Rationale: Beginning in 2006, epidemics of a fatal lung injury of unknown cause in children were observed in Korea every spring. A recent study demonstrated that this type of children’s interstitial lung disease (chILD) is associated with humidifier disinfectant use. Objectives: To determine the clinical characteristics of this type of chILD and to assess whether the nationwide suspension of humidifier disinfectant sales in the autumn of 2011 affected its incidence. Methods: The clinical characteristics of suspected cases between 2006 and 2011 were determined by a nationwide retrospective study. The potential causal relationship with humidifier disinfectants was examined by a prospective surveillance study after humidifier disinfectant sales were suspended. Measurements and Main Results: In total, 138 children were diagnosed with this type of chILD, which was characterized by rapid progression, high mortality, predominance in the spring season, and a familial tendency. The annual incidence increased in 2011 and then dropped to zero in 2012. The children were on average 30.4 months old. The most frequent symptoms at admission were cough and dyspnea. As the disease progressed, the typical complication was spontaneous air leak. Eighty children (58%) died. Two years after humidifier disinfectant-sale suspension, no more new cases were found. Conclusions: This study suggests that humidifier disinfectant inhalation causes an idiopathic type of chILD that is characterized by spontaneous air leak, rapid progression, lack of response to treatment, and high mortality. Further safety studies must be performed on common environmental compounds, particularly those that enter the human body by an unusual route.

The rapid development in big data analytics and the data-rich environment of intensive care units together provide unprecedented opportunities for medical breakthroughs in the field of critical care. We developed and validated a machine learning-based model, the Pediatric Risk of Mortality Prediction Tool (PROMPT), for real-time prediction of all-cause mortality in pediatric intensive care units. Utilizing two separate retrospective observational cohorts, we conducted model development and validation using a machine learning algorithm with a convolutional neural network. The development cohort comprised 1445 pediatric patients with 1977 medical encounters admitted to intensive care units from January 2011 to December 2017 at Severance Hospital (Seoul, Korea). The validation cohort included 278 patients with 364 medical encounters admitted to the pediatric intensive care unit from January 2016 to November 2017 at Samsung Medical Center. Using seven vital signs, along with patient age and body weight on intensive care unit admission, PROMPT achieved an area under the receiver operating characteristic curve in the range of 0.89–0.97 for mortality prediction 6 to 60 h prior to death. Our results demonstrated that PROMPT provided high sensitivity with specificity and outperformed the conventional severity scoring system, the Pediatric Index of Mortality, in predictive ability. Model performance was indistinguishable between the development and validation cohorts. PROMPT is a deep model-based, data-driven early warning score tool that can predict mortality in critically ill children and may be useful for the timely identification of deteriorating patients.