Journal Information
Share
Download PDF
More article options
Original article
Available online 4 April 2025
Prediction of COVID-19 mortality using machine learning strategies and a large-scale panel of plasma inflammatory proteins: A cohort study
Predicción de la mortalidad por COVID-19 utilizando estrategias de aprendizaje automático y un panel a gran escala de proteínas inflamatorias plasmáticas: un estudio de cohorte
Luiz Filipe Bastos Mendesa, Henrique Ritter Dal-Pizzola, Gabriele Prestesb, Carolina Saibro Girardia, Lucas Santosa, Daniel Pens Gelaina, Glauco A. Westphalc, Roger Walzd, Cristiane Ritterb,e, Felipe Dal-Pizzolb,e,
Corresponding author
piz@unesc.net

Corresponding author at: Laboratory of Experimental Pathophysiology, Graduate Program in Health Sciences, Health Sciences Unit, University of Southern Santa Catarina (UNESC), Criciúma, Santa Catarina, Brazil.
, Jose Claudio Fonseca Moreiraa
a Departamento de Bioquímica, Centro de Estudos em Estresse Oxidativo, Instituto de Ciências Básicas da Saúde, Universidade Federal do Rio Grande do Sul, Porto Alegre, RS, Brazil
b Laboratory of Experimental Pathophysiology, Graduate Program in Health Sciences, Health Sciences Unit, University of Southern Santa Catarina (UNESC), Criciúma, Santa Catarina, Brazil
c Centro Hospitalar Unimed, Joinville, SC, Brazil
d Center for Applied Neuroscience, University Hospital (HU), Federal University of Santa Catarina (UFSC), Florianópolis, SC, Brazil
e Intensive Care Unit, Hospital São José, Criciúma, SC, Brazil
Received 23 December 2024. Accepted 01 March 2025
Article information
Abstract
Full Text
Bibliography
Download PDF
Statistics
Figures (3)
Show moreShow less
Tables (1)
Table 1. Clinical characteristics of included patients.
Tables
Additional material (5)
Abstract
Objective

To apply machine learning algorithms to generate models capable of predicting mortality in COVID-19 patients, using a large platform of plasma inflammatory mediators.

Desing

Prospective, descriptive, cohort study.

Setting

6 intensive care units in 2 hospitals in Southern Brazil.

Patients

Patients aged > 18 years who were diagnosed with COVID-19 through reverse transcriptase reaction or rapid antigen test.

Interventions

None.

Main variables of interest

Demographic and clinical variables, 65 inflammatory biomarkers, mortality.

Results

Combinations of two or three proteins yield higher predictive value when compared to individual proteins or the full set of the 65 proteins. A proliferation-inducing ligand (APRIL) and cluster of differentiation 40 ligand (CD40L) consistently emerge among the highest-ranking combinations, suggesting a potential synergistic effect in predicting clinical outcomes. The network structure suggested a dysregulated immune response in non-survivors characterized by the failure of regulatory cytokines to temper an overwhelming inflammatory reaction.

Conclusion

Our results highlight the value of feature selection and careful consideration of biomarker combinations to improve prediction accuracy in COVID-19 patients.

Keywords:
COVID-19
Machine learning
Prognostication
Inflammation
Network
Immunity
Resumen
Objetivo

Aplicar algoritmos de aprendizaje automático para generar modelos capaces de predecir la mortalidad en pacientes con COVID-19, utilizando una amplia plataforma de mediadores inflamatorios plasmáticos.

Diseño

Estudio de cohorte prospectivo, descriptivo.

Ámbito

6 unidades de cuidados intensivos en 2 hospitales del sur de Brasil.

Pacientes

Pacientes mayores de 18 años diagnosticados con COVID-19 mediante reacción de transcriptasa inversa o prueba rápida de antígeno.

Intervenciones

Ninguna.

Variables de interés principales

Variables demográficas y clínicas, 65 biomarcadores inflamatorios, mortalidad.

Resultados

Las combinaciones de dos o tres proteínas muestran un mayor valor predictivo en comparación con proteínas individuales o el conjunto completo de las 65 proteínas. APRIL y CD40 L consistentemente aparecen entre las combinaciones de mayor rango, lo que sugiere un posible efecto sinérgico en la predicción de los resultados clínicos. La estructura de la red sugiere una respuesta inmunitaria desregulada en los no sobrevivientes, caracterizada por la incapacidad de las citocinas regulatorias para moderar una reacción inflamatoria abrumadora.

Conclusión

Nuestros resultados destacan la importancia de la selección de características y la cuidadosa consideración de combinaciones de biomarcadores para mejorar la precisión predictiva en pacientes con COVID-19.

Palabras clave:
COVID-19
Aprendizaje automático
Pronóstico
Inflamación
Red
Inmunidad

Article

These are the options to access the full texts of the publication Medicina Intensiva (English Edition)
Member
If you are a member of the Sociedad Española de Medicina Intensiva, Crítica y Unidades Coronarias::
Go to the members area of the website of the SEMICYUC (www.semicyuc.org )and click the link to the magazine.
Subscriber
Subscriber

If you already have your login data, please click here .

If you have forgotten your password you can you can recover it by clicking here and selecting the option “I have forgotten my password”
Subscribe
Subscribe to

Medicina Intensiva (English Edition)

Purchase
Purchase article

Purchasing article the PDF version will be downloaded

Purchase now
Contact
Phone for subscriptions and reporting of errors
From Monday to Friday from 9 a.m. to 6 p.m. (GMT + 1) except for the months of July and August which will be from 9 a.m. to 3 p.m.
Calls from Spain
932 415 960
Calls from outside Spain
+34 932 415 960
Email
Idiomas
Medicina Intensiva (English Edition)
Article options
Tools
Supplemental materials
es en

¿Es usted profesional sanitario apto para prescribir o dispensar medicamentos?

Are you a health professional able to prescribe or dispense drugs?