Big Data Analytics for Healthcare Recommendation Systems

Abstract

Healthcare industry is an indispensable entity in the real world where large volumes of data is accumulated from time to time. Such data assumes characteristics of big data and it is desirable to analyze it and bring about latent relationships among variables in the healthcare data. Data in healthcare industry is rich in useful information. However, a comprehensive big data approach is essential to mine the data and acquire business intelligence. There are many use cases of big data analytics. However, in healthcare industry it is imperative to have knowledge-driven recommendations that help all stakeholders. With the emergence of cloud computing, big data analytics has become a reality. Distributed programming frameworks like Hadoop and Spark, to mention few, are available with associated Distributed File System (DFS) to manage big data. Many researchers contributed towards developing algorithms based on machine learning which is part of Artificial Intelligence (AI). Since healthcare industry is one of the sources of big data, it needs distributed environments for processing. Big data analytics is essential to analyze healthcare data in a comprehensive manner. The cloud computing and big data ecosystem is playing favorable role in realizing big data analytics for healthcare recommendations. A typical recommender system in healthcare industry is supposed to produce recommendations in various aspects of the domain. This paper throws light into different recommenders in healthcare domain that use big data analytics to generate recommendations. It not only provides useful insights but also discussed research gaps that can be used to investigate further to improve the state of the art.