A fully integrated open-source toolkit for mining healthcare big-data: architecture and applications

摘要

We create an analytics toolkit based on open-source modules that facilitate the exploration of healthcare-related datasets. We illustrate our framework by providing a detailed analysis of physician and hospital ratings data. Our technique should prove valuable to software developers, big-data architects, hospital administrators, policy makers and patients. As an illustration of the capabilities of our toolkit, we examine a controversial issue in the medical field regarding the relationship between seniority of medical professionals and clinical outcomes. We use a publicly available dataset of national hospital ratings in the USA to suggest that there is no significant association between experience of medical professionals and hospital ratings as defined by the US government.