Autor(es):
Von Rekowski, Cristiana ; AH Fonseca, Tiago ; Araújo, Rúben ; Martins, Ana ; Pinto, Iola ; Oliveira, M. Conceição ; Justino, Gonçalo C. ; Bento, Luís ; Calado, Cecília
Data: 2025
Identificador Persistente: http://hdl.handle.net/10362/183518
Origem: Repositório Institucional da UNL
Assunto(s): cytokine profiling; inflammatory biomarkers; intensive care unit; invasive mechanical ventilation; machine learning; mortality; prompt analyses; Materials Science(all); Instrumentation; Engineering(all); Process Chemistry and Technology; Computer Science Applications; Fluid Flow and Transfer Processes
Descrição
Funding Information: This research was supported by Funda\u00E7\u00E3o para a Ci\u00EAncia e a Tecnologia (FCT), grant numbers DSAIPA/DS/0117/2020 and RNEM-LISBOA-01-0145-FEDER-022125 (Portuguese Mass Spectrometry Network). Centro de Qu\u00EDmica Estrutural is a Research Unit funded by FCT through projects UIDB/00100/2020 and UIDP/00100/2020. Institute of Molecular Sciences is an Associate Laboratory funded by FCT through project LA/P/0056/2020. Cristiana P. Von Rekowski, Tiago A.H. Fonseca, and R\u00FAben Ara\u00FAjo acknowledge the FCT PhD grants 2023.01951.BD, 2024.02043.BD, and 2021.05553.BD, respectively. Publisher Copyright: © 2025 by the authors.
Predicting disease states and outcomes—and anticipating the need for specific procedures—enhances the efficiency of patient management, particularly in the dynamic and heterogenous environments of intensive care units (ICUs). This study aimed to develop robust predictive models using small sets of blood analytes to predict disease severity and mortality in ICUs, as fewer analytes are advantageous for future rapid analyses using biosensors, enabling fast clinical decision-making. Given the substantial impact of inflammatory processes, this research examined the serum profiles of 25 cytokines, either in association with or independent of nine routine blood analyses. Serum samples from 24 male COVID-19 patients admitted to an ICU were divided into three groups: Group A, including less severe patients, and Groups B and C, that needed invasive mechanical ventilation (IMV). Patients from Group C died within seven days after the current analysis. Naïve Bayes models were developed using the full dataset or with feature subsets selected either through an information gain algorithm or univariate data analysis. Strong predictive models were achieved for IMV (AUC = 0.891) and mortality within homogeneous (AUC = 0.774) or more heterogeneous (AUC = 0.887) populations utilizing two to nine features. Despite the small sample, these findings underscore the potential for effective prediction models based on a limited number of analytes.
