Cybersecurity Technologies for Protecting Social Medical Data in Public Healthcare Environments
DOI:
https://doi.org/10.70135/seejph.vi.485Keywords:
Cybersecurity, Healthcare Data, Anomaly Detection, Machine Learning, Electronic Health Records (EHR), Hybrid ModelAbstract
The growing digitization of healthcare systems has made safeguarding sensitive social medical data a crucial priority. The primary objective of this study is to utilize sophisticated cybersecurity technologies, particularly machine learning (ML) algorithms, to improve the security of Electronic Health Records (EHR) in public healthcare settings. The proposed approach presents an innovative technique that merges the advantages of isolation forest and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) [IF-DBSCAN]algorithms for anomaly detection, achieving an impressive accuracy rate of 0.968. The study examines the difficulties presented by the distinct characteristics of healthcare data, which includes both medical and social information. The inadequacy of conventional security measures has necessitated the incorporation of sophisticated machine learning algorithms to detect abnormal patterns that may indicate potential security breaches. The hybrid model, which combines isolation forest and DBSCAN, seeks to overcome the constraints of current anomaly detection techniques by offering a resilient and precise solution specifically designed for the healthcare domain. The isolation forest is highly proficient at isolating anomalies by leveraging the inherent attributes of normal data, whereas DBSCAN is adept at detecting clusters and outliers within densely populated data regions. The integration of these two algorithms is anticipated to augment the overall anomaly detection capabilities, thereby strengthening the cybersecurity stance of healthcare systems. The proposed method is subjected to thorough evaluation using real-world datasets obtained from public healthcare environments. The accuracy rate of 0.968 demonstrates the effectiveness of the hybrid approach in accurately differentiating between normal and anomalous activities in EHR data. The research makes a valuable contribution to the field of cybersecurity in healthcare and also tackles the increasing concerns related to the privacy and reliability of social medical data. This research introduces an innovative method for protecting social medical data in public healthcare settings. It utilizes a sophisticated combination of isolation forest and DBSCAN to detect anomalies. The method's high accuracy in the evaluation highlights its potential to greatly improve cybersecurity in healthcare systems, thereby guaranteeing the confidentiality and integrity of sensitive patient information.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.