Securing healthcare data management using machine learning and blockchain technology: A comparative performance evaluation of support vector machine and conventional classifiers

Abstract

As access to healthcare has become more central to people’s daily lives, the amount of medical big data has grown exponentially. Wearable Internet of Things (IoT)-reliant technology is gaining popularity in the medical field as a means to improve patient care and reduce wait times. In recent years, billions of sensors, devices, and machines have been hooked up to the web. One such technology, remote patient monitoring, is increasingly used in modern patient care and treatment. In addition, these developments pose substantial security issues about the recording of transaction data and the transmission of information itself, and pose considerable dangers to users’ privacy. Concerns about the privacy of a patient’s medical records have the ability to discontinue treatment, putting the patient’s life in threat. Thus, a system is proposed using machine learning in combination with blockchain technology to allow secure management as well as analysis of large amounts of healthcare data. With the help of machine learning, it is feasible to sort through all of the data and extract out only the most pertinent information. This is accomplished with the help of trained methodologies. After this data has been saved, the next issue will be the exchange of data and ensuring its trustworthiness. The concept of blockchain is introduced at this point. The Blockchain technology relies on consensus to ensure that all data is accurate and that all transactions are conducted in a safe manner. The management of healthcare is one area where blockchain technology offers the ability to have a huge impact by placing patients at the center of the system and improving the privacy and portability of health records. This study is primarily concerned with finding solutions to issues relating to the administration of healthcare data by utilizing Blockchain technology and incorporating some crucial characteristics developed with Machine Learning. The performance evaluation of proposed Support Vector Machine is compared with the other conventional machine learning classifiers. It is observed from the experimental finding that performance accuracy of Support vector machine is 98% which is better as compared to other traditional machine learning classifiers.