Predicting clinical outcomes at hospital admission of patients with COVID-19 pneumonia using artificial intelligence: a secondary analysis of a randomized clinical trial

BackgroundPredicting clinical improvement after hospital admission in patients with COVID-19 is crucial for effective resource allocation. Machine-learning tools can help identify patients likely to show clinical improvement based on real-world data. This study used two approaches—least absolute shr...

Full description

Saved in:
Bibliographic Details
Main Authors: Caio César Souza Conceição, Camila Marinelli Martins, Mayck Medeiros Silva, Hugo Caire de Castro Faria Neto, Davide Chiumello, Patricia Rieken Macedo Rocco, Fernanda Ferreira Cruz, Pedro Leme Silva
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-05-01
Series:Frontiers in Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmed.2025.1561980/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849316128676904960
author Caio César Souza Conceição
Camila Marinelli Martins
Mayck Medeiros Silva
Hugo Caire de Castro Faria Neto
Davide Chiumello
Davide Chiumello
Davide Chiumello
Patricia Rieken Macedo Rocco
Fernanda Ferreira Cruz
Pedro Leme Silva
author_facet Caio César Souza Conceição
Camila Marinelli Martins
Mayck Medeiros Silva
Hugo Caire de Castro Faria Neto
Davide Chiumello
Davide Chiumello
Davide Chiumello
Patricia Rieken Macedo Rocco
Fernanda Ferreira Cruz
Pedro Leme Silva
author_sort Caio César Souza Conceição
collection DOAJ
description BackgroundPredicting clinical improvement after hospital admission in patients with COVID-19 is crucial for effective resource allocation. Machine-learning tools can help identify patients likely to show clinical improvement based on real-world data. This study used two approaches—least absolute shrinkage and selection operator (LASSO) and CombiROC—to identify predictive variables at hospital admission for detecting clinical improvement after 7 days.MethodsA secondary analysis was conducted on the modified intention-to-treat placebo group from a previous randomized clinical trial (RCT, NCT04561219) of patients with COVID-19. The analysis assessed clinical, laboratory, and blood markers at admission to predict clinical improvement, defined as a two-point increase on the World Health Organization clinical progression scale after 7 days. LASSO and CombiROC were used to select optimal predictive variables. The Youden criteria identified the best threshold for different variable combinations, which were then compared based on the highest area under the curve (AUC) and accuracy. AUCs were compared using DeLong’s algorithm.ResultsOverall, 203 patients were included in the analysis, and they were divided into two groups; clinical improvement (n = 154) and no clinical improvement (n = 49). The median age was 55 years (interquartile range, 46–66 years); 65% were male. LASSO identified three predictive variables (SaO2, hematocrit, and interleukin [IL]-13) with high sensitivity of 98% (95% confidence interval [CI], 92–100%) but low specificity of 26% (95% CI, 10–48%) for clinical improvement. CombiROC selected a broader set of variables (T cell–attracting chemokine, hemoglobin, hepatocyte growth factor, hematocrit, IL-3, PDGF-BB, RANTES, and SaO2), achieving balanced sensitivity of 82% (95% CI, 69–91%) and specificity of 74% (95% CI, 49–91%). LASSO and CombiROC showed comparable accuracy (82 and 80%, respectively) and similar area under the ROC curves (LASSO: AUC, 0.704; 95% CI, 0.571–0.837; CombiROC: AUC, 0.823; 95% CI, 0.708–0.937; p = 0.185).ConclusionFor patients hospitalized with COVID-19 pneumonia, predictive variables identified by LASSO and CombiROC analyses demonstrated similar accuracy and AUCs in predicting clinical improvement. LASSO, with fewer variables (SaO2, hematocrit, and IL-13) showed high sensitivity but low specificity, whereas CombiROC’s broader selection of variables provided balanced sensitivity and specificity for predicting clinical improvement.Clinical trial registrationBrazilian Registry of Clinical Trials (REBEC) number RBR-88bs9x and ClinicalTrials.gov number NCT04561219.
format Article
id doaj-art-2fb0fcd8faea421791f6b95a16642d09
institution Kabale University
issn 2296-858X
language English
publishDate 2025-05-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Medicine
spelling doaj-art-2fb0fcd8faea421791f6b95a16642d092025-08-20T03:51:58ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-05-011210.3389/fmed.2025.15619801561980Predicting clinical outcomes at hospital admission of patients with COVID-19 pneumonia using artificial intelligence: a secondary analysis of a randomized clinical trialCaio César Souza Conceição0Camila Marinelli Martins1Mayck Medeiros Silva2Hugo Caire de Castro Faria Neto3Davide Chiumello4Davide Chiumello5Davide Chiumello6Patricia Rieken Macedo Rocco7Fernanda Ferreira Cruz8Pedro Leme Silva9Laboratory of Pulmonary Investigation, Institute of Biophysics Carlos Chagas Filho, Federal University of Rio de Janeiro, Rio de Janeiro, BrazilAAC&T Research Consulting LTDA, Curitiba, BrazilLaboratory of Pulmonary Investigation, Institute of Biophysics Carlos Chagas Filho, Federal University of Rio de Janeiro, Rio de Janeiro, BrazilLaboratory of Immunopharmacology, Oswaldo Cruz Institute (Fiocruz), Rio de Janeiro, BrazilDepartment of Health Sciences, University of Milan, Milan, ItalyAnaesthesia and Intensive Care, San Paolo University Hospital, Milan, ItalyCoordinated Research Center on Respiratory Failure, University of Milan, Milan, ItalyLaboratory of Pulmonary Investigation, Institute of Biophysics Carlos Chagas Filho, Federal University of Rio de Janeiro, Rio de Janeiro, BrazilLaboratory of Pulmonary Investigation, Institute of Biophysics Carlos Chagas Filho, Federal University of Rio de Janeiro, Rio de Janeiro, BrazilLaboratory of Pulmonary Investigation, Institute of Biophysics Carlos Chagas Filho, Federal University of Rio de Janeiro, Rio de Janeiro, BrazilBackgroundPredicting clinical improvement after hospital admission in patients with COVID-19 is crucial for effective resource allocation. Machine-learning tools can help identify patients likely to show clinical improvement based on real-world data. This study used two approaches—least absolute shrinkage and selection operator (LASSO) and CombiROC—to identify predictive variables at hospital admission for detecting clinical improvement after 7 days.MethodsA secondary analysis was conducted on the modified intention-to-treat placebo group from a previous randomized clinical trial (RCT, NCT04561219) of patients with COVID-19. The analysis assessed clinical, laboratory, and blood markers at admission to predict clinical improvement, defined as a two-point increase on the World Health Organization clinical progression scale after 7 days. LASSO and CombiROC were used to select optimal predictive variables. The Youden criteria identified the best threshold for different variable combinations, which were then compared based on the highest area under the curve (AUC) and accuracy. AUCs were compared using DeLong’s algorithm.ResultsOverall, 203 patients were included in the analysis, and they were divided into two groups; clinical improvement (n = 154) and no clinical improvement (n = 49). The median age was 55 years (interquartile range, 46–66 years); 65% were male. LASSO identified three predictive variables (SaO2, hematocrit, and interleukin [IL]-13) with high sensitivity of 98% (95% confidence interval [CI], 92–100%) but low specificity of 26% (95% CI, 10–48%) for clinical improvement. CombiROC selected a broader set of variables (T cell–attracting chemokine, hemoglobin, hepatocyte growth factor, hematocrit, IL-3, PDGF-BB, RANTES, and SaO2), achieving balanced sensitivity of 82% (95% CI, 69–91%) and specificity of 74% (95% CI, 49–91%). LASSO and CombiROC showed comparable accuracy (82 and 80%, respectively) and similar area under the ROC curves (LASSO: AUC, 0.704; 95% CI, 0.571–0.837; CombiROC: AUC, 0.823; 95% CI, 0.708–0.937; p = 0.185).ConclusionFor patients hospitalized with COVID-19 pneumonia, predictive variables identified by LASSO and CombiROC analyses demonstrated similar accuracy and AUCs in predicting clinical improvement. LASSO, with fewer variables (SaO2, hematocrit, and IL-13) showed high sensitivity but low specificity, whereas CombiROC’s broader selection of variables provided balanced sensitivity and specificity for predicting clinical improvement.Clinical trial registrationBrazilian Registry of Clinical Trials (REBEC) number RBR-88bs9x and ClinicalTrials.gov number NCT04561219.https://www.frontiersin.org/articles/10.3389/fmed.2025.1561980/fullCOVID-19biomarkersmachine learningLASSOCombiROCclinical improvement
spellingShingle Caio César Souza Conceição
Camila Marinelli Martins
Mayck Medeiros Silva
Hugo Caire de Castro Faria Neto
Davide Chiumello
Davide Chiumello
Davide Chiumello
Patricia Rieken Macedo Rocco
Fernanda Ferreira Cruz
Pedro Leme Silva
Predicting clinical outcomes at hospital admission of patients with COVID-19 pneumonia using artificial intelligence: a secondary analysis of a randomized clinical trial
Frontiers in Medicine
COVID-19
biomarkers
machine learning
LASSO
CombiROC
clinical improvement
title Predicting clinical outcomes at hospital admission of patients with COVID-19 pneumonia using artificial intelligence: a secondary analysis of a randomized clinical trial
title_full Predicting clinical outcomes at hospital admission of patients with COVID-19 pneumonia using artificial intelligence: a secondary analysis of a randomized clinical trial
title_fullStr Predicting clinical outcomes at hospital admission of patients with COVID-19 pneumonia using artificial intelligence: a secondary analysis of a randomized clinical trial
title_full_unstemmed Predicting clinical outcomes at hospital admission of patients with COVID-19 pneumonia using artificial intelligence: a secondary analysis of a randomized clinical trial
title_short Predicting clinical outcomes at hospital admission of patients with COVID-19 pneumonia using artificial intelligence: a secondary analysis of a randomized clinical trial
title_sort predicting clinical outcomes at hospital admission of patients with covid 19 pneumonia using artificial intelligence a secondary analysis of a randomized clinical trial
topic COVID-19
biomarkers
machine learning
LASSO
CombiROC
clinical improvement
url https://www.frontiersin.org/articles/10.3389/fmed.2025.1561980/full
work_keys_str_mv AT caiocesarsouzaconceicao predictingclinicaloutcomesathospitaladmissionofpatientswithcovid19pneumoniausingartificialintelligenceasecondaryanalysisofarandomizedclinicaltrial
AT camilamarinellimartins predictingclinicaloutcomesathospitaladmissionofpatientswithcovid19pneumoniausingartificialintelligenceasecondaryanalysisofarandomizedclinicaltrial
AT mayckmedeirossilva predictingclinicaloutcomesathospitaladmissionofpatientswithcovid19pneumoniausingartificialintelligenceasecondaryanalysisofarandomizedclinicaltrial
AT hugocairedecastrofarianeto predictingclinicaloutcomesathospitaladmissionofpatientswithcovid19pneumoniausingartificialintelligenceasecondaryanalysisofarandomizedclinicaltrial
AT davidechiumello predictingclinicaloutcomesathospitaladmissionofpatientswithcovid19pneumoniausingartificialintelligenceasecondaryanalysisofarandomizedclinicaltrial
AT davidechiumello predictingclinicaloutcomesathospitaladmissionofpatientswithcovid19pneumoniausingartificialintelligenceasecondaryanalysisofarandomizedclinicaltrial
AT davidechiumello predictingclinicaloutcomesathospitaladmissionofpatientswithcovid19pneumoniausingartificialintelligenceasecondaryanalysisofarandomizedclinicaltrial
AT patriciariekenmacedorocco predictingclinicaloutcomesathospitaladmissionofpatientswithcovid19pneumoniausingartificialintelligenceasecondaryanalysisofarandomizedclinicaltrial
AT fernandaferreiracruz predictingclinicaloutcomesathospitaladmissionofpatientswithcovid19pneumoniausingartificialintelligenceasecondaryanalysisofarandomizedclinicaltrial
AT pedrolemesilva predictingclinicaloutcomesathospitaladmissionofpatientswithcovid19pneumoniausingartificialintelligenceasecondaryanalysisofarandomizedclinicaltrial