Association of Bacteremia with Vaccination Status in Children Aged 2 to 36 Months

Risk Factors for Pediatric Sepsis in the Emergency Department: A Machine Learning Pilot Study

OBJECTIVE

To identify underappreciated sepsis risk factors among children presenting to a pediatric emergency department (ED).

METHODS

A retrospective observational study (2017-2019) of children aged 18 years and younger presenting to a pediatric ED at a tertiary care children's hospital with fever, hypotension, or an infectious disease International Classification of Diseases (ICD)-10 diagnosis. Structured patient data including demographics, problem list, and vital signs were extracted for 35,074 qualifying ED encounters. According to the Improving Pediatric Sepsis Outcomes Classification, confirmed by expert review, 191 patients met clinical sepsis criteria. Five machine learning models were trained to predict sepsis/nonsepsis outcomes. Top features enabling model performance (N = 20) were then extracted to identify patient risk factors.

RESULTS

Machine learning methods reached a performance of up to 93% sensitivity and 84% specificity in identifying patients who received a hospital diagnosis of sepsis. A random forest classifier performed the best, followed by a classification and regression tree. Maximum documented heart rate was the top feature in these models, with importance coefficients (ICs) of 0.09 and 0.21, which represent how much an individual feature contributes to the model. Maximum mean arterial pressure was the second most important feature (IC 0.05, 0.13). Immunization status (IC 0.02), age (IC 0.03), and patient zip code (IC 0.02) were also among the top features enabling models to predict sepsis from ED visit data. Stratified analysis revealed changes in the predictive importance of risk factors by race, ethnicity, oncologic history, and insurance status.

CONCLUSIONS

Machine learning models trained to identify pediatric sepsis using ED clinical and sociodemographic variables confirmed well-established predictors, including heart rate and mean arterial pressure, and identified underappreciated relationships between sepsis and patient age, immunization status, and demographics.

Immunization Status and the Management of Febrile Children in the Pediatric Emergency Department: What Are We Doing?

OBJECTIVES

Widespread Haemophilus influenzae and Streptococcus pneumoniae immunization has decreased occult bacteremia and bacterial meningitis rates. Practice has evolved in pediatric emergency departments (PEDs) to favor fewer diagnostic tests for and empiric treatment of invasive bacterial infection. We lack evidence-based guidance on evaluation and treatment of unimmunized (UnI) or underimmunized (UnderI) febrile children. This study aims to determine how parental report of immunization status in febrile PED patients impacts rates of diagnostic testing, interventions, and hospital admissions.

METHODS

This is a retrospective cohort study with chart review of encounters of children aged 3 to 36 months presenting to an academic, tertiary care PED in 2019 using International Classification of Diseases-10 code for fever (R50.9). Inclusion criteria were documented fever of 38°C and higher and well appearance. Encounters were excluded if there was a history of chronic illness or documentation of ill appearance or hemodynamic instability. Encounters were grouped by provider-documented immunization status. Fischer exact test and logistic regression compared rates of diagnostic testing (serum, urine or cerebrospinal fluid laboratory studies, and chest radiographs), interventions (intravenous fluid bolus, intravenous antibiotic or steroid administration, respiratory support, or breathing treatment), and hospital admissions between UnderI, UnI, and fully immunized (FI) groups.

RESULTS

Of the 1813 encounters reviewed, 1093 (60%) included provider-documented immunization status and 788 (43%) met final inclusion criteria: 23 (2.1%) UnI, 44 (5.8%) UnderI, and 721 (92.1%) FI. The UnderI and UnI children experienced significantly higher rates of laboratory evaluation including complete blood count and blood culture, medical intervention, and antibiotic prescriptions while in the PED. No significant differences were observed for rates of chest radiographs, hospital admissions, or 72-hour PED return visits.

CONCLUSIONS

Higher rates of laboratory testing and interventions were observed in UnderI and UnI versus FI febrile patients at a PED, likely demonstrating increased clinical suspicion for invasive bacterial infection in this group despite lacking national guidelines. Given continued vaccine hesitancy, further studies are needed for guiding management of febrile UnI and UnderI children presenting for emergency care.