{
  "abstract": "Background: High AUROC is often taken as evidence that a transcriptomic classifier is promising, but rank discrimination can conceal fixed-threshold failure after cohort or platform transfer. Methods: We benchmarked four GEO whole-blood cohorts: GSE65682 for discovery, GSE95233 for external microarray validation, GSE154918 for cross-platform RNA-seq validation, and GSE28750 for non-infectious inflammation stress testing. We compared logistic-regression workflows using training-derived standard scaling, training-derived robust scaling, sample-wise rank normalization with training-derived scaling, and robust scaling using unsupervised external-cohort reference statistics. Internal performance used five-fold cross-validation with fold-contained imputation and scaling. External uncertainty used 2,000 stratified bootstrap replicates. Results: Internal discrimination was very high for all strategies, but external validation revealed threshold collapse for training-derived standard and robust scaling. In GSE154918, both had balanced accuracy 0.50 at the 0.5 threshold despite very high AUROC, equivalent to random classification at that fixed threshold. The strict-inductive sample-rank strategy preserved fixed-threshold performance across external cohorts (balanced accuracy 0.95–1.00). Robust external-cohort adaptation also performed well (0.95–1.00) but uses unlabeled external-cohort distribution statistics and is therefore reported as adaptation rather than fixed single-sample transfer. Calibration and regularization sensitivity did not rescue the failing training-derived scaling strategies. In the sepsis-versus-non-infectious-inflammation stress test, robust external-cohort adaptation had the highest observed balanced accuracy (0.80, 95% CI 0.61–0.95), but its difference from sample-rank normalization was uncertain in paired bootstrap analysis. Conclusions: High AUROC can mask fixed-threshold failure in sepsis transcriptomic classifiers. In this benchmark, strict-inductive sample-rank normalization was the most stable fixed external strategy, while robust external-cohort scaling was best interpreted as unsupervised cohort adaptation whose reliability depends on external reference-sample availability.",
  "abstract_shown": true,
  "affiliations": [
    "Quanzhou Medical College, Quanzhou, Fujian, People’s Republic of China"
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Hongwei Zheng"
    },
    {
      "name": "Wenbiao Chen"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6ath638q859c6.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pone.0357585",
  "fulltext_url": null,
  "id": "6ath638q859c6",
  "issns": [
    "1932-6203"
  ],
  "landing_url": "https://doi.org/10.1371/journal.pone.0357585",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2713|Sepsis Diagnosis and Treatment"
    ],
    [
      "plos",
      "/Biology and life sciences/Biochemistry/Biomarkers"
    ],
    [
      "plos",
      "/Biology and life sciences/Biochemistry/Nucleic acids/RNA/Non-coding RNA/Transfer RNA"
    ],
    [
      "plos",
      "/Biology and life sciences/Computational biology/Genome analysis/Transcriptome analysis"
    ],
    [
      "plos",
      "/Biology and life sciences/Genetics/Genomics/Genome analysis/Transcriptome analysis"
    ],
    [
      "plos",
      "/Biology and life sciences/Immunology/Immune response/Inflammation"
    ],
    [
      "plos",
      "/Computer and information sciences/Data management/Metadata"
    ],
    [
      "plos",
      "/Computer and information sciences/Software engineering/Preprocessing"
    ],
    [
      "plos",
      "/Engineering and technology/Electronics engineering/Electronics/Comparators"
    ],
    [
      "plos",
      "/Engineering and technology/Software engineering/Preprocessing"
    ],
    [
      "plos",
      "/Medicine and health sciences/Clinical medicine/Signs and symptoms/Inflammation"
    ],
    [
      "plos",
      "/Medicine and health sciences/Clinical medicine/Signs and symptoms/Sepsis"
    ],
    [
      "plos",
      "/Medicine and health sciences/Immunology/Immune response/Inflammation"
    ]
  ],
  "openalex": "W7207750790",
  "pdf_url": "https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0357585&type=printable",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-03",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/6ath638q859c6.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:56Z",
      "native_id": "10.1371/journal.pone.0357585",
      "source": "plos",
      "url": "https://doi.org/10.1371/journal.pone.0357585"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "plos:computational biology",
      "subfield": "bioinformatics"
    },
    {
      "field": "biology",
      "origin": "plos:genomics",
      "subfield": "genetics-genomics"
    },
    {
      "field": "biology",
      "origin": "plos:immunology",
      "subfield": "immunology"
    }
  ],
  "title": "High AUROC can mask decision failure in sepsis transcriptomic classifiers: Preprocessing stability outweighs post hoc calibration across cohorts",
  "title_text": "High AUROC can mask decision failure in sepsis transcriptomic classifiers: Preprocessing stability outweighs post hoc calibration across cohorts",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:56Z",
  "url": "https://research.draconitic.com/paper/6ath638q859c6",
  "venue": "PLOS One",
  "versions": []
}