AUTHOR=Yuan Siyi , Sun Yunbo , Xiao Xiongjian , Long Yun , He Huaiwu 

TITLE=Using Machine Learning Algorithms to Predict Candidaemia in ICU Patients With New-Onset Systemic Inflammatory Response Syndrome

JOURNAL=Frontiers in Medicine

VOLUME=Volume 8 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2021.720926

DOI=10.3389/fmed.2021.720926

ISSN=2296-858X

ABSTRACT=Background: Distinguishing ICU patients with candidaemia can help with the precise prescription of antifungal drugs in the creation of personalized guidelines. Previous prediction models of cadidaemia mostly used traditional logistic model and had some limitations. In this study, we developed a machine learning algorithm trained in predicting candidaemia in patients with new-onset systemic inflammatory response syndrome (SIRS).
Methods: This retrospective, observational study used clinical information collected between January 2013 and December 2017 from 3 hospitals. ICU patient data were used to train 4 machine learning algorithms–XGBoost, Support Vector Machine (SVM), Random Forest (RF), ExtraTrees (ET)–and a logistic regression (LR) model to predict patients with candidaemia.
Results: Of the 31070 cases of new-onset SIRS (in 28143 patients) included in the analysis, 137 new-onset SIRS cases (in 137 patients) were proven to be blood-culture positive for candidaemia. Risk factors, such as fungal colonization, diabetes, acute kidney injury, total number of parenteral nutrition days and renal replacement therapy, were important predictors of candidaemia. The XGBoost machine learning model outperformed the other models in distinguishing patients with candidaemia (XGBoost vs. SVM vs. RF vs. ET vs. LR; area under the curve (AUC) 0.92 vs. 0.86 vs. 0.91 vs. 0.90 vs. 0.52, respectively). The XGBoost model had a sensitivity of 84%, specificity of 89% and negative predictive value of 99.6% at the best cut-off value.
Conclusions: Machine learning algorithms can potentially predict candidaemia in the ICU and have better efficiency than previous models. These prediction models can be used to guide antifungal treatment for ICU patients when SIRS occurs.