Introduction Triage is an essential emergency department (ED) process designed to provide timely management depending on acuity and severity, although it may be inconsistent with the clinical and hospitalization outcomes. Thus, research have attempted to augment this process, with machine learning models showing advantages in predicting critical condition and hospitalization outcomes. Here, nationwide registry data were used to develop a machine learning-based classification model to predict the clinical course of paediatric ED visitors. Material & Method This cross-sectional observational study used data from the National Emergency Department Information System on emergency visits of children under 15 years of age from January 1, 2016 to December 31, 2017. The primary and secondary outcomes were to identify critically ill children and predict hospitalization from triage data, respectively. We trained a random forest model and compared its performance with that of the conventional triage system. Result A total of 2,621,710 children were eligible for the analysis and included 12,951 (0.5%) critical outcomes and 303,808 (11.6%) hospitalizations. The area under the receiver operating characteristic curve was 0.974 (95% confidence interval [CI] 0.971-0.977) for critical outcomes and 0.884 (95% CI 0.883?0.885) for hospitalization, which were higher than those of the conventional triage system. Conclusion The machine learning-based model using structured triage data from a nationwide database can effectively predict critical illness and hospitalization among children visiting the ED.