AI RESEARCH
CDMT-EHR: A Continuous-Time Diffusion Framework for Generating Mixed-Type Time-Series Electronic Health Records
arXiv CS.LG
•
ArXi:2603.23719v1 Announce Type: new Electronic health records (EHRs) are invaluable for clinical research, yet privacy concerns severely restrict data sharing. Synthetic data generation offers a promising solution, but EHRs present unique challenges: they contain both numerical and categorical features that evolve over time. While diffusion models have nstrated strong performance in EHR synthesis, existing approaches predominantly rely on discrete-time formulations, which suffer from finite-step approximation errors and coupled.