ABSTRACT
The recent explosive surge of digital health data has made a significant impact on the proliferation of data science research in healthcare. However, traditional approaches have reached limited achievements in facing the big health data due to their weak scalability and poor applicability in tackling massive amount of healthcare data. By the structured analysis of the historical and modern methods, this article presents a comprehensive overview of the existing challenges, techniques, and future directions of computational health informatics in the big data era. This chapter outlines the challenges in the generic big health data as four high Vs, which are high volume, velocity, variety, and veracity. Moreover, it introduces a systematic data processing pipeline that covers data capturing, storing, sharing, analyzing, searching, and decision support. In this book chapter, we compare and categorize numerous machine learning techniques and algorithms for computational health informatics, based on which, we identify and analyze the essential prospects lying ahead in this big data age.
