The Pediatric Data Science and Analytics Subgroup of the Pediatric Acute Lung Injury and Sepsis Investigators Network: Use of Supervised Machine Learning Applications in Pediatric Critical Care Medicine Research.

OBJECTIVE: Perform a scoping review of supervised machine learning in pediatric critical care to identify published applications, methodologies, and implementation frequency to inform best practices for the development, validation, and reporting of predictive models in pediatric critical care. DESIGN: Scoping review and expert opinion. SETTING: We queried CINAHL Plus with Full Text (EBSCO), Cochrane Library (Wiley), Embase (Elsevier), Ovid Medline, and PubMed for articles published between 2000 and 2022 related to machine learning concepts and pediatric critical illness. Articles were excluded if the majority of patients were adults or neonates, if unsupervised machine learning was the primary methodology, or if information related to the development, validation, and/or implementation of the model was not reported. Article selection and data extraction were performed using dual review in the Covidence tool, with discrepancies resolved by consensus. SUBJECTS: Articles reporting on the development, validation, or implementation of supervised machine learning models in the field of pediatric critical care medicine. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Of 5075 identified studies, 141 articles were included. Studies were primarily (57%) performed at a single site. The majority took place in the United States (70%). Most were retrospective observational cohort studies. More than three-quarters of the articles were published between 2018 and 2022. The most common algorithms included logistic regression and random forest. Predicted events were most commonly death, transfer to ICU, and sepsis. Only 14% of articles reported external validation, and only a single model was implemented at publication. Reporting of validation methods, performance assessments, and implementation varied widely. Follow-up with authors suggests that implementation remains uncommon after model publication. CONCLUSIONS: Publication of supervised machine learning models to address clinical challenges in pediatric critical care medicine has increased dramatically in the last 5 years. While these approaches have the potential to benefit children with critical illness, the literature demonstrates incomplete reporting, absence of external validation, and infrequent clinical implementation.

A Case of a Lethal Diquat Ingestion in a Toddler.

BACKGROUND: Diquat is an herbicide that may cause rapid and profound systemic toxicity. It can cause multisystem organ failure, primarily via its effects on the gastrointestinal, renal, cardiovascular, and central nervous systems. Case fatality rates as high as 43% have been reported. There is a paucity of pediatric literature on diquat poisoning, and in this article, we will discuss an unfortunate pediatric case that highlights the severity of diquat toxicity. CASE REPORT: We present the case of a child who ingested diquat, which led to multisystem organ failure and death. WHY SHOULD AN EMERGENCY PHYSICIAN BE AWARE OF THIS?: Clinicians should be aware of this herbicide's potential for significant morbidity and mortality, especially in children, in whom small quantities can be lethal. It is important that emergency physicians are aware of the significant toxicity of diquat and provide early gastric decontamination, as it is the only proven therapeutic strategy.

Characteristics and Outcomes of Children With Necrotizing Pneumonia.

OBJECTIVES: In this study, we describe the characteristics and outcomes of pediatric necrotizing pneumonia in the United States. DESIGN AND SETTING: A retrospective analysis of the Healthcare Cost and Utilization Project 2016 Kids Inpatient Database was performed. The Kids Inpatient Database is a large deidentified hospital discharge database of pediatric patients in the United States. PATIENTS: The database was filtered using International Classification of Diseases, 10th Edition code J85.0 to identify necrotizing pneumonia in children 28 days to 20 years old. INTERVENTIONS: Children with necrotizing pneumonia with and without bacterial isolation and with and without complex chronic conditions were compared. Sample weighting was employed to produce national estimates. MEASUREMENTS AND MAIN RESULTS: Of the 2,296,220 discharges, 746 patients had necrotizing pneumonia (prevalence: 3.2/10,000 discharges). In patients with necrotizing pneumonia, 46.6% required chest tubes, 6.1% underwent video-assisted thoracoscopic surgery, and 27.6% were mechanically ventilated. Pneumothorax was identified in 16.7% and pyothorax in 27.4%. The overall mortality rate was 4.1% (n = 31). Bacterial isolation was documented in 40.9%. The leading organisms identified in patients without a complex chronic condition were Streptococcus pneumoniae (12.6%) and Staphylococcus aureus (9.2%) and in patients with a complex chronic condition were S. aureus (13.4%) and Pseudomonas aeruginosa (12.8%). Patients with bacterial isolation were significantly more likely to develop pneumothorax (odds ratio, 2.6; CI, 1.6-4.2) or septic shock (odds ratio, 3.2; CI, 1.9-5.4) and require a chest tube (odds ratio, 2.5; CI, 1.7-3.5) or mechanical ventilation (odds ratio, 2.3; CI, 1.5-3.3) than patients without bacterial isolation. CONCLUSIONS: Bacterial etiology of necrotizing pneumonia in children varied with the presence or absence of a complex chronic condition. Bacterial isolation is associated with increased invasive procedures and complications. The mortality rate is higher in children with complex chronic conditions. This study provides national data on necrotizing pneumonia among hospitalized children.

Pediatric COVID-19 presenting as supraglottitis with vocal cord hypomobility.

In the United States, an estimated 7.3% of confirmed cases of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection (COVID-19) are among persons aged less than 18 years. Data regarding clinical manifestations in this age group are still evolving. An upper airway predilection has been reported in children. We describe the case of a 15-year-old female with supraglottitis and unilateral hypomobility of vocal cord with concern for critical airway, associated with COVID-19. She was managed by a multidisciplinary team including critical care, infectious diseases, and otolaryngology. This report adds to the sparse but evolving body of literature on the clinical presentation of COVID-19 disease in children.