Big data analytics in healthcare: data sources, tools, challenges, and opportunities

Abstract The increasing number of patients with chronic diseases and the concentration of medical resources have a substantial economic impact, leading to hospital visits, hospital readmissions, and additional healthcare expenses. Healthcare providers must now adopt big data strategies to keep up with the ever-increasing data deluge and enhance patient care. Therefore, this study aims to provide an overview of big data’s role in healthcare prediction by discussing its data sources, analytical techniques, and challenges. Also, it proposes a conceptual framework to be adopted in real-time big healthcare data analytics. In addition, this paper answers the following questions. First, what are the most popular Big Data sources that can be utilized in healthcare prediction? Second, how can Big Data sources and Big Data processing frameworks be integrated to enhance healthcare prediction accuracy? The studies discussed in this paper have been presented in popular scientific research databases, such as IEEE, Springer, and Elsevier. Machine learning, deep learning, and healthcare are some terms used to search for these studies. Hence, a review of published papers utilizing machine learning and deep learning methods for the purposes of diagnosing, detecting, predicting, and monitoring conditions pertaining to healthcare has been conducted. The conducted review identified the key challenges, research directions, and recommendations for real-time healthcare prediction using machine learning technologies. In addition, the proposed conceptual framework can serve as a general methodology to be adopted by other researchers in the healthcare domain.