A machine learning-based risk score for prediction of mechanical ventilation in children with dengue shock syndrome: A retrospective cohort study

• Published in: PloS one 2024-12, Vol.19 (12), p.e0315281
• Main Authors: Thanh, Nguyen Tat, Luan, Vo Thanh, Viet, Do Chau, Tung, Trinh Huu, Thien, Vu
• Format: Article
• Language: English
• Subjects: Analysis; Artificial respiration; Business metrics; Care and treatment; Child; Child, Preschool; Children; Cohort analysis; Complications and side effects; Confidentiality; Datasets; Dengue; Dengue fever; Dengue hemorrhagic fever; Diagnosis; Diseases; Evaluation; Failure; Fatalities; Female; Hematocrit; Hospitalization; Hospitals; Humans; Infant; Infections; Laboratories; Learning algorithms; Literature reviews; Machine Learning; Male; Mechanical ventilation; Medical prognosis; Missing data; Mortality; Patient outcomes; Patients; Pediatrics; Prediction models; Regression analysis; Respiration, Artificial; Respiratory failure; Respiratory Insufficiency - mortality; Respiratory Insufficiency - therapy; Retrospective Studies; Review boards; Risk assessment; Risk Factors; Robustness; Severe Dengue - therapy; Statistical analysis; Support vector machines; Variables; Vasoactive agents; Vector-borne diseases; Ventilation; Ventilators
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0315281

Patients with severe dengue who develop severe respiratory failure requiring mechanical ventilation (MV) support have significantly increased mortality rates. This study aimed to develop a robust machine learning-based risk score to predict the need for MV in children with dengue shock syndrome (DSS) who developed acute respiratory failure. This single-institution retrospective study was conducted at a tertiary pediatric hospital in Vietnam between 2013 and 2022. The primary outcome was severe respiratory failure requiring MV in the children with DSS. Key covariables were predetermined by the LASSO method, literature review, and clinical expertise, including age (< 5 years), female patients, early onset day of DSS (≤ day 4), large cumulative fluid infusion, higher colloid-to-crystalloid fluid infusion ratio, severe bleeding, severe transaminitis, low platelet counts (< 20 x 109/L), elevated hematocrit, and high vasoactive-inotropic score. These covariables were analyzed using supervised models, including Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), k-Nearest Neighbor (KNN), and eXtreme Gradient Boosting (XGBoost). Shapley Additive Explanations (SHAP) analysis was used to assess feature contribution. A total of 1,278 patients were included, with a median patient age of 8.1 years (IQR: 5.4-10.7). Among them, 170 patients (13.3%) with DSS required mechanical ventilation. A significantly higher fatality rate was observed in the MV group than that in the non-MV group (22.4% vs. 0.1%). The RF and SVM models showed the highest model discrimination. The SHAP model explained the significant predictors. Internal validation of the predictive model showed high consistency between the predicted and observed data, with a good slope calibration in training (test) sets 1.0 (0.934), and a low Brier score of 0.04. Complete-case analysis was used to construct the risk score. We developed a robust machine learning-based risk score to estimate the need for MV in hospitalized children with DSS.