Metraipolis › archive › dc_8914cc0debeb
CoMedBench: A Multi-Source Benchmark of Synthetic Medical Data Fidelity and Downstream Utility — arXiv:2608.12805
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.12805
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:27:26.079Z
- SHA-256 of the archived text
632f5008cab103cf400ad550a86662ee199645d3cef0b8fe137e13e02fd89757- Stable URL of this page
https://metraipolis.com/documento/dc_8914cc0debeb
How to cite
CoMedBench: A Multi-Source Benchmark of Synthetic Medical Data Fidelity and Downstream Utility — arXiv:2608.12805 — arXiv (en), https://arxiv.org/abs/2608.12805 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8914cc0debeb (Metraipolis archive dc_8914cc0debeb, sha256 632f5008cab103cf400ad550a86662ee199645d3cef0b8fe137e13e02fd89757)
BibTeX
@misc{dc8914cc0debeb,
title = {CoMedBench: A Multi-Source Benchmark of Synthetic Medical Data Fidelity and Downstream Utility — arXiv:2608.12805},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.12805},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8914cc0debeb; sha256 632f5008cab103cf400ad550a86662ee199645d3cef0b8fe137e13e02fd89757},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12805. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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). Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.12805 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T04:20:35.826Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).