Abstract

Medicine faces a digital chasm in its quest for personalized treatments. Despite the adoption of electronic health records (EHR), most hospitals are ill-equipped for data science research. Here we propose MEDomics as the core of self-cognizant hospitals where data are systematically organized and data quality is assessed so that applying artificial intelligence to unmet clinical needs becomes easier. Capitalizing on implemented digital infrastructure, we show how novel and known prognostic factors for oncological disease can be explored. We also show how natural language processing of EHR can be used to update clinical prognosis as a patient’s oncologic illness course unfolds.

Request Data and Code