18DATA ANALYSIS AND MACHINE LEARNING EFFORT IN HEALTHCARE: ORGANIZATION, LIMITATIONS, AND DEVELOPMENT OF AN APPROACH

OLEG RODERICK, NICHOLAS MARKO, DAVID SANCHEZ AND ARUN ARYASOMAJULA

Division of Analytics Research and Clinical Informatics, Department of Data Science, Geisinger Health System, Danville, PA, USA

18.1 INTRODUCTION

In the last decade, we are seeing a steady increase in automated, data‐driven analysis applied to the needs of industry [1]. Reviews occasionally use the term “third wave”: of data sharing, of scientific approach, of impact on individual lives [2–4]. We may state that we are entering a third wave of interest in data science.

Techniques of data mining were successfully applied in finance, marketing, and social media [5]. In its third wave, data science is spreading to the more traditional, predigital fields: journalism, urban planning, political process, education, sports, art and design, fashion, even culinary arts, and physical fitness. The need to share data for research purposes is slowly transforming the practices of data stockpiling [6, 7]. Ideas and methods that previously belonged in engineering and academic fields are now used to deal with massive data in almost every type of human activity.

Healthcare occupies an interesting position: it is both cutting‐edge and very traditional. It makes use of the most modern research in development of means of diagnosis and intervention. At the same time, its goals—increased safety, health, and informed freedom ...

Get Internet of Things and Data Analytics Handbook now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.