Integrating Inflammatory and Endothelial Biomarkers in Machine Learning Models to Predict Sepsis Development in Critically Ill Patients: A Combined Retrospective and Prospective Multicenter Study
Year: 2026
Type: article
Study design: Observational Study
Abstract: Sepsis is a severe, life-threatening condition in which timely recognition improves patient outcomes. Machine learning (ML) methods, usually relying on vital sign data, have shown promise in early sepsis prediction; however, they underrepresent sepsis biomarkers, which are widely used in clinical practice. We aimed to develop and validate interpretable ML models for early sepsis prediction using non-temporal data from the first 24 h of intensive care unit (ICU) admission, and to quantify the incremental value of inflammatory (Interleukin-6 (IL-6), procalcitonin (PCT), C-Reactive Protein (CRP)) and endothelial (soluble Endothelial Protein C Receptor (sEPCR)) biomarkers. A combined cohort of 1257 ICU patients from retrospective and prospective multicenter datasets was analyzed. We evaluated four tree-based models alongside Logistic Regression. We assessed discrimination (Area Under the Receiver Operating Characteristic Curve (AUC); Area Under the Precision-Recall Curve (AUPRC)), calibration, clinical utility (Decision Curve Analysis), and used structured feature ablation and Shapley additive explanations (SHAP) for interpretation. Light Gradient Boosting Machine (LGBM) achieved the best performance on the combined cohort, with an AUC of 0.86 and an AUPRC of 0.62. Moreover, LGBM achieved an AUC of 0.728 and an AUPRC of 0.288 during prospective multicenter validation from the retrospective to the prospective data. Feature ablation demonstrated that inclusion of IL-6, PCT, CRP, and sEPCR significantly improved model performance (AUC: p = 0.003; AUPRC: p = 0.001). SHAP analysis identified IL-6 and PCT as among the most influential predictors, both showing threshold-like nonlinear effects. These findings highlight the critical added value of biologically relevant biomarkers in ML-based clinical decision support.
Source: Pathogens
Authors: Ioannis Papapanagiotou(Data curation, Formal analysis, Investigation, Methodology, Software, Visualization, Writing – original draft), Alice G. Vassiliou(Conceptualization, Funding acquisition, Project administration, Resources, Supervision, Validation, Visualization, Writing – review & editing), Charikleia S. Vrettou(Data curation, Investigation, Methodology, Validation, Visualization, Writing – review & editing), Maria Theodorakopoulou(Investigation, Methodology, Validation, Visualization, Writing – review & editing), Zafeiria Mastora(Investigation, Methodology, Validation, Visualization, Writing – review & editing), Apostolos Karalis(Validation, Visualization, Writing – original draft), Vassiliki Giannopoulou(Data curation, Investigation, Methodology, Writing – original draft), Olga Kampouropoulou(Data curation, Investigation, Methodology, Writing – original draft), Ioannis Charcharos(Investigation, Methodology, Validation, Visualization, Writing – review & editing), Georgios Poupouzas(Data curation, Investigation, Methodology, Writing – original draft), Vasileios Issaris(Data curation, Investigation, Methodology, Writing – original draft), Konstantina Dede(Data curation, Investigation, Methodology, Writing – original draft), Helen Christopoulou(Data curation, Investigation, Methodology, Writing – original draft), Kyriakos Karkoulias(Data curation, Investigation, Methodology, Writing – original draft), Sylvia Raftopoulou(Data curation, Investigation, Methodology, Writing – original draft), Sophia Pouriki, Chrysi Keskinidou(Data curation, Investigation, Methodology, Writing – original draft), Nikolaos S. Lotsios(Data curation, Investigation, Methodology, Writing – original draft), Theofanis Ganitidis, Spyretta Golemati(Investigation, Methodology, Validation, Visualization, Writing – review & editing), Anastasia Kotanidou(Conceptualization, Funding acquisition, Project administration, Resources, Supervision, Validation, Visualization, Writing – review & editing), Stavros Papapanagiotou, Ioanna Dimopoulou(Conceptualization, Funding acquisition, Project administration, Resources, Supervision, Validation, Visualization, Writing – review & editing)
Language: English
Field: Medicine
Domain: Health Sciences
Keywords: sepsis prediction, early sepsis detection, inflammatory markers, endothelial markers, interleukin-6, procalcitonin, C-reactive protein, soluble endothelial protein C receptor, critically ill patients, intensive care unit, tree-based models, LightGBM, SHAP, clinical decision support, model validation
Open Access status: gold
Estimated APC paid: $2,654
OpenAlex ID: W7162799091
