Existing Electronic Health Record (EHR) systems are rich, and often highly heterogeneous, sources of data. In the last ten years, there has been ample interest in how the growing volume of EHR data may be used to better monitor and support decisions at the bedside, with several of the largest industrial players now entering the arena (Google, Apple Microsoft and Amazon). But EHR systems are designed to mitigate clinical liability and facilitate billing, not to support algorithm development. As the most well-resourced data companies continue their push into healthcare domain, EMR systems will inevitably change to accommodate algorithm designers. In this talk, we will present several case studies that highlight the challenges and opportunities that are available in this rapidly evolving data ecosystem, and the import role that academic researchers can play in forging the future of recommendation systems in health.
CCS CONCEPTS • Information systems → Information systems applications; Recommender systems; Information retrieval; • Human-centered computing → Human computer interaction (HCI); • Applied computing → Health care information systems; Health informatics; Recommender systems, Health recommender systems; Multi-criteria rating; Health promotion