Random forest differentiation of Escherichia coli in elderly sepsis using biomarkers and infectious sites

Abstract

Abstract This study addresses the challenge of accurately diagnosing sepsis subtypes in elderly patients, particularly distinguishing between Escherichia coli (E. coli) and non-E. coli infections. Utilizing machine learning, we conducted a retrospective analysis of 119 elderly sepsis patients, employing a random forest model to evaluate clinical biomarkers and infection sites. The model demonstrated high diagnostic accuracy, with an overall accuracy of 87.5%, and impressive precision and recall rates of 93.3% and 87.5%, respectively. It identified infection sites, platelet distribution width, reduced platelet count, and procalcitonin levels as key predictors. The model achieved an F1 Score of 90.3% and an area under the receiver operating characteristic curve of 88.0%, effectively differentiating between sepsis subtypes. Similarly, logistic regression and least absolute shrinkage and selection operator analysis underscored the significance of infectious sites. This methodology shows promise for enhancing elderly sepsis diagnosis and contributing to the advancement of precision medicine in the field of infectious diseases.

Keywords

• Sepsis
• Elderly
• Machine learning
• Random forest
• Escherichia coli
• Diagnostic accuracy