Using big data to improve safety and quality in radiation oncology

Abstract

This chapter reviews new approaches to quality and safety improvement in radiation oncology with a specific focus on big data. One way to conceptualize big data’s aspects of quality and safety is through the well-established quality model proposed by Avedis Donebedian and colleagues at the University of Michigan in the 1960s. In this paradigm, quality and safety measures fall into one of three categories: Structure, Process, and Outcomes. In the context of big data and oncology, most of the outcomes studies to date have focused on new methods to provide prognostic accuracy using radiomics signatures and the like. The chapter presents an effort to develop a semiautomatic method to identify anomalies in a patient’s electronic medical record. There are a number of ways to approach the quality assurance problem programmatically, the two most common being rules-based systems and probabilistic models.

Ähnliche Arbeiten