Article

Semantic-Constrained Generative Modeling for Health-Care Data Under Distribution Shift

2026-08-13

Abstract excerpt

Generative models have become increasingly important for synthetic healthcare data generation, yet they often prioritize statistical fidelity while overlooking clinically meaningful semantic relationships, particularly under distribution shift. This study proposes a Semantic-Constrained Variational Autoencoder (SC-VAE) that integrates ontology-inspired clinical constraints into deep generative modelling to improve...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 713a38c3-5678-51ec-98ee-0847bf098828
DOI: 10.20944/preprints202608.0884.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Semantic-Constrained Generative Modeling for Health-Care Data Under Distribution ShiftDOI 10.20944/preprints202608.0884.v1Read

Generating synthetic electronic health record data: a methodological scoping review with benchmarking on phenotype data and open-source software.Semantic proximity Read

Generating Patient’s Electronic Health Records with Unseen Diseases Using Ontology-enhanced Generative Adversarial NetworksSemantic proximity Read

Large Language Models forecast Patient Health Trajectories enabling Digital TwinsSemantic proximity Read

A Multidimensional Benchmark of Generative Models for Neonatal Clinical Tabular Data: Trade-offs in Fidelity, Utility, and RealismSemantic proximity Read

Exploring the Role of Synthetic Data in the Future of AI in Healthcare: A Scoping Review of Frameworks, Challenges, and ImplicationsSemantic proximity Read

Mending Synthetic Healthcare Data with MAPS: Model Agnostic Post-hoc Synthetic Data Refinement FrameworkSemantic proximity Read

Synthetic Observational Health Data with GANs: from slow adoption to a boom in medical research and ultimately digital twins?Semantic proximity Read

A Multidimensional Evaluation of Privacy-Preserving Generative Models for Neonatal Clinical Tabular Data: Fidelity, Utility, and Realism Trade-offsSemantic proximity Read

Synthetic Observational Health Data with GANs: from slow adoption to a boom in medical research and ultimately digital twins?Semantic proximity Read

Evaluating Fidelity and Machine Learning Utility of Synthetic Tabular Data Generated Using Generative ModelsSemantic proximity Read

The Synthetic Fidelity–Stability Framework (SFSF): A Systematic Multi-Dimensional Benchmark of Synthetic Clinical Laboratory Data GeneratorsSemantic proximity Read

Tabular Transformer Generative Adversarial Network for Heterogeneous distribution in healthcareSemantic proximity Read