Metraipolis › archive › dc_3e93d8a02e45

Alert-List Concordance for Evaluating Imputation Strategies in ICU Sepsis Prediction — arXiv:2610.22635

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22635
License (as archived)
CC0-1.0
Archived
2026-10-19T08:48:25.743Z
SHA-256 of the archived text
07dd66b500cca01cae1f20e5e09841833090bf6933f3b3751153b7d623fae9e0
Stable URL of this page
https://metraipolis.com/documento/dc_3e93d8a02e45

How to cite

Alert-List Concordance for Evaluating Imputation Strategies in ICU Sepsis Prediction — arXiv:2610.22635 — arXiv (en), https://arxiv.org/abs/2610.22635 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3e93d8a02e45 (Metraipolis archive dc_3e93d8a02e45, sha256 07dd66b500cca01cae1f20e5e09841833090bf6933f3b3751153b7d623fae9e0)
BibTeX
@misc{dc3e93d8a02e45,
  title = {Alert-List Concordance for Evaluating Imputation Strategies in ICU Sepsis Prediction — arXiv:2610.22635},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22635},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3e93d8a02e45; sha256 07dd66b500cca01cae1f20e5e09841833090bf6933f3b3751153b7d623fae9e0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22635. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Preprocessing is an under-measured reliability risk in clinical prediction: a model can keep a similar AUROC and still change who receives an alert. Imputation quality is commonly evaluated using reconstruction error or aggregate discrimination, neither of which directly measures agreement on which patients are flagged. At a matched alert rate, pipelines with similar aggregate performance can produce different patient lists. This question is especially relevant under the frequent, structured missingness of real ICU records. We therefore introduce alert-list concordance, which asks whether two pipelines identify the same high-risk patients, measured by the Jaccard similarity of their top-k% alert sets with patient-level bootstrap confidence intervals. On PhysioNet/CinC 2019 (40,336 patients, 71.9% missingness), we compare nine imputation strategies and a native-missingness baseline using a fixed XGBoost configuration, fitted and Platt-calibrated separately for each strategy. After Bonferroni correction, 22 of the 28 reconstruction-method pairs showed no statistically significant difference in patient-level AUROC, yet their alert lists overlap at Jaccard 0.518 to 0.750. Similar aggregate discrimination can therefore accompany different patient selections. ForwardFill is a separate outlier, pairing higher discrimination with the lowest overlap in the matrix, 0.40 to 0.45. The broad pattern holds within each hospital system and under six patient-level aggregation rules. At the row level, eight of ten methods fall within an AUROC range of 0.011. In this row-level pipeline, deep imputers did not outperform mean imputation on discrimination, and the sequential implementations cost 5 to 12 times mean imputation in total pipeline wall-clock time on our hardware.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Quantitative Methods (q-bio.QM).
Pagina del lavoro: https://arxiv.org/abs/2610.22635 — 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 2026-10-19T08:42:40.230Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).