Security Enhancement in Electronic health records

Abstract

This paper has examined some of the ways in which machine learning (ML) can be used in electronic health records security. Indeed, the overall volume of data in the cloud has increased dramatically. This trend has also come with an increase in the amount of sensitive data that individuals and companies or organizations continue to keep in the cloud. As such, there has been a growing need for significant improvements in electronic health records security ─ to ensure that operations and data interactions in the cloud keep abreast with the dynamic nature of information technology. Motivated by the quest for electronic health records security, this paper has examined different approaches that most of the previous scholarly investigations (which focus on the adoption of machine learning in electronic health records security) have proposed ─ towards better threat detection. The paper has begun with a general algorithm responsible for establishing the summation of risk levels before proceeding to more advanced algorithms through which threats to cloud data could be determined. Imperative to note is that the advanced approaches have been found to embrace anomaly detection and signature detection, translating into a proposed hybrid model for threat detection in the cloud. Whereas a major weakness is that the proposed model is not compared to another competitive model, its strength lies in the capacity to give an insight into ways in which certain time frames and profile categories could be specified, leading to a better classification of cloud user profiles and the eventual detection of anomalies.