Machine Learning in Healthcare: Applications, Current Status, and Future Prospects

Abstract

Significant progress in science related to an understanding of disease and treatment has contributed to an increase in the life span of people. With increasing urbanization and changing lifestyles, the burden of disease patterns has transitioned from communicable diseases to non-communicable diseases. In resource-limited countries, increasing rates of illness and economic challenges both are significant concerns related to healthcare. Long-term diseases such as diabetes mellitus, heart diseases, kidney diseases, and different types of malignancies are associated with significant morbidities. Reduction in mortality rates and improving quality of life are the key goals. Early diagnosis and better care with reasonable cost are key aspects for improving patient satisfaction. Enormous data and increased complexities have led to rising interest in the use of machine learning (ML) in healthcare. Disease prediction using ML is gaining significant attention in data science. ML is used to learn from a set of examples and evaluate the criteria by using training examples. Different classification algorithms include supervised learning, unsupervised learning, semi-supervised, and reinforcement learning. In this chapter, we discuss the key applications of different types of ML algorithms along with their utility in healthcare settings. The advantages and limitations of different algorithms and future prospectus are also discussed.