Cargando…

Identifying Predictors Associated with Risk of Death or Admission to Intensive Care Unit in Internal Medicine Patients with Sepsis: A Comparison of Statistical Models and Machine Learning Algorithms

Background: Sepsis is a time-dependent disease: the early recognition of patients at risk for poor outcome is mandatory. Aim: To identify prognostic predictors of the risk of death or admission to intensive care units in a consecutive sample of septic patients, comparing different statistical models...

Descripción completa

Detalles Bibliográficos
Autores principales: Mirijello, Antonio, Fontana, Andrea, Greco, Antonio Pio, Tosoni, Alberto, D’Agruma, Angelo, Labonia, Maria, Copetti, Massimiliano, Piscitelli, Pamela, De Cosmo, Salvatore
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10215570/
https://www.ncbi.nlm.nih.gov/pubmed/37237828
http://dx.doi.org/10.3390/antibiotics12050925
_version_ 1785048094819221504
author Mirijello, Antonio
Fontana, Andrea
Greco, Antonio Pio
Tosoni, Alberto
D’Agruma, Angelo
Labonia, Maria
Copetti, Massimiliano
Piscitelli, Pamela
De Cosmo, Salvatore
author_facet Mirijello, Antonio
Fontana, Andrea
Greco, Antonio Pio
Tosoni, Alberto
D’Agruma, Angelo
Labonia, Maria
Copetti, Massimiliano
Piscitelli, Pamela
De Cosmo, Salvatore
author_sort Mirijello, Antonio
collection PubMed
description Background: Sepsis is a time-dependent disease: the early recognition of patients at risk for poor outcome is mandatory. Aim: To identify prognostic predictors of the risk of death or admission to intensive care units in a consecutive sample of septic patients, comparing different statistical models and machine learning algorithms. Methods: Retrospective study including 148 patients discharged from an Italian internal medicine unit with a diagnosis of sepsis/septic shock and microbiological identification. Results: Of the total, 37 (25.0%) patients reached the composite outcome. The sequential organ failure assessment (SOFA) score at admission (odds ratio (OR): 1.83; 95% confidence interval (CI): 1.41–2.39; p < 0.001), delta SOFA (OR: 1.64; 95% CI: 1.28–2.10; p < 0.001), and the alert, verbal, pain, unresponsive (AVPU) status (OR: 5.96; 95% CI: 2.13–16.67; p < 0.001) were identified through the multivariable logistic model as independent predictors of the composite outcome. The area under the receiver operating characteristic curve (AUC) was 0.894; 95% CI: 0.840–0.948. In addition, different statistical models and machine learning algorithms identified further predictive variables: delta quick-SOFA, delta-procalcitonin, mortality in emergency department sepsis, mean arterial pressure, and the Glasgow Coma Scale. The cross-validated multivariable logistic model with the least absolute shrinkage and selection operator (LASSO) penalty identified 5 predictors; and recursive partitioning and regression tree (RPART) identified 4 predictors with higher AUC (0.915 and 0.917, respectively); the random forest (RF) approach, including all evaluated variables, obtained the highest AUC (0.978). All models’ results were well calibrated. Conclusions: Although structurally different, each model identified similar predictive covariates. The classical multivariable logistic regression model was the most parsimonious and calibrated one, while RPART was the easiest to interpret clinically. Finally, LASSO and RF were the costliest in terms of number of variables identified.
format Online
Article
Text
id pubmed-10215570
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-102155702023-05-27 Identifying Predictors Associated with Risk of Death or Admission to Intensive Care Unit in Internal Medicine Patients with Sepsis: A Comparison of Statistical Models and Machine Learning Algorithms Mirijello, Antonio Fontana, Andrea Greco, Antonio Pio Tosoni, Alberto D’Agruma, Angelo Labonia, Maria Copetti, Massimiliano Piscitelli, Pamela De Cosmo, Salvatore Antibiotics (Basel) Article Background: Sepsis is a time-dependent disease: the early recognition of patients at risk for poor outcome is mandatory. Aim: To identify prognostic predictors of the risk of death or admission to intensive care units in a consecutive sample of septic patients, comparing different statistical models and machine learning algorithms. Methods: Retrospective study including 148 patients discharged from an Italian internal medicine unit with a diagnosis of sepsis/septic shock and microbiological identification. Results: Of the total, 37 (25.0%) patients reached the composite outcome. The sequential organ failure assessment (SOFA) score at admission (odds ratio (OR): 1.83; 95% confidence interval (CI): 1.41–2.39; p < 0.001), delta SOFA (OR: 1.64; 95% CI: 1.28–2.10; p < 0.001), and the alert, verbal, pain, unresponsive (AVPU) status (OR: 5.96; 95% CI: 2.13–16.67; p < 0.001) were identified through the multivariable logistic model as independent predictors of the composite outcome. The area under the receiver operating characteristic curve (AUC) was 0.894; 95% CI: 0.840–0.948. In addition, different statistical models and machine learning algorithms identified further predictive variables: delta quick-SOFA, delta-procalcitonin, mortality in emergency department sepsis, mean arterial pressure, and the Glasgow Coma Scale. The cross-validated multivariable logistic model with the least absolute shrinkage and selection operator (LASSO) penalty identified 5 predictors; and recursive partitioning and regression tree (RPART) identified 4 predictors with higher AUC (0.915 and 0.917, respectively); the random forest (RF) approach, including all evaluated variables, obtained the highest AUC (0.978). All models’ results were well calibrated. Conclusions: Although structurally different, each model identified similar predictive covariates. The classical multivariable logistic regression model was the most parsimonious and calibrated one, while RPART was the easiest to interpret clinically. Finally, LASSO and RF were the costliest in terms of number of variables identified. MDPI 2023-05-18 /pmc/articles/PMC10215570/ /pubmed/37237828 http://dx.doi.org/10.3390/antibiotics12050925 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Mirijello, Antonio
Fontana, Andrea
Greco, Antonio Pio
Tosoni, Alberto
D’Agruma, Angelo
Labonia, Maria
Copetti, Massimiliano
Piscitelli, Pamela
De Cosmo, Salvatore
Identifying Predictors Associated with Risk of Death or Admission to Intensive Care Unit in Internal Medicine Patients with Sepsis: A Comparison of Statistical Models and Machine Learning Algorithms
title Identifying Predictors Associated with Risk of Death or Admission to Intensive Care Unit in Internal Medicine Patients with Sepsis: A Comparison of Statistical Models and Machine Learning Algorithms
title_full Identifying Predictors Associated with Risk of Death or Admission to Intensive Care Unit in Internal Medicine Patients with Sepsis: A Comparison of Statistical Models and Machine Learning Algorithms
title_fullStr Identifying Predictors Associated with Risk of Death or Admission to Intensive Care Unit in Internal Medicine Patients with Sepsis: A Comparison of Statistical Models and Machine Learning Algorithms
title_full_unstemmed Identifying Predictors Associated with Risk of Death or Admission to Intensive Care Unit in Internal Medicine Patients with Sepsis: A Comparison of Statistical Models and Machine Learning Algorithms
title_short Identifying Predictors Associated with Risk of Death or Admission to Intensive Care Unit in Internal Medicine Patients with Sepsis: A Comparison of Statistical Models and Machine Learning Algorithms
title_sort identifying predictors associated with risk of death or admission to intensive care unit in internal medicine patients with sepsis: a comparison of statistical models and machine learning algorithms
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10215570/
https://www.ncbi.nlm.nih.gov/pubmed/37237828
http://dx.doi.org/10.3390/antibiotics12050925
work_keys_str_mv AT mirijelloantonio identifyingpredictorsassociatedwithriskofdeathoradmissiontointensivecareunitininternalmedicinepatientswithsepsisacomparisonofstatisticalmodelsandmachinelearningalgorithms
AT fontanaandrea identifyingpredictorsassociatedwithriskofdeathoradmissiontointensivecareunitininternalmedicinepatientswithsepsisacomparisonofstatisticalmodelsandmachinelearningalgorithms
AT grecoantoniopio identifyingpredictorsassociatedwithriskofdeathoradmissiontointensivecareunitininternalmedicinepatientswithsepsisacomparisonofstatisticalmodelsandmachinelearningalgorithms
AT tosonialberto identifyingpredictorsassociatedwithriskofdeathoradmissiontointensivecareunitininternalmedicinepatientswithsepsisacomparisonofstatisticalmodelsandmachinelearningalgorithms
AT dagrumaangelo identifyingpredictorsassociatedwithriskofdeathoradmissiontointensivecareunitininternalmedicinepatientswithsepsisacomparisonofstatisticalmodelsandmachinelearningalgorithms
AT laboniamaria identifyingpredictorsassociatedwithriskofdeathoradmissiontointensivecareunitininternalmedicinepatientswithsepsisacomparisonofstatisticalmodelsandmachinelearningalgorithms
AT copettimassimiliano identifyingpredictorsassociatedwithriskofdeathoradmissiontointensivecareunitininternalmedicinepatientswithsepsisacomparisonofstatisticalmodelsandmachinelearningalgorithms
AT piscitellipamela identifyingpredictorsassociatedwithriskofdeathoradmissiontointensivecareunitininternalmedicinepatientswithsepsisacomparisonofstatisticalmodelsandmachinelearningalgorithms
AT decosmosalvatore identifyingpredictorsassociatedwithriskofdeathoradmissiontointensivecareunitininternalmedicinepatientswithsepsisacomparisonofstatisticalmodelsandmachinelearningalgorithms
AT identifyingpredictorsassociatedwithriskofdeathoradmissiontointensivecareunitininternalmedicinepatientswithsepsisacomparisonofstatisticalmodelsandmachinelearningalgorithms