Abstract Medical organizations are progressively navigating a highly unstable, complex environment in which scientific improvements and new medical delivery business models are only factors. The key objective of every medical provider is to provide preeminent class care to all of their patients. It is obvious that medical science is increasingly becoming more intricate and expensive, and achieving its final target is a serious challenge. Deep learning (DL) methods are widely used in many fields of science such as speech recognition, image processing and classification, and language learning methods processing. In the same way, existing typical data analysis and processing methods have numerous restrictions on a large quantity of data processing. Both DL and big data analytics are currently extremely active areas of research in medical science. Big data is gaining more importance because many medical organizations have collected large amounts of information related to its domain. The ability to handle big data enables conducting unprecedented research studies and implementing new models of medical science delivery. The existing DL techniques used in generic scenarios, therefore, has a major presence in specific scenarios like medicine and machine learning landscapes in big data. Another reason for poor performance is the high involvement of humans in the designing of algorithms for medicine big data through DL techniques. In this chapter, we analyzed the relationship between DL and big data, their roles in medicine, their effects on the development of medicine industry, applications of DL and big data in medicine, challenges and promises of both DL and big data with respect of medicine, and prevailing techniques and tools for performance optimization of medical big data that can be used by the medical industry.