Electronic Records, Registries, and the Development of “Big Data”: Crowd-Sourcing Quality toward Knowledge

Despite many perceived advances in treatment over the past few decades, cancer continues to present a significant health burden, particularly to the aging US population. Forces including shrinking funding mechanisms, cost and quality concerns, as well as disappointing clinical outcomes have driven a surge of recent efforts into utilizing the technological innovation that has permeated other industries by leveraging large and complex data sets, so called “big data.” In this review, we will review some of the history of oncology data collection, including the earliest data registries, as well as explore the future directions of this new brand of research while highlighting some of the more recent and promising efforts to harness the power of the electronic health record and the multitude of data co-located there, in an effort to improve individualized cancer-related outcomes in rapid real time.