Author(s): Araújo, Rúben ; Ramalhete, Luís ; Von Rekowski, Cristiana ; Fonseca, Tiago AH ; Calado, Cecília ; Bento, Luís
Date: 2025
Persistent ID: http://hdl.handle.net/10362/182080
Origin: Repositório Institucional da UNL
Subject(s): bloodstream infections; COVID-19; cytokine profiling; Gram typing; ICU diagnostics; machine learning; Endocrinology, Diabetes and Metabolism; Biochemistry; Molecular Biology; SDG 3 - Good Health and Well-being
Funding Information: This research was funded by project grant DSAIPA/DS/0117/2020, supported by Funda\u00E7\u00E3o para a Ci\u00EAncia e a Tecnologia, Portugal, and IPL/IDI&CA2024/R-DICIP_ISEL by Instituto Polit\u00E9cnico de Lisboa, Portugal. The present work was conducted in Instituto Polit\u00E9cnico de Lisboa and in the Engineering & Health Laboratory, resulting from a collaboration protocol established between Universidade Cat\u00F3lica Portuguesa and Instituto Polit\u00E9cnico de Lisboa. Additionally, R. Ara\u00FAjo, T. Fonseca, and C. Rekowski acknowledge their PhD grants from FCT (references: 2021.05553.BD, 2024.02043.BD, and 2023.01951.BD, respectively). Publisher Copyright: © 2025 by the authors.
Background: Timely and accurate identification of bloodstream infections (BSIs) in intensive care unit (ICU) patients remains a key challenge, particularly in COVID-19 settings, where immune dysregulation can obscure early clinical signs. Methods: Cytokine profiling was evaluated to discriminate between ICU patients with and without BSIs, and, among those with confirmed BSIs, to further stratify bacterial infections by Gram type. Serum samples from 45 ICU COVID-19 patients were analyzed using a 21-cytokine panel, with feature selection applied to identify candidate markers. Results: A machine learning workflow identified key features, achieving robust performance metrics with AUC values up to 0.97 for BSI classification and 0.98 for Gram typing. Conclusions: In contrast to traditional approaches that focus on individual cytokines or simple ratios, the present analysis employed programmatically generated ratios between pro-inflammatory and anti-inflammatory cytokines, refined through feature selection. Although further validation in larger and more diverse cohorts is warranted, these findings underscore the potential of advanced cytokine-based diagnostics to enhance precision medicine in infection management.
