Metraipolis › archive › dc_6f4d822ec0bf

VFR-Audit: Verdict-Level Reliability for Fairness Audits in Hospital Length-of-Stay Prediction — arXiv:2608.30846

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30846
License (as archived)
CC0-1.0
Archived
2026-10-17T07:44:58.008Z
SHA-256 of the archived text
25196ac8992a9aada10e39e42c9c80da9626cc31959eba9fc7c40c532f46c339
Stable URL of this page
https://metraipolis.com/documento/dc_6f4d822ec0bf

How to cite

VFR-Audit: Verdict-Level Reliability for Fairness Audits in Hospital Length-of-Stay Prediction — arXiv:2608.30846 — arXiv (en), https://arxiv.org/abs/2608.30846 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6f4d822ec0bf (Metraipolis archive dc_6f4d822ec0bf, sha256 25196ac8992a9aada10e39e42c9c80da9626cc31959eba9fc7c40c532f46c339)
BibTeX
@misc{dc6f4d822ec0bf,
  title = {VFR-Audit: Verdict-Level Reliability for Fairness Audits in Hospital Length-of-Stay Prediction — arXiv:2608.30846},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30846},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6f4d822ec0bf; sha256 25196ac8992a9aada10e39e42c9c80da9626cc31959eba9fc7c40c532f46c339},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30846. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Fairness audits in clinical Artificial Intelligence convert continuous fairness metrics into binary pass-or-fail verdicts against operational thresholds, where hospital governance boards, payers, and regulators act on the resulting verdicts. Such audits are repeated over time and across hospital sites, thus the same verdict can flip between pass and fail across audits. Existing uncertainty methods such as Bayesian posteriors, bootstrap confidence intervals, and permutation tests address verdict instability only at the continuous-metric level. Converting metric-level uncertainty into a verdict-stability claim remains a manual step that scales poorly across the (model, metric, attribute) cells an audit covers. Existing uncertainty methods also leave open whether bias-mitigation steps, such as reweighing or per-group threshold shifts, yield a stable passing verdict at the cost of model discrimination measured as AUROC or this http URL address this verdict-stability gap, we propose VFR-Audit, a framework built around the Verdict Flip Rate (VFR), a scalar bounded between 0 and 0.5 that measures the probability of verdict reversal under stratified bootstrap resampling. VFR-Audit reports VFR alongside three reliability axes, namely within-cohort resampling stability, audit-size sensitivity, and cross-hospital verdict agreement via Fleiss' kappa.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.30846 — 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 2026-10-17T07:28:26.628Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).