As COVID-19 cases were flattening, stakeholders within Cerner and at client facilities needed accurate and up to date estimations of COVID-19 growth in local metro areas. With existing models generally only providing state-level information, and with the need to take into account constantly shifting institutional and individual social distancing behavior, the process of building the Cerner COVID-19 Resurgence Risk Index (CCRI) model included navigating challenges not only in data and machine learning, but also in UX design and deployment.

In this talk, we discuss the story of how statistical and machine learning methods, UX design, scalable web hosting, and cloud computing platforms were used to rapidly prototype and deploy the CCRI model in weeks instead of months. The resulting model is leveraged across Cerner as part of Cerner’s COVID-19 “Recover” phase, including the COVID-19 Client Readiness Lights on Network Dashboard and the Real Time Health System Command Center Dashboard.