Securing Sensitive Medical Information with Basic and Pre-large Coati Optimization Algorithm for E-Health System Data Sanitation

Privacy preservation is increasingly crucial in e-Health systems, particularly within the realm of privacy-preserving data mining, which aims to reveal underlying patterns while concealing sensitive information for data sanitization purposes. The need to protect sensitive patient information while c...

Full description

Saved in:
Bibliographic Details
Published in:Wireless personal communications 2024-05, Vol.136 (2), p.1261-1281
Main Authors: Madhavi, M., Sasirooba, T., Kumar, G. Kranthi
Format: Article
Language:English
Subjects:
Algorithms
Communications Engineering
Computer Communication Networks
Data mining
Effectiveness
Engineering
Heuristic methods
Networks
Optimization
Optimization algorithms
Privacy
Sanitation
Side effects
Signal,Image and Speech Processing
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Privacy preservation is increasingly crucial in e-Health systems, particularly within the realm of privacy-preserving data mining, which aims to reveal underlying patterns while concealing sensitive information for data sanitization purposes. The need to protect sensitive patient information while complying with regulatory standards as well as the need to analyze meaningful data represents significant challenges in the privacy protection within e-Health systems. Additionally, heuristics have been developed to remove transactions from sensitive data. These heuristic algorithms are slower to adapt and have a shorter convergence time. As a result, reasonable side effects are hard to achieve.To address this, a novel approach based on the Coati optimization algorithm (COA) is introduced in this study. This algorithm facilitates the selection of appropriate transactions for removal, enhancing the effectiveness of data sanitization. With the help of COA, two frameworks are developed, namely the simple COA for removing transactions (sCOA2RT) and the pre-large COA for removing transactions (pCOA2RT). A fitness evaluation algorithm examines four side effects, including hiding failure, artificial costs, missing costs, and database dissimilarities. The effectiveness of these frameworks is demonstrated on three e-Health datasets, demonstrating that they are capable of achieving reasonable side effects compared to previous approaches.
ISSN:0929-6212
1572-834X
DOI:10.1007/s11277-024-11342-6