Allison Baker is a Data Scientist with the Hospital Corporation of America (HCA), with a background in statistical genetics and predictive analytics. A Cleveland, Ohio native, she has a BS in mathematics and statistics from John Carroll University, and an MS in genetic epidemiology and biostatistics from Case Western Reserve University. After two years at the Center for Human Genetics Research at Vanderbilt University, she began working at HCA as a biostatistician in the Clinical Services Group. Faced with more complex problems, she explored machine learning techniques to answer her clinical questions. This rapidly transitioned Allison into her current role as Data Scientist, where she collaborates with the Data Development team to build real-time predictive applications.

Predicting Patient Outcomes in Real-Time at HCA

The Hospital Corporation of America (HCA) is the leading healthcare provider in the country, with over 160 hospitals and 115 freestanding surgery centers in 20 states and the U.K. In this country alone, HCA facilities provide approximately four to five percent of all inpatient care. With access to hundreds of thousands of patient records, HCA has advanced at becoming a leader in Data Science in the healthcare community. Data Scientist Allison Baker and Development Manager of Data Products Cody Hall work with a talented team of data scientists, software engineers, and web developers, and are building the framework and infrastructure to support a real-time prediction application, with the ability to scale across the entire company. Paramount to these efforts has been the capability of integrating the architecture for software production with the predictive models generated by H2O. This talk will review the processes by which HCA is building a pipeline to predict patient outcomes in real-time, heavily relying on H2O’s POJO scoring API and implemented in Clojure data processing.