cs.AINov 14, 2026

Evidence-Conditioned Completion and Synthesis of Electronic Health Records

Authors: Sicheng Shu, Parker Knight, Huitao Li, Yuan Luo, Yifan Peng, Shawn N. Murphy, Rui Yang, Chuan Hong

Organizations: Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, NC, USA · Department of Biostatistics, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA · Department of Biomedical Informatics and Medical Education, University of Washington, WA, USA · Department of Population Health Sciences, Weill Cornell Medicine, New York, NY, USA · 

Abstract

Patient information can guide electronic health record (EHR) generation, but how its amount shapes predictive utility and disclosure risk remains poorly characterized. Here we present EHRDiB, which unifies visit completion and synthesis by distinguishing original missingness from withheld inputs and combining a shared multimodal representation with an evidence-conditioned latent diffusion bridge. We compared EHRDiB with three completion and eight synthesis methods on MIMIC-IV and numerical and discretized Duke Health representations. Evaluation covered downstream predictive utility, generative diversity, and distributional fidelity for both tasks, and disclosure risk for synthesis. EHRDiB achieved the smallest utility gaps from real-data-trained classifiers in seven of eight completion comparisons. In synthesis, AUPRC gaps were 45.2% smaller for ten MIMIC-IV principal-diagnosis targets and 53.3% smaller for numerical Duke Health data relative to the best comparator. Synthesis with calibrated thresholding yielded the lowest marginal distribution error across all three datasets, with Coverage above 0.95 for both output rules. Across twelve evidence-fraction intervals in MIMIC-IV synthesis, membership-inference AUROC increased from 0.516 to 0.598 as the mean target evidence fraction rose from 0.20 to 0.50; utility gaps narrowed relative to the lowest evidence configuration but did not decrease monotonically. Our study provides a unified framework and empirical foundation for EHR generation that considers both its utility for clinical analysis and its information disclosure risk.

Figures & tables

Explore similar work

CardsList
  1. CDMT-EHR: A Continuous-Time Diffusion Framework for Generating Mixed-Type Time-Series Electronic Health Records

    Mar 24, 2026Shaonan Liu, Yuichiro Iwashita, Soichiro Nakako +2Synthetic Data GenerationDiffusion Models