EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Realistic Synthetic Electronic Health Record Data Generation for Cardiovascular Risk Prediction

Kavitha Bai A. S, J. Somasekar

Journal of Vascular Diseases · 25.07.2026 · 5 (4) · 29

DOI: 10.3390/jvd5040029 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Vascular Diseases, online erschienen am 25.07.2026. Verfasst von Kavitha Bai A. S und 1 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Increasing access to Electronic Health Records (EHRs) has enabled the development of Machine Learning (ML) models to predict early cardiovascular disease (CVD) risk. Nevertheless, real EHR data is usually limited in availability and distribution because of confidentiality issues, legal limitations, and insufficient access. Synthetic data generation has become a promising approach to overcome such difficulties.

Objectives

This study proposes a Large Language Model (LLM)-guided retrieval-aware framework for generating realistic synthetic EHR data on a large scale to train ML models to predict cardiovascular risks accurately.

Methods

The framework uses a Tabular Denoising Diffusion Probabilistic Model to learn the underlying distribution of the original dataset and generate an initial synthetic dataset. To improve the clinical plausibility of the generated data, a knowledge-guided refinement module with LLaMA 2 13B combined with Retrieval-Augmented Generation (RAG) is introduced. The LLM analyzes statistical trends in real and synthetic data while retrieving relevant medical information to detect and correct clinically implausible correlations.

Results

Experimental findings show that the optimized synthetic dataset preserves important statistical features of the original data and achieves high performance in predicting CVD.

Conclusions

Thus, the framework offers a scalable, privacy-conservative method for generating realistic synthetic healthcare data suitable for medical research.

Zitieren

APA

S, K. B. A., & Somasekar, J. (2026). Realistic Synthetic Electronic Health Record Data Generation for Cardiovascular Risk Prediction. Journal of Vascular Diseases, 5(4), 29. https://doi.org/10.3390/jvd5040029

Vancouver

S KBA, Somasekar J. Realistic Synthetic Electronic Health Record Data Generation for Cardiovascular Risk Prediction. Journal of Vascular Diseases. 2026;5(4):29. doi:10.3390/jvd5040029

BibTeX
@article{S2026,
  author = {S, Kavitha Bai A. and Somasekar, J.},
  title = {Realistic Synthetic Electronic Health Record Data Generation for Cardiovascular Risk Prediction},
  journal = {Journal of Vascular Diseases},
  year = {2026},
  volume = {5},
  number = {4},
  pages = {29},
  doi = {10.3390/jvd5040029}
}
Kostenlos starten →