Modelling of healthcare data analytics using optimal machine learning model in big data environment

Recent advances in wireless networking, big data technologies, namely Internet of Things (IoT) 5G networks, health care big data analytics, and other technologies in artificial intelligence (AI) and wearables, have supported the progression of intellectual disease diagnosis methods. Medical data covers all patient data such as pharmacy texts, electronic health reports (EHR), prescriptions, study data from medical journals, clinical photographs, and diagnostic reports. Big data is a renowned method in the healthcare sector, with beneficial datasets that are highly difficult, voluminous, and rapid for healthcare providers for interpreting and computing using prevailing tools. This study combines concepts like deep learning (DL) and big data analytics in medical field. This article develops a new healthcare data analytics using optimal machine learning model in big data environment (HDAOML-BDE) technique. The presented HDAOML-BDE technique mainly aims to examine the healthcare data for disease detection and classification in the big data environment. For handling big data, the HDAOML-BDE technique uses Hadoop MapReduce environment. In addition, the HDAOML-BDE technique uses manta ray foraging optimization-based feature selection (MRFO-FS) technique to reduce high dimensionality problems. Moreover, the HDAOML-BDE method uses relevance vector machine (RVM) model for the healthcare data environment. Furthermore, the arithmetic optimization algorithm (AOA) is utilized for the parameter tuning of the RVM classifier. The simulation results of the HDAOML-BDE technique are tested on a healthcare dataset, and the outcomes portray the improved performance of the HDAOML-BDE strategy over recent approaches in different measures.