Privacy-Preserving Generative Modeling and Clinical Validation of Longitudinal Health Records for Chronic Disease

2025-11-29

AI Summary

In chronic disease research, longitudinal health data are difficult to share due to stringent privacy constraints, while existing generative models lack both effective temporal modeling and formal privacy guarantees. To address this, we propose DP-TimeGAN—a novel generative framework integrating an enhanced TimeGAN architecture with rigorous differential privacy (DP) mechanisms. DP-TimeGAN is the first method to provide quantifiable ε-differential privacy for synthetic longitudinal clinical time-series data without compromising fidelity. Evaluated on a chronic kidney disease dataset, the generated data achieve an average realism score of 0.778 and match real-data performance in time-series transfer learning (TSTR). Clinical expert blind evaluation further confirms its superior diagnostic support capability over baseline methods. This work advances the privacy–utility trade-off frontier, establishing a new paradigm for compliant, high-quality medical AI modeling grounded in formal privacy theory.

Technology Category

• Machine Learning: Privacy
• Natural Language Processing: Generation
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Data privacy is a critical challenge in modern medical workflows as the adoption of electronic patient records has grown rapidly. Stringent data protection regulations limit access to clinical records for training and integrating machine learning models that have shown promise in improving diagnostic accuracy and personalized care outcomes. Synthetic data offers a promising alternative; however, current generative models either struggle with time-series data or lack formal privacy guaranties. In this paper, we enhance a state-of-the-art time-series generative model to better handle longitudinal clinical data while incorporating quantifiable privacy safeguards. Using real data from chronic kidney disease and ICU patients, we evaluate our method through statistical tests, a Train-on-Synthetic-Test-on-Real (TSTR) setup, and expert clinical review. Our non-private model (Augmented TimeGAN) outperforms transformer- and flow-based models on statistical metrics in several datasets, while our private model (DP-TimeGAN) maintains a mean authenticity of 0.778 on the CKD dataset, outperforming existing state-of-the-art models on the privacy-utility frontier. Both models achieve performance comparable to real data in clinician evaluations, providing robust input data necessary for developing models for complex chronic conditions without compromising data privacy.

Problem

• Generates synthetic longitudinal health records with privacy guarantees
• Addresses data scarcity for chronic disease machine learning models
• Balances privacy and utility in clinical time-series data generation

Innovation

• Enhanced time-series generative model for clinical data
• Incorporated quantifiable privacy safeguards in generative modeling
• Achieved high authenticity and privacy in synthetic data generation