A Machine Learning Predictive Model of Bloodstream Infection in Hospitalized Patients
Authors:
- Rita MurriRita Murri
- Giulia De AngelisGAGiulia De Angelis
- Laura AntenucciLALaura Antenucci
- Barbara FioriBFBarbara Fiori
- Riccardo RinaldiRRRiccardo Rinaldi
- Massimo FantoniMassimo Fantoni
- Andrea DamianiADAndrea Damiani
- Stefano PatarnelloSPStefano Patarnello
- Maurizio SanguinettiMaurizio Sanguinetti
- Vincenzo ValentiniVVVincenzo Valentini
- Brunella PosteraroBrunella Posteraro
- Carlotta MasciocchiCMCarlotta Masciocchi
Open Access
- 17 February 2024
- journal article
- research article
- Published by MDPI AG in Diagnostics
- Vol. 14 (4) , 445
Abstract
The aim of the study was to build a machine learning-based predictive model to discriminate between hospitalized patients at low risk and high risk of bloodstream infection (BSI). A Data Mart including all patients hospitalized between January 2016 and December 2019 with suspected BSI was built. Multivariate logistic regression was applied to develop a clinically interpretable machine learning predictive model. The model was trained on 2016–2018 data and tested on 2019 data. A feature selection based on a univariate logistic regression first selected candidate predictors of BSI. A multivariate logistic regression with stepwise feature selection in five-fold cross-validation was applied to express the risk of BSI. A total of 5660 hospitalizations (4026 and 1634 in the training and the validation subsets, respectively) were included. Eleven predictors of BSI were identified. The performance of the model in terms of AUROC was 0.74. Based on the interquartile predicted risk score, 508 (31.1%) patients were defined as being at low risk, 776 (47.5%) at medium risk, and 350 (21.4%) at high risk of BSI. Of them, 14.2% (72/508), 30.8% (239/776), and 64% (224/350) had a BSI, respectively. The performance of the predictive model of BSI is promising. Computational infrastructure and machine learning models can help clinicians identify people at low risk for BSI, ultimately supporting an antibiotic stewardship approach.Keywords
This publication has 35 references indexed in Scilit:
- When not to start antibiotics: avoiding antibiotic overuse in the intensive care unitClinical Microbiology and Infection, 2020
- Emergency department triage prediction of clinical outcomes using machine learning modelsCritical Care, 2019
- Pathologic Difference between Sepsis and Bloodstream InfectionsThe Journal of Applied Laboratory Medicine, 2019
- Machine learning for fast identification of bacteraemia in SIRS patients treated on standard care wards: a cohort studyScientific Reports, 2018
- The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3)JAMA, 2016
- Understanding the mechanisms and drivers of antimicrobial resistanceThe Lancet, 2016
- Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD)Annals of Internal Medicine, 2015
- Does This Adult Patient With Suspected Bacteremia Require Blood Cultures?JAMA, 2012
- Logistic Regression: A Brief PrimerAcademic Emergency Medicine, 2011
- Who Needs a Blood Culture? A Prospectively Derived and Validated Prediction RuleThe Journal of Emergency Medicine, 2008