Generating Clinically Realistic EHR Data via a Hierarchy- and Semantics-Guided Transformer

TL;DR

This paper introduces HiSGT, a novel transformer-based framework that generates highly realistic synthetic EHR data by incorporating hierarchical and semantic information of clinical codes, improving data fidelity and utility.

Contribution

The paper proposes a hierarchical and semantics-guided transformer model that leverages clinical code relationships and descriptions for more accurate EHR data generation.

Findings

HiSGT outperforms baseline models in statistical similarity to real EHRs.

Synthetic data generated by HiSGT enhances downstream disease classification.

The approach improves the clinical fidelity of synthetic electronic health records.

Abstract

Generating realistic synthetic electronic health records (EHRs) holds tremendous promise for accelerating healthcare research, facilitating AI model development and enhancing patient privacy. However, existing generative methods typically treat EHRs as flat sequences of discrete medical codes. This approach overlooks two critical aspects: the inherent hierarchical organization of clinical coding systems and the rich semantic context provided by code descriptions. Consequently, synthetic patient sequences often lack high clinical fidelity and have limited utility in downstream clinical tasks. In this paper, we propose the Hierarchy- and Semantics-Guided Transformer (HiSGT), a novel framework that leverages both hierarchical and semantic information for the generative process. HiSGT constructs a hierarchical graph to encode parent-child and sibling relationships among clinical codes and employs a graph neural network to derive hierarchy-aware embeddings. These are then fused with semantic embeddings extracted from a pre-trained clinical language model (e.g., ClinicalBERT), enabling the Transformer-based generator to more accurately model the nuanced clinical patterns inherent in real EHRs. Extensive experiments on the MIMIC-III and MIMIC-IV datasets demonstrate that HiSGT significantly improves the statistical alignment of synthetic data with real patient records, as well as supports robust downstream applications such as chronic disease classification. By addressing the limitations of conventional raw code-based generative models, HiSGT represents a significant step toward clinically high-fidelity synthetic data generation and a general paradigm suitable for interpretable medical code representation, offering valuable applications in data augmentation and privacy-preserving healthcare analytics.