Next Article in Journal
Characterization of blaKPC-2 and blaNDM-1 Plasmids of a K. pneumoniae ST11 Outbreak Clone
Next Article in Special Issue
Reduced Prognostic Role of Serum PCT Measurement in Very Frail Older Adults Admitted to the Emergency Department
Previous Article in Journal
Cytotoxicity and Antibiofilm Activity of Silver-Polypropylene Nanocomposites
Previous Article in Special Issue
Correction: Jensen et al. Prior Antibiotic Use Increases Risk of Urinary Tract Infections Caused by Resistant Escherichia coli among Elderly in Primary Care: A Case-Control Study. Antibiotics 2022, 11, 1382
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Antibiotics
Volume 12
Issue 5
10.3390/antibiotics12050925
antibiotics-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

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

by
Antonio Mirijello
1,*,†,
Andrea Fontana
2,†,
Antonio Pio Greco
1,
Alberto Tosoni
3,
Angelo D’Agruma
1,
Maria Labonia
4,
Massimiliano Copetti
2,
Pamela Piscitelli
1,‡,
Salvatore De Cosmo
1,‡ and
on behalf of the Internal Medicine Sepsis Study Group
§
1
Department of Medical Sciences, Fondazione IRCCS Casa Sollievo della Sofferenza, 71013 San Giovanni Rotondo, Italy
2
Unit of Biostatistics, Fondazione IRCCS Casa Sollievo della Sofferenza, 71013 San Giovanni Rotondo, Italy
3
Department of Internal Medicine and Gastroenterology, Fondazione Policlinico Universitario “A. Gemelli” IRCCS, 00168 Rome, Italy
4
Unit of Microbiology, Fondazione IRCCS Casa Sollievo della Sofferenza, 71013 San Giovanni Rotondo, Italy
*
Author to whom correspondence should be addressed.
†
These authors contributed equally to this work.
‡
These authors also contributed equally to this work.
§
The Internal Medicine Sepsis Study Group: Mariagiovanna Antonaccio, Stefano Carughi, Michele Corritore, Serafino Curci, Maria Maddalena D’Errico, Angela de Matthaeis, Gabriella Pacilli (IRCCS Casa Sollievo della Sofferenza, San Giovanni Rotondo), Cristina d’Angelo (Padre Pio Rehabilitation Centers Foundation, ONLUS, San Giovanni Rotondo).
Antibiotics 2023, 12(5), 925; https://doi.org/10.3390/antibiotics12050925
Submission received: 16 April 2023 / Revised: 15 May 2023 / Accepted: 16 May 2023 / Published: 18 May 2023
(This article belongs to the Special Issue Antibiotic Resistance and Antimicrobial Use in Elderly Patients)
Browse Figures
Review Reports Versions Notes

Abstract

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.
Keywords: sepsis; machine learning; prognostication; internal medicine; SOFA sepsis; machine learning; prognostication; internal medicine; SOFA

Share and Cite

MDPI and ACS Style

Mirijello, A.; Fontana, A.; Greco, A.P.; Tosoni, A.; D’Agruma, A.; Labonia, M.; Copetti, M.; Piscitelli, P.; De Cosmo, S.; on behalf of the Internal Medicine Sepsis Study Group. 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. Antibiotics 2023, 12, 925. https://doi.org/10.3390/antibiotics12050925

AMA Style

Mirijello A, Fontana A, Greco AP, Tosoni A, D’Agruma A, Labonia M, Copetti M, Piscitelli P, De Cosmo S, on behalf of the Internal Medicine Sepsis Study Group. 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. Antibiotics. 2023; 12(5):925. https://doi.org/10.3390/antibiotics12050925

Chicago/Turabian Style

Mirijello, Antonio, Andrea Fontana, Antonio Pio Greco, Alberto Tosoni, Angelo D’Agruma, Maria Labonia, Massimiliano Copetti, Pamela Piscitelli, Salvatore De Cosmo, and on behalf of the Internal Medicine Sepsis Study Group. 2023. "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" Antibiotics 12, no. 5: 925. https://doi.org/10.3390/antibiotics12050925

APA Style

Mirijello, A., Fontana, A., Greco, A. P., Tosoni, A., D’Agruma, A., Labonia, M., Copetti, M., Piscitelli, P., De Cosmo, S., & on behalf of the Internal Medicine Sepsis Study Group. (2023). 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. Antibiotics, 12(5), 925. https://doi.org/10.3390/antibiotics12050925

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop