Service-Specific Heterogeneity in Sepsis Variable Significance and Machine Learning Model Performance: A Stratified Analysis of the BIAlert Cohort

Vista sencilla de ítem
dc.contributor.authorBorges-Sa, Marcio
dc.contributor.authorMacias-Fassio, Eric
dc.contributor.authorDelgado, Alejandro
dc.contributor.authorSantiago Salas Sosa
dc.contributor.authorAranda, María
dc.contributor.authorSocias, Antonia
dc.contributor.authordel Castillo, Alberto
dc.contributor.authorGiglio, Andrés
dc.coverage.spatialSuiza
dc.date.accessioned2026-08-18T16:38:35Z
dc.date.available2026-08-18T16:38:35Z
dc.date.issued2026-06-24
dc.description.abstractBackground/Objectives: Sepsis detection relies on clinical variables and scoring systems assumed to perform uniformly across hospital settings. However, sepsis phenotype distributions shift between clinical environments, suggesting that variable importance may be setting dependent. This study aimed to quantify service-specific variability in the discriminatory capacity of clinical variables for sepsis detection and to evaluate whether this heterogeneity translates into differential performance of machine learning models compared to traditional clinical scoring systems. Methods: This stratified sub-analysis of the BIAlert Sepsis cohort (203,755 patients; 11,864 sepsis episodes, 2014–2018) evaluated 61 structured quantitative variables across nine hospital services (≥90 sepsis episodes each). Within each service, the Mann–Whitney–Wilcoxon test (p < 0.01, Holm-corrected) assessed differences between septic and non-septic episodes. Five machine learning models (Random Forest/BIAlert, XGBoost, CatBoost, SVM, Neural Network) and three clinical rules (NEWS, SIRS, qSOFA) were evaluated globally and stratified across four clinical environments. Results: The proportion of significant variables ranged from 95.1% in the Emergency Department (58/61) to 37.7% in the Intensive Care Unit (23/61). Lactate was the only universally significant variable (9/9 services). Clinical scoring systems collapsed in Critical Care (qSOFA and NEWS AUC 0.459). BIAlert maintained the highest AUC across all environments (0.975–0.857). The Friedman test confirmed significant differences (χ2 = 28.00, p < 0.001), with BIAlert achieving a mean rank of 1.0. Conclusions: The discriminatory capacity of clinical variables for sepsis detection is not uniform across hospital services. ML models, particularly BIAlert, maintained robust performance where fixed-rule scoring systems failed.
dc.identifier.citationJournal of Clinical Medicine, Vol. 15, N° 13 (2026) pp. 1-14
dc.identifier.doihttps://doi.org/10.3390/jcm15134904
dc.identifier.issne2077-0383
dc.identifier.orcidhttps://orcid.org/0000-0002-0533-4531
dc.identifier.urihttps://hdl.handle.net/20.500.12254/7713
dc.language.isoen
dc.publisherMDPI
dc.rightsAtribución-NoComercial-CompartirIgual 3.0 Chile (CC BY-NC-SA 3.0 CL)
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/cl/
dc.titleService-Specific Heterogeneity in Sepsis Variable Significance and Machine Learning Model Performance: A Stratified Analysis of the BIAlert Cohort
dc.typeArticle
Archivos
Bloque original
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
jcm-15-04904-3.pdf
Tamaño:
1.1 MB
Formato:
Adobe Portable Document Format
Descargar
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
347 B
Formato:
Item-specific license agreed upon to submission
Descripción:
Descargar
Colecciones
Artículos de Revistas