Introduction: Pediatric in-hospital cardiac arrests and emergent transfers to the pediatric intensive care unit (ICU) represent a serious patient safety concern with associated increased morbidity and mortality. Some institutions have turned to the electronic health record and predictive analytics in search of earlier and more accurate detection of patients at risk for decompensation. Methods: Objective electronic health record data from 2011 to 2017 was utilized to develop an automated early warning system score aimed at identifying hospitalized children at risk of clinical deterioration. Five vital sign measurements and supplemental oxygen requirement data were used to build the Vitals Risk Index (VRI) model, using multivariate logistic regression. We compared the VRI to the hospital’s existing early warning system, an adaptation of Monaghan’s Pediatric Early Warning Score system (PEWS). The patient population included hospitalized children 18 years of age and younger while being cared for outside of the ICU. This dataset included 158 case hospitalizations (102 emergent transfers to the ICU and 56 “code blue” events) and 135,597 control hospitalizations. Results: When identifying deteriorating patients 2 hours before an event, there was no significant difference between Pediatric Early Warning Score and VRI’s areas under the receiver operating characteristic curve at false-positive rates ≤ 10% (pAUC₁₀ of 0.065 and 0.064, respectively; P = 0.74), a threshold chosen to compare the 2 approaches under clinically tolerable false-positive rates. Conclusions: The VRI represents an objective, simple, and automated predictive analytics tool for identifying hospitalized pediatric patients at risk of deteriorating outside of the ICU setting.

Objective: To develop and validate a predictive algorithm that identifies pediatric patients at risk of asthma-related emergencies, and to test whether algorithm performance can be improved in an external site via local retraining.Methods: In a retrospective cohort at the first site, data from 26 008 patients with asthma aged 2-18 years (2012-2017) were used to develop a lasso-regularized logistic regression model predicting emergency department visits for asthma within one year of a primary care encounter, known as the Asthma Emergency Risk (AER) score. Internal validation was conducted on 8634 patient encounters from 2018. External validation of the AER score was conducted using 1313 pediatric patient encounters from a second site during 2018. The AER score components were then reweighted using logistic regression using data from the second site to improve local model performance. Prediction intervals (PI) were constructed via 10 000 bootstrapped samples.Results: At the first site, the AER score had a cross-validated area under the receiver operating characteristic curve (AUROC) of 0.768 (95% PI: 0.745-0.790) during model training and an AUROC of 0.769 in the 2018 internal validation dataset (p = 0.959). When applied without modification to the second site, the AER score had an AUROC of 0.684 (95% PI: 0.624-0.742). After local refitting, the cross-validated AUROC improved to 0.737 (95% PI: 0.676-0.794; p = 0.037 as compared to initial AUROC).Conclusions: The AER score demonstrated strong internal validity, but external validity was dependent on reweighting model components to reflect local data characteristics at the external site.

Bicycling is a common childhood activity that is associated with significant injury risk. This study’s aim was to assess pediatric bicycle injury epidemiology and impacts of the COVID-19 pandemic. We conducted a cross-sectional evaluation of patients age < 18 years presenting with bicycle injury to a pediatric trauma center. A pre-pandemic period (1 March 2015–29 February 2020) was compared to the pandemic period (1 March 2020–28 February 2021). A total of 611 injury events for children < 18 years were included (471 pre-pandemic events and 140 pandemic events). The relative frequency of pandemic injuries was greater than pre-pandemic injuries (p < 0.001), resulting in a 48% increase in pandemic period injuries versus the pre-pandemic average (141 pandemic vs. 94.4/year pre-pandemic). Individuals of female sex represented a larger proportion of injuries in the pandemic period compared to the pre-pandemic period (37% pandemic vs. 28% pre-pandemic, p = 0.035). Injuries were more common on weekends versus weekdays (p = 0.01). Time series analysis showed a summer seasonality trend. Localizing injury events to ZIP codes showed regional injury density patterns. During COVID-19, there was an increase in bicycle injury frequency and proportional shift toward more injuries involving individuals of female sex. Otherwise, injury patterns were largely unchanged. These results demonstrate the necessity of safety interventions tailored to community needs.

Increasing evidence supports the influence of neighborhood factors on health care use and outcomes. This study measured the association between area-level social determinants of health (SDH) and type of dental care use among Ohio pediatric Medicaid beneficiaries. A retrospective dental claims analysis was completed for children aged 1 through 5 years enrolled in Ohio Medicaid with a dental visit in 2017. Dental care use was measured from 2017 through 2021 as 1 of 4 visit types: (1) preventive, (2) caries treatment, (3) dental general anesthesia (GA), and (4) dental emergency department. The Ohio Children's Opportunity Index defined area-level SDH at the census tract level. Exploratory analysis included descriptive statistics of area-level SDH for each outcome. Poisson regression models were developed to examine the associations between the number of each dental care use outcome and Ohio Children's Opportunity Index quintiles. Visualizations were facilitated with geospatial mapping. Fifty-six percent of children (10,008/17,675) had caries treatment visits. Overall area-level SDH were positively associated with preventive (fifth vs first quintile incidence rate ratio [IRR], 1.09; 95% CI, 1.07 to 1.12), caries treatment (fifth vs first quintile IRR, 1.16; 95% CI, 1.08 to 1.24), and dental GA visits (fifth vs first quintile IRR, 2.13; 95% CI, 1.13 to 4.01). Children with preventive, caries treatment, and dental GA visits were more likely to live in neighborhoods with better SDH. Future efforts should investigate the mechanisms by which area-level factors influence dental access and use. Neighborhood factors influence pediatric dental care use. Patient home addresses might add value to caries risk assessment tools and efforts by care networks to optimize efficient care use.

Objective: To develop a machine learning (ML) algorithm capable of identifying children at risk of out‐of‐home placement among a Medicaid‐insured population.Study Setting and Design: The study population includes children enrolled in a Medicaid accountable care organization between 2018 and 2022 in two nonurban Ohio counties served by the Centers for Medicare and Medicaid Services‐funded Integrated Care for Kids Model.Using a retrospective cohort, we developed and compared a set of ML algorithms to identify children at risk of out‐of‐home placement within one year. ML algorithms tested include least absolute shrinkage and selection operator (LASSO)‐regularized logistic regression and eXtreme gradient‐boosted trees (XGBoost). We compared both modeling approaches with and without race as a candidate predictor. Performance metrics included the area under the receiver operating characteristic curve (AUROC) and the corrected partial AUROC at specificities ≥ 90% (pAUROC₉₀). Algorithmic bias was tested by comparing pAUROC₉₀ across each model between Black and White children.Data Sources and Analytic Sample: The modeling dataset was comprised of Medicaid claims and patient demographics data from Partners For Kids, a pediatric accountable care organization.Principal Findings: Overall, XGBoost models outperformed LASSO models. When race was included in the model, XGBoost had an AUROC of 0.78 (95% confidence interval [CI]: 0.77–0.79) while the LASSO model had an AUROC of 0.75 (95% CI: 0.74–0.77). When race was excluded from the model, XGBoost had an AUROC of 0.76 (95% CI: 0.74–0.77) while LASSO had an AUROC of 0.73 (95% CI: 0.72–0.74).Conclusions: The more complex XGBoost outperformed the simpler LASSO in predicting out‐of‐home placement and had less evidence of racial bias. This study highlights the complexities of developing predictive models in systems with known racial disparities and illustrates what can be accomplished when ML developers and policy leaders collaborate to maximize data to meet the needs of children and families.