Democratising Clinical AI through Dataset Condensation for Classical Clinical Models
This work addresses data democratisation in healthcare by enabling safe, model-agnostic sharing of synthetic clinical data, though it is incremental as it extends existing techniques to non-differentiable models.
The paper tackled the problem of dataset condensation for non-differentiable clinical models like decision trees and Cox regression, which are incompatible with existing methods, and resulted in a method that produces condensed datasets preserving model utility with effective differential privacy guarantees across six datasets.
Dataset condensation (DC) learns a compact synthetic dataset that enables models to match the performance of full-data training, prioritising utility over distributional fidelity. While typically explored for computational efficiency, DC also holds promise for healthcare data democratisation, especially when paired with differential privacy, allowing synthetic data to serve as a safe alternative to real records. However, existing DC methods rely on differentiable neural networks, limiting their compatibility with widely used clinical models such as decision trees and Cox regression. We address this gap using a differentially private, zero-order optimisation framework that extends DC to non-differentiable models using only function evaluations. Empirical results across six datasets, including both classification and survival tasks, show that the proposed method produces condensed datasets that preserve model utility while providing effective differential privacy guarantees - enabling model-agnostic data sharing for clinical prediction tasks without exposing sensitive patient information.