Big Data and Machine Learning Meet the Health Sciences

Abstract

Big data and machine learning are gaining traction in health sciences research. They might provide predictive models for both clinical practice and public health systems. Big data is a broad term used to denote volumes of large and complex measurements. Beyond genomics and other “omic” fields, big data includes administrative, molecular, clinical, environmental, sociodemographic, and even social media information. Machine learning, also known as pattern recognition, represents a range of techniques used to analyze big data by identifying patterns of interaction among features. Compared with traditional statistical methods that provide primarily average group-level results, machine learning algorithms allow predictions and stratification of clinical outcomes at the level of an individual subject. In the present chapter, we provide a concise historical perspective of some important events in health sciences and the analytical methods used to find causes and treatment of illnesses. The overall aim is to understand why big data and machine learning have recently become promising methods to define, predict, and treat illnesses, and how they can transform the way we conceptualize care in health sciences.