet recommendations to overcome a chronic disease or distributing vaccines early to ensure an outbreak is contained. Similar to how a flu shot can reduce your chances of getting the flu – especially among those most vulnerable to the disease – predictive analytics should be able to reduce the chances of other health issues from ever starting.

This would transform how government operates, how resources are allocated and greatly benefit the public’s health.

But predictive analytics aren’t the future – they are already here. While the greatest benefits have yet to be realized, at the Chicago Department of Public Health (CDPH) we are already leveraging data and history to make smarter, more targeted decisions today by piloting predictive analytics within our food safety program.

Recently, CDPH partnered with development and coding groups to identify various data related to food establishments and their locations - building environments and 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.

Over the next month, our food inspectors will use these data to determine establishments most at risk for health code violations, evaluating several hundred establishments to test the model. Based on their results and additional stakeholder input, we will evaluate the system and make adjustments as needed. Once it is proven successful, we will expand the program to help identify more health code violations more quickly, helping to make our food supply even safer and prevent more cases of food poisoning before they occur.

To be clear, this new system will not replace our current program. We will still inspect every food establishment following our current schedule, ensuring the entire food supply remains safe and healthy for our residents and tourists. But predictive analytics will allow us to better concentrate our efforts on those establishments more likely to have challenges. In time, this system will help us work more closely with restaurateurs so they can improve their business and decrease complaints. In short, businesses and their customers will both be happier and healthier.

This new model builds on earlier innovations CDPH has made concerning food protection. As the Centers for Disease Control and Prevention has reported, most cases of foodborne illnesses go unreported as health agencies typically wait for customers to file an official report. To fix this discrepancy, CDPH and its partners launched a new application on Twitter, www.foodbornechicago.org, where the agency monitors public tweets from Chicago that mention food poisoning. Whenever a resident tweets about a case of food poisoning in the City, CDPH responds and invites the individual to provide additional information so our inspectors can follow up. And it’s working.

Since its launch in March 23, 2013, 191 cases have been reported through the new system, resulting in spot inspections that would not have occurred otherwise. Not only have these inspections yielded additional health code violations, in one case, an outbreak, affecting numerous individuals, was identified sooner by CDPH thanks to early reports via Twitter.

The Twitter application has already proven successful, allowing CDPH to identify previously unreported problems. We fully expect the predictive analytics pilot will prove to be equally successful, further improving the department’s inspections and the health and safety of the food supply. Once proven successful, predictive analytics could be used in other public health areas - allowing Chicago to again innovate in new ways, using data to improve the safety and well-being of all people. The future is bright.