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.

Murri, R., De Angelis, G., Antenucci, L., Fiori, B., Rinaldi, R., Fantoni, M., Damiani, A., Patarnello, S., Sanguinetti, M., Valentini, V., Posteraro, B., Masciocchi, C., A Machine Learning Predictive Model of Bloodstream Infection in Hospitalized Patients, <<DIAGNOSTICS>>, 2024; 14 (4): 445-445. [doi:10.3390/diagnostics14040445] [https://hdl.handle.net/10807/271276]

A Machine Learning Predictive Model of Bloodstream Infection in Hospitalized Patients

Murri, Rita;De Angelis, Giulia;Antenucci, Laura;Fiori, Barbara;Rinaldi, Riccardo;Fantoni, Massimo;Damiani, Andrea;Sanguinetti, Maurizio;Valentini, Vincenzo;Posteraro, Brunella;Masciocchi, Carlotta
2024

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.
2024
Inglese
Murri, R., De Angelis, G., Antenucci, L., Fiori, B., Rinaldi, R., Fantoni, M., Damiani, A., Patarnello, S., Sanguinetti, M., Valentini, V., Posteraro, B., Masciocchi, C., A Machine Learning Predictive Model of Bloodstream Infection in Hospitalized Patients, <<DIAGNOSTICS>>, 2024; 14 (4): 445-445. [doi:10.3390/diagnostics14040445] [https://hdl.handle.net/10807/271276]
File in questo prodotto:
File Dimensione Formato  
diagnostics-14-00445-v2.pdf

accesso aperto

Tipologia file ?: Versione Editoriale (PDF)
Licenza: Creative commons
Dimensione 2.1 MB
Formato Adobe PDF
2.1 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10807/271276
Citazioni
  • ???jsp.display-item.citation.pmc??? 0
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact