# Synthesizing Multimodal Electronic Health Records via Predictive Diffusion Models

arXiv: https://arxiv.org/abs/2406.13942 · HTML: https://mlsanity.com/paper/2406.13942/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 16 of its 36 references that are in the map.
- First posted on arXiv 20 Jun 2024.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 16 of 16)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models](https://mlsanity.com/paper/2210.08933/) (2022)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism](https://mlsanity.com/paper/1608.05745/) (2016)
- [Dipole: Diagnosis Prediction in Healthcare via Attention-based Bidirectional Recurrent Neural Networks](https://mlsanity.com/paper/1706.05764/) (2017)
- [AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration](https://mlsanity.com/paper/1911.12205/) (2019)
- [RAIM: Recurrent Attentive and Intensive Model of Multimodal Patient Monitoring Data](https://mlsanity.com/paper/1807.08820/) (2018)
- [Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Records](https://mlsanity.com/paper/1709.01648/) (2017)
- [EVA: Generating Longitudinal Electronic Health Records Using Conditional Variational Autoencoders](https://mlsanity.com/paper/2012.10020/) (2020)
- [MedDiff: Generating Electronic Health Records using Accelerated Denoising Diffusion Model](https://mlsanity.com/paper/2302.04355/) (2023)
- [PromptEHR: Conditional Electronic Healthcare Records Generation with Prompt Learning](https://mlsanity.com/paper/2211.01761/) (2022)
- [Hierarchical Pretraining on Multimodal Electronic Health Records](https://mlsanity.com/paper/2310.07871/) (2023)

## Built on by (most cited first, 7 of 7)

- [SynEHRgy: Synthesizing Mixed-Type Structured Electronic Health Records using Decoder-Only Transformers](https://mlsanity.com/paper/2411.13428/) (2024)
- [MEDMKG: Benchmarking Medical Knowledge Exploitation with Multimodal Knowledge Graph](https://mlsanity.com/paper/2505.17214/) (2025)
- [DepMicroDiff: Diffusion-Based Dependency-Aware Multimodal Imputation for Microbiome Data](https://mlsanity.com/paper/2507.23676/) (2025)
- [Critical Challenges and Guidelines in Evaluating Synthetic Tabular Data: A Systematic Review](https://mlsanity.com/paper/2504.18544/) (2025)
- [Democratising Clinical AI through Dataset Condensation for Classical Clinical Models](https://mlsanity.com/paper/2603.09356/) (2026)
- [CDMT-EHR: A Continuous-Time Diffusion Framework for Generating Mixed-Type Time-Series Electronic Health Records](https://mlsanity.com/paper/2603.23719/) (2026)
- [AdaPCLA: Adaptive Prior-Calibrated Logit Adjustment for Long-Tailed Longitudinal EHR Generation](https://mlsanity.com/paper/2607.12645/) (2026)

## Abstract (arXiv)

Synthesizing electronic health records (EHR) data has become a preferred strategy to address data scarcity, improve data quality, and model fairness in healthcare. However, existing approaches for EHR data generation predominantly rely on state-of-the-art generative techniques like generative adversarial networks, variational autoencoders, and language models. These methods typically replicate input visits, resulting in inadequate modeling of temporal dependencies between visits and overlooking the generation of time information, a crucial element in EHR data. Moreover, their ability to learn visit representations is limited due to simple linear mapping functions, thus compromising generation quality. To address these limitations, we propose a novel EHR data generation model called EHRPD. It is a diffusion-based model designed to predict the next visit based on the current one while also incorporating time interval estimation. To enhance generation quality and diversity, we introduce a novel time-aware visit embedding module and a pioneering predictive denoising diffusion probabilistic model (PDDPM). Additionally, we devise a predictive U-Net (PU-Net) to optimize P-DDPM.We conduct experiments on two public datasets and evaluate EHRPD from fidelity, privacy, and utility perspectives. The experimental results demonstrate the efficacy and utility of the proposed EHRPD in addressing the aforementioned limitations and advancing EHR data generation.