CoMedBench: A Multi-Source Benchmark of Synthetic Medical Data Fidelity and Downstream Utility

Access to clinical data is essential for developing reliable healthcare machine learning systems, but direct use of electronic health records is constrained by privacy regulation, institutional review, data-use agreements, and the risk of re-identification. Synthetic data promises a practical alternative: it can preserve useful statistical and clinical structure while reducing exposure of sensitive patient records. Prior studies often evaluate a single generator, one dataset, or a narrow downstream task, making it difficult to know when synthetic data can support model development and when it fails to preserve task-critical signal. We introduce CoMedBench, a reproducible benchmark that evaluates a family of generators under a common clinical-validity framework and one shared training and evaluation engine, spanning static tabular and temporal downstream tasks on established critical-care datasets. In total the benchmark spans 37 dataset-task pairs across two modalities consists of 20 static tabular and 17 temporal ICU time-series-drawn from seven public data sources: three intensive-care databases (MIMIC-III, MIMIC-IV, and eICU) together with the UCI Machine Learning Repository, the CDC BRFSS diabetes cohort (2015), NHANES (1999-2014), and the pycox survival datasets (GBSG and METABRIC). The benchmark evaluates both statistical fidelity and task utility by comparing models trained and tested across real and synthetic data. In these settings, synthetic training data preserves most of the downstream signal: on tabular tasks the reference generator CoMed-CTGAN retains a mean AUROC utility (the synthetic-to-real performance ratio) of 90.6%, rising to 97.3% for the strongest generator, CoMed-TVAE. Temporal ICU tasks are harder and more generator-sensitive: CoMed-CTGAN retains 81.6% (AUROC) and only 64.0% under the imbalance-sensitive AUPRC, whereas CoMed-TVAE still retains ~95% (AUROC).

Clinically Grounded Privacy Evaluation of Medical LMs

Medical language models (LMs) can memorize and reproduce protected health information, but privacy evaluations often focus on recovery of training text rather than disclosure under realistic threat models. We introduce a clinically grounded framework that evaluates leakage along a graded axis of adversarial access, ranging from publicly inferable demographics to leaked note fragments. At each tier, we measure verbatim memorization of patient-specific text and semantic leakage of sensitive diagnoses. Applying the framework to an LM pretrained on 378k clinical notes, we find that routine encounter metadata (i.e. name, date of birth, provider, practice, visit date) elicits high rates of verbatim memorization across a patient's timeline and sensitive-diagnosis recovery (AUROC 0.91 for abortion, 0.81 for HIV). At the same time, exact-match memorization can overstate disclosure: 36% of memorized tokens reflect templated documentation. Our work highlights the risks of training on longitudinal clinical data, providing a practical framework for contextual privacy evaluation of medical LMs.

American Family Cohort, a data resource description

This manuscript is a research resource description and presents a large and novel Electronic Health Records (EHR) data resource, American Family Cohort (AFC). The AFC data is derived from Centers for Medicare and Medicaid Services (CMS) certified American Board of Family Medicine (ABFM) PRIME registry. The PRIME registry is the largest national Qualified Clinical Data Registry (QCDR) for Primary Care. The data is converted to a popular common data model, the Observational Health Data Sciences and Informatics (OHDSI) Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM). The resource presents approximately 90 million encounters for 7.5 million patients. All 100% of the patients present age, gender, and address information, and 73% report race. Nealy 93% of patients have lab data in LOINC, 86% have medication data in RxNorm, 93% have diagnosis in SNOWMED and ICD, 81% have procedures in HCPCS or CPT, and 61% have insurance information. The richness, breadth, and diversity of this research accessible and research ready data is expected to accelerate observational studies in many diverse areas. We expect this resource to facilitate research in many years to come.

A Knowledge Graph-based Approach for Exploring the U.S. Opioid Epidemic

The United States is in the midst of an opioid epidemic with recent estimates indicating that more than 130 people die every day due to drug overdose. The over-prescription and addiction to opioid painkillers, heroin, and synthetic opioids, has led to a public health crisis and created a huge social and economic burden. Statistical learning methods that use data from multiple clinical centers across the US to detect opioid over-prescribing trends and predict possible opioid misuse are required. However, the semantic heterogeneity in the representation of clinical data across different centers makes the development and evaluation of such methods difficult and non-trivial. We create the Opioid Drug Knowledge Graph (ODKG) -- a network of opioid-related drugs, active ingredients, formulations, combinations, and brand names. We use the ODKG to normalize drug strings in a clinical data warehouse consisting of patient data from over 400 healthcare facilities in 42 different states. We showcase the use of ODKG to generate summary statistics of opioid prescription trends across US regions. These methods and resources can aid the development of advanced and scalable models to monitor the opioid epidemic and to detect illicit opioid misuse behavior. Our work is relevant to policymakers and pain researchers who wish to systematically assess factors that contribute to opioid over-prescribing and iatrogenic opioid addiction in the US.