{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T08:32:56Z","timestamp":1793694776489,"version":"4.5.1"},"reference-count":25,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T00:00:00Z","timestamp":1782259200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>Background\/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\u20132018) evaluated 61 structured quantitative variables across nine hospital services (\u226590 sepsis episodes each). Within each service, the Mann\u2013Whitney\u2013Wilcoxon test (p &lt; 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\u20130.857). The Friedman test confirmed significant differences (\u03c72 = 28.00, p &lt; 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.<\/jats:p>","DOI":"10.3390\/jcm15134904","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T03:20:21Z","timestamp":1782357621000},"page":"4904","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Service-Specific Heterogeneity in Sepsis Variable Significance and Machine Learning Model Performance: A Stratified Analysis of the BIAlert Cohort"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9929-3111","authenticated-orcid":false,"given":"Marcio","family":"Borges-Sa","sequence":"first","affiliation":[{"name":"Multidisciplinary Sepsis Unit, Son Llatzer University Hospital, 07198 Palma de Mallorca, Spain"},{"name":"Multidisciplinary Sepsis Group, Health Research Institute of the Balearic Islands (IdISBa), 07120 Palma de Mallorca, Spain"},{"name":"Balearic Islands University, 07122 Palma de Mallorca, Spain"},{"name":"Fundaci\u00f3n C\u00f3digo Sepsis, 46003 Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8275-5294","authenticated-orcid":false,"given":"Eric","family":"Macias-Fassio","sequence":"additional","affiliation":[{"name":"Instituto de Ingenier\u00eda del Conocimiento (IIC), 28049 Madrid, Spain"},{"name":"BiometricsAI, Universidad Aut\u00f3noma de Madrid, 28049 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9782-4731","authenticated-orcid":false,"given":"Alejandro","family":"Delgado","sequence":"additional","affiliation":[{"name":"Instituto de Ingenier\u00eda del Conocimiento (IIC), 28049 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Santiago","family":"Salas-Sosa","sequence":"additional","affiliation":[{"name":"Instituto de Ingenier\u00eda del Conocimiento (IIC), 28049 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mar\u00eda","family":"Aranda","sequence":"additional","affiliation":[{"name":"Multidisciplinary Sepsis Unit, Son Llatzer University Hospital, 07198 Palma de Mallorca, Spain"},{"name":"Multidisciplinary Sepsis Group, Health Research Institute of the Balearic Islands (IdISBa), 07120 Palma de Mallorca, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonia","family":"Socias","sequence":"additional","affiliation":[{"name":"Multidisciplinary Sepsis Unit, Son Llatzer University Hospital, 07198 Palma de Mallorca, Spain"},{"name":"Multidisciplinary Sepsis Group, Health Research Institute of the Balearic Islands (IdISBa), 07120 Palma de Mallorca, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alberto","family":"del Castillo","sequence":"additional","affiliation":[{"name":"Multidisciplinary Sepsis Unit, Son Llatzer University Hospital, 07198 Palma de Mallorca, Spain"},{"name":"Multidisciplinary Sepsis Group, Health Research Institute of the Balearic Islands (IdISBa), 07120 Palma de Mallorca, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andres","family":"Giglio","sequence":"additional","affiliation":[{"name":"Multidisciplinary Sepsis Unit, Son Llatzer University Hospital, 07198 Palma de Mallorca, Spain"},{"name":"Multidisciplinary Sepsis Group, Health Research Institute of the Balearic Islands (IdISBa), 07120 Palma de Mallorca, Spain"},{"name":"Balearic Islands University, 07122 Palma de Mallorca, Spain"},{"name":"Critical Care Department, Cl\u00ednica Las Condes Hospital, Santiago 7591046, Chile"},{"name":"Faculty of Medicine, Finis Terrae University, Santiago 7501015, Chile"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1001\/jama.2016.0287","article-title":"The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3)","volume":"315","author":"Singer","year":"2016","journal-title":"JAMA"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2003","DOI":"10.1001\/jama.2019.5791","article-title":"Derivation, Validation, and Potential Treatment Implications of Novel Clinical Phenotypes for Sepsis","volume":"321","author":"Seymour","year":"2019","journal-title":"JAMA"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"816","DOI":"10.1016\/S2213-2600(17)30294-1","article-title":"Classification of patients with sepsis according to blood genomic endotype","volume":"5","author":"Scicluna","year":"2017","journal-title":"Lancet Respir. Med."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1097\/CCM.0000000000003084","article-title":"Unsupervised Analysis of Transcriptomics in Bacterial Sepsis Across Multiple Datasets","volume":"46","author":"Sweeney","year":"2018","journal-title":"Crit. Care Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1360","DOI":"10.1007\/s00134-023-07239-w","article-title":"Uncovering heterogeneity in sepsis: A comparative analysis of subphenotypes","volume":"49","author":"Kennedy","year":"2023","journal-title":"Intensive Care Med."},{"key":"ref_6","first-page":"256","article-title":"Clinical subtypes in critically ill patients with sepsis","volume":"29","author":"Rademaker","year":"2025","journal-title":"Crit. Care"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1001\/jama.2016.0288","article-title":"Assessment of Clinical Criteria for Sepsis","volume":"315","author":"Seymour","year":"2016","journal-title":"JAMA"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"906","DOI":"10.1164\/rccm.201604-0854OC","article-title":"Quick Sepsis-related Organ Failure Assessment, Systemic Inflammatory Response Syndrome, and Early Warning Scores for Detecting Clinical Deterioration in Infected Patients outside the Intensive Care Unit Am","volume":"195","author":"Churpek","year":"2017","journal-title":"J. Respir. Crit. Care Med."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1490","DOI":"10.1016\/j.ajem.2018.10.058","article-title":"Comparison of SIRS, qSOFA, and NEWS in the ED","volume":"37","author":"Usman","year":"2019","journal-title":"Am. J. Emerg. Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"ooab062","DOI":"10.1093\/jamiaopen\/ooab062","article-title":"Comparison of early warning scores for sepsis early identification and prediction in the general ward setting","volume":"4","author":"Yu","year":"2021","journal-title":"JAMIA Open"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1186\/s13054-018-1952-x","article-title":"Performance of qSOFA outside ICU: Systematic review","volume":"22","author":"Song","year":"2018","journal-title":"Crit. Care"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wang, C., Xu, R., Zeng, Y., and Hu, X. (2022). Comparison of qSOFA, SIRS and NEWS: A meta-analysis. PLoS ONE, 17.","DOI":"10.1371\/journal.pone.0266755"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1007\/s00134-019-05872-y","article-title":"Machine learning for the prediction of sepsis: A systematic review and meta-analysis of diagnostic test accuracy","volume":"46","author":"Fleuren","year":"2020","journal-title":"Intensive Care Med."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1001\/jamainternmed.2021.2626","article-title":"External Validation of a Widely Implemented Proprietary Sepsis Prediction Model in Hospitalized Patients","volume":"181","author":"Wong","year":"2021","journal-title":"JAMA Intern. Med."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1001\/jamainternmed.2022.7182","article-title":"Factors Associated With Variability in the Performance of a Proprietary Sepsis Prediction Model Across 9 Networked Hospitals in the US","volume":"183","author":"Lyons","year":"2023","journal-title":"JAMA Intern. Med."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1455","DOI":"10.1038\/s41591-022-01894-0","article-title":"Prospective, multi-site study of patient outcomes after implementation of the TREWS machine learning-based early warning system for sepsis","volume":"28","author":"Adams","year":"2022","journal-title":"Nat. Med."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1007\/s00134-021-06574-0","article-title":"Source-specific host response and outcomes in critically ill patients with sepsis: A prospective cohort study","volume":"48","author":"Butler","year":"2022","journal-title":"Intensive Care Med."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"855","DOI":"10.3390\/jcm15020855","article-title":"Hospital-Wide Sepsis Detection: A Machine Learning Model Based on Prospectively Expert-Validated Cohort","volume":"15","author":"Giglio","year":"2026","journal-title":"J. Clin. Med."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Borges-Sa, M., Giglio, A., Aranda, M., Socias, A., del Castillo, A., Mena, J., Franco, S., Ortega, M., Nieto, Y., and Estrada, V. (2025). Decoding Sepsis: A 16-Year Retrospective Analysis of Activation Patterns, Mortality Predictors, and Outcomes from a Hospital-Wide Sepsis Protocol. J. Clin. Med., 14.","DOI":"10.20944\/preprints202507.2650.v1"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1001\/jama.2016.20328","article-title":"Prognostic Accuracy of the SOFA Score, SIRS Criteria, and qSOFA Score for In-Hospital Mortality Among Adults With Suspected Infection Admitted to the Intensive Care Unit","volume":"317","author":"Raith","year":"2017","journal-title":"JAMA"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Lee, K.H., Dong, J.J., Kim, S., Kim, D., Hyun, J.H., Chae, M.H., Lee, B.S., and Song, Y.G. (2022). Prediction of Bacteremia Based on 12-Year Medical Data Using a Machine Learning Approach: Effect of Medical Data by Extraction Time. Diagnostics, 12.","DOI":"10.3390\/diagnostics12010102"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"57","DOI":"10.3390\/jpm14010057","article-title":"A Simple Bacteremia Score for Predicting Bacteremia in Patients with Suspected Infection in the Emergency Department: A Cohort Study","volume":"14","author":"Han","year":"2024","journal-title":"J. Pers. Med."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"17567","DOI":"10.1038\/s41598-026-48275-y","article-title":"Development and Validation of a Bacteremia Prediction Score for Adult Emergency Department Patients Using Hybrid Machine Learning and Regression","volume":"16","author":"Kim","year":"2026","journal-title":"Sci. Rep."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1164\/rccm.202406-1167OC","article-title":"Status of Sepsis Care in European Hospitals: Results from an International Cross-Sectional Survey","volume":"211","author":"Scheer","year":"2025","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"102124","DOI":"10.1016\/j.eclinm.2023.102124","article-title":"Predicting sepsis using deep learning across international sites: A retrospective development and validation study","volume":"62","author":"Moor","year":"2023","journal-title":"eClinicalMedicine"}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/13\/4904\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T04:01:19Z","timestamp":1782360079000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/13\/4904"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,24]]},"references-count":25,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["jcm15134904"],"URL":"https:\/\/doi.org\/10.3390\/jcm15134904","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,24]]}}}