Kawasaki Disease Before and During the COVID-19 Pandemic: A Nationwide Population-based Study in the United States.

BACKGROUND: A decrease in the incidence of Kawasaki disease during the COVID-19 pandemic has been reported globally. Yet, previous US studies utilized patient populations of limited size and geographic scope, leaving a knowledge gap regarding the national trend. Employing a large sample size will increase the generalizability of the results and allow for more detailed analyses. METHODS: The observational study using the 2016-2020 National (Nationwide) Inpatient Sample examined changes in the Kawasaki disease hospitalization rate in pediatric patients during the COVID-19 pandemic. Sensitivity analyses examined hospitalizations between October and December each year, as the code for multisystem inflammatory syndrome in children was implemented in October 2020. RESULTS: In total, 24,505 hospitalizations with Kawasaki disease diagnoses were examined. Hospitalization rates were 65.1 and 53.8 per 1,000,000 pediatric population during the prepandemic and pandemic periods, respectively. Sensitivity analyses showed an overall decrease of 36.1%, with larger decreases for patients 1-4 years old (49.6%), males (40.0%), Asians or Pacific Islanders (57.9%) and patients in the South (47.5%), compared with their counterparts. Associations of the pandemic period with longer lengths of stay and higher daily costs were detected (adjusted mean ratio 1.11; P < 0.01 for length of stay, and adjusted mean ratio 1.33, P < 0.01 for costs). CONCLUSIONS: A decrease in the incidence of Kawasaki disease during the COVID-19 pandemic was observed nationwide in the United States. Contrary to a report from Japan, we did not observe a relationship between population density and a decrease in Kawasaki disease hospitalization. More detailed analyses in targeted geographical areas may provide further insights.

Alerting on mortality among patients discharged from the emergency department: a machine learning model.

OBJECTIVES: Physicians continuously make tough decisions when discharging patients. Alerting on poor outcomes may help in this decision. This study evaluates a machine learning model for predicting 30-day mortality in emergency department (ED) discharged patients. METHODS: We retrospectively analysed visits of adult patients discharged from a single ED (1/2014-12/2018). Data included demographics, evaluation and treatment in the ED, and discharge diagnosis. The data comprised of both structured and free-text fields. A gradient boosting model was trained to predict mortality within 30 days of release from the ED. The model was trained on data from the years 2014-2017 and validated on data from the year 2018. In order to reduce potential end-of-life bias, a subgroup analysis was performed for non-oncological patients. RESULTS: Overall, 363 635 ED visits of discharged patients were analysed. The 30-day mortality rate was 0.8%. A majority of the mortality cases (65.3%) had a known oncological disease. The model yielded an area under the curve (AUC) of 0.97 (95% CI 0.96 to 0.97) for predicting 30-day mortality. For a sensitivity of 84% (95% CI 0.81 to 0.86), this model had a false positive rate of 1:20. For patients without a known malignancy, the model yielded an AUC of 0.94 (95% CI 0.92 to 0.95). CONCLUSIONS: Although not frequent, patients may die following ED discharge. Machine learning-based tools may help ED physicians identify patients at risk. An optimised decision for hospitalisation or palliative management may improve patient care and system resource allocation.