Machine learning-based models for prediction of in-hospital mortality in patients with dengue shock syndrome

Abstract

BACKGROUND

Severe dengue children with critical complications have been attributed to high mortality rates, varying from approximately 1% to over 20%. To date, there is a lack of data on machine-learning-based algorithms for predicting the risk of in-hospital mortality in children with dengue shock syndrome (DSS).

AIM

To develop machine-learning models to estimate the risk of death in hospitalized children with DSS.

METHODS

This single-center retrospective study was conducted at tertiary Children’s Hospital No. 2 in Viet Nam, between 2013 and 2022. The primary outcome was the in-hospital mortality rate in children with DSS admitted to the pediatric intensive care unit (PICU). Nine significant features were predetermined for further analysis using machine learning models. An oversampling method was used to enhance the model performance. Supervised models, including logistic regression, Naïve Bayes, Random Forest (RF), K-nearest neighbors, Decision Tree and Extreme Gradient Boosting (XGBoost), were employed to develop predictive models. The Shapley Additive Explanation was used to determine the degree of contribution of the features.

RESULTS

In total, 1278 PICU-admitted children with complete data were included in the analysis. The median patient age was 8.1 years (interquartile range: 5.4-10.7). Thirty-nine patients (3%) died. The RF and XGboost models demonstrated the highest performance. The Shapley Addictive Explanations model revealed that the most important predictive features included younger age, female patients, presence of underlying diseases, severe transaminitis, severe bleeding, low platelet counts requiring platelet transfusion, elevated levels of international normalized ratio, blood lactate and serum creatinine, large volume of resuscitation fluid and a high vasoactive inotropic score (> 30).

CONCLUSION

We developed robust machine learning-based models to estimate the risk of death in hospitalized children with DSS. The study findings are applicable to the design of management schemes to enhance survival outcomes of patients with DSS.

Keywords: Dengue shock syndrome; Dengue mortality; Machine learning; Supervised models; Logistic regression; Random forest; K-nearest neighbors; Support vector machine; Extreme Gradient Boost; Shapley addictive explanations

Core Tip: The in-hospital mortality rate of children with dengue shock syndrome (DSS) at a large tertiary pediatric hospital in Viet Nam was 3%. The supervised models showed good predictive value. In particular, the Random Forest and Extreme Gradient Boost models demonstrated the highest model performance. The supervised machine learning model showed that the nine most important predictive variables included younger age, presence of underlying diseases, severe transaminitis, critical bleeding, platelet transfusion requirement, elevated international normalized ratio and blood lactate levels, and high vasoactive inotropic score (> 30). Identification of mortality predictors in patients with DSS will help optimize management protocols to enhance survival outcomes.