Computationally Efficient and Stable Real-World Synthetic Emergency Room EHR Data Generation: High Similarity and Privacy Preserving Diffusion Model Approach

Objective: This study aims to develop real-world synthetic electronic health record (EHR) for emergency departments using computationally efficient and stable diffusion probabilistic models. Materials: and Methods In this research, we compare the performance of diffusion models and state-of-the-art generative adversarial networks (GANs) in terms of statistical similarity, privacy, medical usefulness, and the feasibility of using the synthetic data for machine learning purposes. Results: Our results demonstrate that diffusion models are significantly more computationally efficient than GANs and perform comparably or slightly better in terms of similarity, privacy, and utility. We also found that the data quality of the diffusion model is statistically very similar for both categorical and continuous values and can address class imbalance precisely. Moreover, the machine learning usefulness of the synthetic data is almost identical to real EHR data. Our privacy analysis shows that the synthetic data generated by diffusion models is private. Discussion: These findings have significant implications for improving the efficiency of emergency settings such as disasters and enabling real-time emergency room data modeling. Therefore, it demonstrates the potential of diffusion models to generate computationally efficient high-quality synthetic data. Conclusion: The study concludes that diffusion models can generate real-world synthetic EHRs that are computationally efficient, private, and high-quality, which can be used for machine learning purposes in emergency settings.