During the past several years, revealing some useful knowledge or protecting individual’s private information in an identifiable health dataset (i.e., within an Electronic Health Record) has become a tradeoff issue. Especially in this era of a global pandemic, security and privacy are often overlooked in lieu of usability. Privacy preserving data mining (PPDM) is definitely going to be have an important role to resolve this problem. Nevertheless, the scenario of mining information in an identifiable health dataset holds high complexity compared to traditional PPDM problems. Leaking individual private information in an identifiable health dataset has becomes a serious legal issue. In this article, the proposed Ant Colony System to Data Mining algorithm takes the multi-threshold constraint to secure and sanitize patents’ records in different lengths, which is applicable in a real medical situation. The experimental results show the proposed algorithm not only has the ability to hide all sensitive information but also to keep useful knowledge for mining usage in the sanitized database.

中文翻译：

---

共享医疗环境中基于多阈值蚁群系统的消毒模型

在过去的几年中，在可识别的健康数据集（即电子健康记录中）中揭示一些有用的知识或保护个人的私人信息已成为一个权衡问题。尤其是在这个全球大流行的时代，安全和隐私往往被忽视而不是可用性。隐私保护数据挖掘（PPDM）肯定会在解决这个问题上发挥重要作用。然而，与传统的 PPDM 问题相比，在可识别的健康数据集中挖掘信息的场景具有很高的复杂性。在可识别的健康数据集中泄露个人私人信息已成为一个严重的法律问题。在本文中，提出的蚁群系统数据挖掘算法采用多阈值约束来保护和清理不同长度的专利记录，这适用于真实的医疗情况。实验结果表明，所提出的算法不仅能够隐藏所有敏感信息，而且可以在净化后的数据库中保留对挖掘使用有用的知识。