An Optimal Attribute-Focused Privacy-Preserving Anonymization Scheme for Healthcare Data in Cloud Systems

Modern healthcare systems rely on the accumulation and analysis of enormous datasets about individual patients, which is where innovative computer technologies such as cloud-based systems come into play. When it comes to protecting the privacy and security of sensitive data stored in cloud services, users face a significant challenge. Protecting people's privacy and securing their personal information is essential. Utilizing the K-means clustering technique, this study presents a novel method for identifying the optimal attribute-focused anonymization algorithm. Here, the Gaussian distribution is applied to eradicate outliers, thereby dramatically improving the quality of anonymized data. Extensive experiments demonstrate that the proposed method reduces information loss and execution time by a factor of 2 and 4, respectively, when compared to current best practices. In addition, its scalability surpasses that of alternative methods for safeguarding the privacy of cloud-stored healthcare information.