Scholarlink

Data privacy has become a critical concern in recent years, particularly with the rising incidence of data breaches in sensitive domains such as healthcare. According to recent reports, the number of healthcare data breaches has increased by over 50% in the last five years, exposing millions of patient records and highlighting the urgent need for robust privacy-preserving solutions. Federated learning is found as a feasible strategy to overcome these problems when training models using client data, with limitations on the compromise of data privacy. The findings reveal that while centralized clustering achieves superior performance due to full data access, federated clustering remains a viable alternative, demonstrating reasonable accuracy and robustness in privacy-sensitive scenarios. This study underscores the need for advanced federated learning techniques to balance the trade-off between data privacy and clustering performance, paving the way for more secure and efficient data analysis in critical fields such as healthcare.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Privacy-Preserving Approach for Clustering and Maintaining Healthcare Data Using Federated Learning Algorithms

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Meghavi Hada,
  • Manish Pandey,
  • Dhirendra Pratap Singh,
  • Jaytrilok Choudhary,
  • Rahul Haripriya

摘要

Data privacy has become a critical concern in recent years, particularly with the rising incidence of data breaches in sensitive domains such as healthcare. According to recent reports, the number of healthcare data breaches has increased by over 50% in the last five years, exposing millions of patient records and highlighting the urgent need for robust privacy-preserving solutions. Federated learning is found as a feasible strategy to overcome these problems when training models using client data, with limitations on the compromise of data privacy. The findings reveal that while centralized clustering achieves superior performance due to full data access, federated clustering remains a viable alternative, demonstrating reasonable accuracy and robustness in privacy-sensitive scenarios. This study underscores the need for advanced federated learning techniques to balance the trade-off between data privacy and clustering performance, paving the way for more secure and efficient data analysis in critical fields such as healthcare.