Research

Paper

AI LLM March 10, 2026

Democratising Clinical AI through Dataset Condensation for Classical Clinical Models

Authors

Anshul Thakur, Soheila Molaei, Pafue Christy Nganjimi, Joshua Fieggen, Andrew A. S. Soltan, Danielle Belgrave, Lei Clifton, David A. Clifton

Abstract

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.

Metadata

arXiv ID: 2603.09356
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-03-10
Fetched: 2026-03-11 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.09356v1</id>\n    <title>Democratising Clinical AI through Dataset Condensation for Classical Clinical Models</title>\n    <updated>2026-03-10T08:36:39Z</updated>\n    <link href='https://arxiv.org/abs/2603.09356v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.09356v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CR'/>\n    <published>2026-03-10T08:36:39Z</published>\n    <arxiv:comment>22 pages, 5 figures, 5 tables</arxiv:comment>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Anshul Thakur</name>\n    </author>\n    <author>\n      <name>Soheila Molaei</name>\n    </author>\n    <author>\n      <name>Pafue Christy Nganjimi</name>\n    </author>\n    <author>\n      <name>Joshua Fieggen</name>\n    </author>\n    <author>\n      <name>Andrew A. S. Soltan</name>\n    </author>\n    <author>\n      <name>Danielle Belgrave</name>\n    </author>\n    <author>\n      <name>Lei Clifton</name>\n    </author>\n    <author>\n      <name>David A. Clifton</name>\n    </author>\n  </entry>"
}