Predicting central line-associated bloodstream infections and mortality using supervised machine learning

Joshua P. Parreco, Antonio E. Hidalgo, Alejandro D. Badilla, Omar Ilyas, Rishi Rattan

Research output: Contribution to journalArticlepeer-review

28 Scopus citations


Purpose: The purpose of this study was to compare machine learning techniques for predicting central line-associated bloodstream infection (CLABSI). Materials and methods: The Multiparameter Intelligent Monitoring in Intensive Care III database was queried for all ICU admissions. The variables included six different severities of illness scores calculated on the first day of ICU admission with their components and comorbidities. The outcomes of interest were in-hospital mortality, central line placement, and CLABSI. Predictive models were created for these outcomes using classifiers with different algorithms: logistic regression, gradient boosted trees, and deep learning. Results: There were 57,786 total hospital admissions and the mortality rate was 10.1%. There were 38.4% patients with a central line and the rate of CLABSI was 1.5%. The classifiers using deep learning performed with the highest AUC for mortality, 0.885 ± 0.010 (p < 0.01) and central line placement, 0.816 ± 0.006 (p < 0.01). The classifier using logistic regression for predicting CLABSI performed with an AUC of 0.722 ± 0.048 (p < 0.01). Conclusions: This study demonstrates models for identifying patients who will develop CLABSI. Early identification of these patients has implications for quality, cost, and outcome improvements.

Original languageEnglish (US)
Pages (from-to)156-162
Number of pages7
JournalJournal of Critical Care
StatePublished - Jun 2018


  • Artificial intelligence
  • Central line-associated bloodstream infection
  • Hospital-acquired infections
  • Machine learning
  • Quality improvement
  • Severity of illness score

ASJC Scopus subject areas

  • Critical Care and Intensive Care Medicine


Dive into the research topics of 'Predicting central line-associated bloodstream infections and mortality using supervised machine learning'. Together they form a unique fingerprint.

Cite this