An Analysis of Integrating Machine Learning in Healthcare for Ensuring Confidentiality of the Electronic Records

Abstract

The adoption of sustainable electronic healthcare infrastructure has revolutionized healthcare services and ensured that E-health technology caters efficiently and promptly to the needs of the stakeholders associated with healthcare. Despite the phenomenal advancement in the present healthcare services, the major obstacle that mars the success of E-health is the issue of ensuring the confidentiality and privacy of the patients' data. A thorough scan of several research studies reveals that healthcare data continues to be the most sought after entity by cyber invaders. Various approaches and methods have been practiced by researchers to secure healthcare digital services. However, there are very few from the Machine learning (ML) domain even though the technique has the proactive ability to detect suspicious accesses against Electronic Health Records (EHRs). The main aim of this work is to conduct a systematic analysis of the existing research studies that address healthcare data confidentiality issues through ML approaches. B.A. Kitchenham guidelines have been practiced as a manual to conduct this work. Seven well-known digital libraries namely IEEE Xplore, Science Direct, Springer Link, ACM Digital Library, Willey Online Library, PubMed (Medical and Bio-Science), and MDPI have been included to perform an exhaustive search for the existing pertinent studies. Results of this study depict that machine learning provides a more robust security mechanism for sustainable management of the EHR systems in a proactive fashion, yet the specified area has not been fully explored by the researchers. K-nearest neighbor algorithm and KNIEM implementation tools are mostly used to conduct experiments on EHR systems' log data. Accuracy and performance measure of practiced techniques are not sufficiently outlined in the primary studies. This research endeavour depicts that there is a need to analyze the dynamic digital healthcare environment more comprehensively. Greater accuracy and effective implementation of ML-based models are the need of the day for ensuring the confidentiality of EHRs in a proactive fashion.