The proliferation of big data in various sectors, including healthcare, necessitates effective management and analysis techniques to extract valuable insights and support decision-making. Traditional methods often struggle with imprecise and incomplete data, leading to unreliable outcomes. This paper proposes a novel framework, the Rough-Fuzzy Enhanced Big Data Analytics Framework (RFE-BDAF), which integrates data mining and data fusion techniques with a rough-fuzzy approach to address these challenges. By leveraging the advanced analytical capabilities of rough set theory combined with fuzzy set theory, the framework aims to enhance data processing, security, privacy, and decision-making in big data environments. The proposed framework employs the Apriori algorithm for rule extraction and demonstrates its effectiveness using a real-world dataset from the MIMIC-III (Medical Information Mart for Intensive Care III) database. Detailed patient records such as symptoms, test results, diagnoses, and treatment outcomes are analyzed to showcase improved decision-making accuracy and data security. Empirical results indicate a significant improvement in data analysis, with a 92% accuracy rate in medical diagnoses compared to traditional systems. This research contributes to the development of more reliable and secure big data management systems, ultimately improving outcomes across various sectors.