Scholarlink

<p>Synthetic data generation is increasingly proposed as an alternative to classical anonymization for sharing health data. We compared concrete applications of both approaches on a small, high-dimensional health claims dataset, assessing their impact on fidelity, reproducibility of study outcomes, and privacy risks. To reflect different sharing contexts, we considered a context-independent, higher-risk scenario with no assumptions about potential attacks, and a context-dependent, lower-risk scenario informed by threat modeling. Analyses on anonymized and synthetic data yielded results similar to those from the original study data, but came at the cost of higher uncertainty when estimating hazard ratios. As expected, higher data utility and fidelity were related to higher privacy risks. Our findings provide a reusable workflow and comparative insights into anonymization and synthetization and show that both methods are valuable means to lower privacy risks in data sharing scenarios but verifying results on the original data should be done whenever possible.</p>

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 case study comparing anonymized and synthetic health insurance claims data for medication safety assessments

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月13日

查看全文
  • Mehmed Halilovic,
  • Thierry Meurers,
  • Marco Alibone,
  • Marion Ludwig,
  • Paul Tiwald,
  • Nico Sieberg-Riedel,
  • Steven Wolter,
  • Lisa Kühnel,
  • Steffen Hess,
  • Fabian Prasser,
  • Karen Otte

摘要

Synthetic data generation is increasingly proposed as an alternative to classical anonymization for sharing health data. We compared concrete applications of both approaches on a small, high-dimensional health claims dataset, assessing their impact on fidelity, reproducibility of study outcomes, and privacy risks. To reflect different sharing contexts, we considered a context-independent, higher-risk scenario with no assumptions about potential attacks, and a context-dependent, lower-risk scenario informed by threat modeling. Analyses on anonymized and synthetic data yielded results similar to those from the original study data, but came at the cost of higher uncertainty when estimating hazard ratios. As expected, higher data utility and fidelity were related to higher privacy risks. Our findings provide a reusable workflow and comparative insights into anonymization and synthetization and show that both methods are valuable means to lower privacy risks in data sharing scenarios but verifying results on the original data should be done whenever possible.