CYBERSECURITY AND DATA QUALITY MANAGEMENT IN AI-DRIVEN SUSTAINABLE HEALTHCARE SYSTEMS

Abstract

The increasing prevalence of cybersecurity threats and the critical need for high-quality data in healthcare systems pose
significant challenges to data integrity, secrecy, and safety. Very complex Healthcare info is vulnerable to breaches and
anomalies, which is essential to implement robust ways to categorize potential threats and measure data quality. This study
investigates the use of machine-learning models to calculate cybersecurity tasks and assess the data quality in healthcare
using the 2019 secondary dataset. The variation of procedures with XGBoost, LightGBM Random-Forest LogisticRegression, Decision-Trees, and models were evaluated for their skill in identifying anomalies and measuring data
integrity. The results indicate that ensemble models with XGBoost (99.98% accuracy) outperform simpler models like
logistic Regression and decision trees, which showed higher misclassification rates. The superior presentation of collective
methods highlights the complexity of cybersecurity threats and the accuracy of healthcare data. These findings emphasize
the significance of using progressive machine-learning procedures in critical sectors like healthcare, where data quality and
security are paramount.