Predicting E. coli concentrations using limited qPCR deployments at Chicago beaches.

Culture-based methods to measure Escherichia coli (E. coli) are used by beach administrators to inform whether bacteria levels represent an elevated risk to swimmers. Since results take up to 12 h, statistical models are used to forecast bacteria levels in lieu of test results; however they underestimate days with elevated fecal indicator bacteria levels. Quantitative polymerase chain reaction (qPCR) tests return results within 3 h but are 2-5 times more expensive than culture-based methods. This paper presents a prediction model which uses limited deployments of qPCR tested sites with inter-beach correlation to predict when bacteria will exceed acceptable thresholds. The model can be used to inform management decisions on when to warn residents or close beaches due to exposure to the bacteria. Using data from Chicago collected between 2006 and 2016, the model proposed in this paper increased sensitivity from 3.4 percent to 11.2 percent-a 230 percent increase. We find that the correlation between beaches are substantial enough to provide higher levels of precision and sensitivity to predictive models. Thus, limited deployments of qPCR testing can be used to deliver better predictions for beach administrators at lower cost and less complexity.

Machine-learned epidemiology: real-time detection of foodborne illness at scale.

Machine learning has become an increasingly powerful tool for solving complex problems, and its application in public health has been underutilized. The objective of this study is to test the efficacy of a machine-learned model of foodborne illness detection in a real-world setting. To this end, we built FINDER, a machine-learned model for real-time detection of foodborne illness using anonymous and aggregated web search and location data. We computed the fraction of people who visited a particular restaurant and later searched for terms indicative of food poisoning to identify potentially unsafe restaurants. We used this information to focus restaurant inspections in two cities and demonstrated that FINDER improves the accuracy of health inspections; restaurants identified by FINDER are 3.1 times as likely to be deemed unsafe during the inspection as restaurants identified by existing methods. Additionally, FINDER enables us to ascertain previously intractable epidemiological information, for example, in 38% of cases the restaurant potentially causing food poisoning was not the last one visited, which may explain the lower precision of complaint-based inspections. We found that FINDER is able to reliably identify restaurants that have an active lapse in food safety, allowing for implementation of corrective actions that would prevent the potential spread of foodborne illness.