An Analytical Approach to Privacy and Performance Trade-Offs in Healthcare Data Sharing

TL;DR

This paper evaluates privacy-preserving data anonymization methods in healthcare, balancing patient privacy with the utility of machine learning models, especially for vulnerable populations, using real hospital data.

Contribution

It compares three anonymization techniques, demonstrating MO-OBAM's superior utility preservation while enhancing privacy protection in healthcare data sharing.

Findings

k-anonymity offers limited privacy protection

Zheng et al.'s method and MO-OBAM provide stronger safeguards

MO-OBAM maintains ML model performance with minimal utility loss

Abstract

The secondary use of healthcare data is vital for research and clinical innovation, but it raises concerns about patient privacy. This study investigates how to balance privacy preservation and data utility in healthcare data sharing, considering the perspectives of both data providers and data users. Using a dataset of adult patients hospitalized between 2013 and 2015, we predict whether sepsis was present at admission or developed during the hospital stay. We identify sub-populations, such as older adults, frequently hospitalized patients, and racial minorities, that are especially vulnerable to privacy attacks due to their unique combinations of demographic and healthcare utilization attributes. These groups are also critical for machine learning (ML) model performance. We evaluate three anonymization methods-$k$-anonymity, the technique by Zheng et al., and the MO-OBAM model-based on their ability to reduce re-identification risk while maintaining ML utility. Results show that $k$-anonymity offers limited protection. The methods of Zheng et al. and MO-OBAM provide stronger privacy safeguards, with MO-OBAM yielding the best utility outcomes: only a 2% change in precision and recall compared to the original dataset. This work provides actionable insights for healthcare organizations on how to share data responsibly. It highlights the need for anonymization methods that protect vulnerable populations without sacrificing the performance of data-driven models.