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

In the 1800s, John Snow had to go door to door during an epidemic of cholera to uncover its mechanisms of spread.1 He recorded where people were getting their drinking water from in order to pinpoint the source of the outbreak. Here we scale up this approach using machine learning to detect potential sources of foodborne illness in real time. Machine learning has become an increasingly common artificial intelligence tool and can be particularly useful when applied to the growing field of syndromic surveillance. Frequently, syndromic surveillance depends upon patients actively reporting symptoms that may signal the presence of a specific disease.2,3