The goal is useful data without unsafe disclosure: synthetic data that supports model development, collaboration, and validation while respecting privacy constraints.
01Sensitive health data
02Generative model
03Privacy and fidelity checks
04Shareable research asset
Recent papers
What this program is building
Selected recent and foundational papers, summarized around the task, why it matters, and the main technical result.
2025Patterns
MediSim: Multi-Granular Simulation for Enriching Longitudinal, Multi-Modal Electronic Health Records
1Longitudinal EHR
2Multi-granular simulator
3Synthetic patient timeline
Task
Generate longitudinal, multimodal EHR-like data at multiple clinical granularities.
Why it matters
Useful synthetic EHR can expand research access while reducing reliance on sensitive raw patient data.
Main result
MediSim models visits, codes, and modalities together so synthetic records remain clinically useful.
Send a concise note with the program name, your role, the problem you want to work on, and any relevant data, code, clinical setting, or research experience.