Combining Federated Machine Learning and Qualitative Methods to Investigate Novel Pediatric Asthma Subtypes: Protocol for a Mixed Methods Study.

BACKGROUND: Pediatric asthma is a heterogeneous disease; however, current characterizations of its subtypes are limited. Machine learning (ML) methods are well-suited for identifying subtypes. In particular, deep neural networks can learn patient representations by leveraging longitudinal information captured in electronic health records (EHRs) while considering future outcomes. However, the traditional approach for subtype analysis requires large amounts of EHR data, which may contain protected health information causing potential concerns regarding patient privacy. Federated learning is the key technology to address privacy concerns while preserving the accuracy and performance of ML algorithms. Federated learning could enable multisite development and implementation of ML algorithms to facilitate the translation of artificial intelligence into clinical practice. OBJECTIVE: The aim of this study is to develop a research protocol for implementation of federated ML across a large clinical research network to identify and discover pediatric asthma subtypes and their progression over time. METHODS: This mixed methods study uses data and clinicians from the OneFlorida+ clinical research network, which is a large regional network covering linked and longitudinal patient-level real-world data (RWD) of over 20 million patients from Florida, Georgia, and Alabama in the United States. To characterize the subtypes, we will use OneFlorida+ data from 2011 to 2023 and develop a research-grade pediatric asthma computable phenotype and clinical natural language processing pipeline to identify pediatric patients with asthma aged 2-18 years. We will then apply federated learning to characterize pediatric asthma subtypes and their temporal progression. Using the Promoting Action on Research Implementation in Health Services framework, we will conduct focus groups with practicing pediatric asthma clinicians within the OneFlorida+ network to investigate the clinical utility of the subtypes. With a user-centered design, we will create prototypes to visualize the subtypes in the EHR to best assist with the clinical management of children with asthma. RESULTS: OneFlorida+ data from 2011 to 2023 have been collected for 411,628 patients aged 2-18 years along with 11,156,148 clinical notes. We expect to complete the computable phenotyping within the first year of the project, followed by subtyping during the second and third years, and then will perform the focus groups and establish the user-centered design in the fourth and fifth years of the project. CONCLUSIONS: Pediatric asthma subtypes incorporating RWD from diverse populations could improve patient outcomes by moving the field closer to precision pediatric asthma care. Our privacy-preserving federated learning methodology and qualitative implementation work will address several challenges of applying ML to large, multicenter RWD data. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/57981.

Development of a Computable Phenotype for Prehospital Pediatric Asthma Encounters.

INTRODUCTION: Asthma exacerbations are a common cause of pediatric Emergency Medical Services (EMS) encounters. Accordingly, prehospital management of pediatric asthma exacerbations has been designated an EMS research priority. However, accurate identification of pediatric asthma exacerbations from the prehospital record is nuanced and difficult due to the heterogeneity of asthma symptoms, especially in children. Therefore, this study's objective was to develop a prehospital-specific pediatric asthma computable phenotype (CP) that could accurately identify prehospital encounters for pediatric asthma exacerbations. METHODS: This is a retrospective observational study of patient encounters for ages 2-18 years from the ESO Data Collaborative between 2018 and 2021. We modified two existing rule-based pediatric asthma CPs and created three new CPs (one rule-based and two machine learning-based). Two pediatric emergency medicine physicians independently reviewed encounters to assign labels of asthma exacerbation or not. Taking that labeled encounter data, a 50/50 train/test split was used to create training and test sets from the labeled data. A 90/10 split was used to create a small validation set from the training set. We used specificity, sensitivity, positive predictive value (PPV), negative predictive value (NPV) and macro F1 to compare performance across all CP models. RESULTS: After applying the inclusion and exclusion criteria, 24,283 patient encounters remained. The machine-learning models exhibited the best performance for the identification of pediatric asthma exacerbations. A multi-layer perceptron-based model had the best performance in all metrics, with an F1 score of 0.95, specificity of 1.00, sensitivity of 0.91, negative predictive value of 0.98, and positive predictive value of 1.00. CONCLUSION: We modified existing and developed new pediatric asthma CPs to retrospectively identify prehospital pediatric asthma exacerbation encounters. We found that machine learning-based models greatly outperformed rule-based models. Given the high performance of the machine-learning models, the development and application of machine learning-based CPs for other conditions and diseases could help accelerate EMS research and ultimately enhance clinical care by accurately identifying patients with conditions of interest.

Measures of Patient Acuity Among Children Encountered by Emergency Medical Services by the Child Opportunity Index.

Background: Children have differing utilization of emergency medical services (EMS) by socioeconomic status. We evaluated differences in prehospital care among children by the Child Opportunity Index (COI), the agreement between a child's COI at the scene and at home, and in-hospital outcomes for children by COI. Methods: We performed a retrospective study of pediatric (<18 years) scene encounters from approximately 2,000 United States EMS agencies from the 2021-2022 ESO Data Collaborative. We evaluated socioeconomic status using the multi-dimensional COI v2.0 at the scene. We described EMS interventions and in-hospital outcomes by COI categories using ordinal regression. We evaluated the agreement between the home and scene COI. Results: Data were available for 99.8% of pediatric scene runs, with 936,940 included EMS responses. Children from lower COI areas more frequently had a response occurring at home (62.9% in Very Low COI areas; 47.1% in Very High COI areas). Children from higher COI areas were more frequently not transported to the hospital (odds ratio [OR] 0.87, 95% confidence interval [CI] 0.86-0.87). Children in lower COI areas had lower use of physical (OR 1.23, 95% CI 1.13-1.33) and chemical (OR 1.41, 95% CI 1.29-1.55) restraints for behavioral health problems. Among injured children with elevated pain scores (≥7), analgesia was provided more frequently to children in higher COI areas (OR 1.73, 95% CI 1.65-1.81). The proportion of children in cardiac arrest was lowest from higher COI areas. Among 107,114 encounters with in-hospital data, the odds of hospitalization was higher among children from higher COI areas (OR 1.14, 95% CI 1.11-1.18) and was lower for in-hospital mortality (OR 0.75, 95% CI 0.65-0.85). Home and scene COI had a strong agreement (Kendall's W = 0.81). Conclusion: Patterns of EMS utilization among children with prehospital emergencies differ by COI. Some measures, such as for in-hospital mortality, occurred more frequently among children transported from Very Low COI areas, whereas others, such as admission, occurred more frequently among children from Very High COI areas. These findings have implications in EMS planning and in alternative out-of-hospital care models, including in regional placement of ambulance stations.

Measuring the Implementation Preferences of Emergency Medical Services Clinicians Using Discrete Choice Experiments.

INTRODUCTION: Prehospital research and evidence-based guidelines (EBGs) have grown in recent decades, yet there is still a paucity of prehospital implementation research. While recent studies have revealed EMS agency leadership perspectives on implementation, the important perspectives and opinions of frontline EMS clinicians regarding implementation have yet to be explored in a systematic approach. The objective of this study was to measure the preferences of EMS clinicians for the process of EBG implementation and whether current agency practices align with those preferences. METHODS: This study was a cross-sectional survey of National Registry of Emergency Medical Technicians registrants. Eligible participants were certified paramedics who were actively practicing EMS clinicians. The survey contained discrete choice experiments (DCEs) for three EBG implementation scenarios and questions about rank order preferences for various aspects of the implementation process. For the DCEs, we used multinomial logistic regression to analyze the implementation preference choices of EMS clinicians, and latent class analysis to classify respondents into groups by their preferences. RESULTS: A total of 183 respondents completed the survey. Respondents had a median age of 39 years, were 74.9% male, 89.6% White, and 93.4% of non-Hispanic ethnicity. For all three DCE scenarios, respondents were significantly more likely to choose options with hospital feedback and individual-level feedback from EMS agencies. Respondents were significantly less likely to choose options with email/online only education, no feedback from hospitals, and no EMS agency feedback to clinicians. In general, respondents' preferences favored classroom-based training over in-person simulation. For all DCE questions, most respondents (66.2%-77.1%) preferred their survey DCE choice to their agency's current implementation practices. In the rank order preferences, most participants selected "knowledge of the underlying evidence behind the change" as the most important component of the process of implementation. CONCLUSIONS: In this study of EMS clinicians' implementation preferences using DCEs, respondents preferred in-person education, feedback on hospital outcomes, and feedback on their individual performance. However, current practice at EMS agencies rarely matched those expressed EMS clinician preferences. Collectively, these results present opportunities for improving EMS implementation from the EMS clinician perspective.

Early Administration of Steroids in the Ambulance Setting: An Observational Design Trial (EASI-AS-ODT).

BACKGROUND: In the emergency department (ED), prompt administration of systemic corticosteroids for pediatric asthma exacerbations decreases hospital admission rates. However, there is sparse evidence for whether earlier administration of systemic corticosteroids by emergency medical services (EMS) clinicians, prior to ED arrival, further improves pediatric asthma outcomes. METHODS: Early Administration of Steroids in the Ambulance Setting: An Observational Design Trial is a multicenter, observational, nonrandomized stepped-wedge design study with seven participating EMS agencies who adopted an oral systemic corticosteroid (OCS) into their protocols for pediatric asthma treatment. Using univariate analyses and multivariable mixed-effects models, we compared hospital admission rates for pediatric asthma patients ages 2-18 years before and after the introduction of a prehospital OCS and for those who did and did not receive a systemic corticosteroid from EMS. RESULTS: A total of 834 patients were included, 21% of whom received a systemic corticosteroid from EMS. EMS administration of systemic corticosteroids increased after the introduction of an OCS from 14.7% to 28.1% (p < 0.001). However, there was no significant difference between hospital admission rates and ED length of stay before and after the introduction of OCS or between patients who did and did not receive a systemic corticosteroid from EMS. Mixed-effects models revealed that age 14-18 years (coefficient -0.83, p = 0.002), EMS administration of magnesium (coefficient 1.22, p = 0.04), and initial EMS respiratory severity score (coefficient 0.40, p < 0.001) were significantly associated with hospital admission. CONCLUSIONS: In this multicenter study, the addition of an OCS into EMS agency protocols for pediatric asthma exacerbations significantly increased systemic corticosteroid administration but did not significantly decrease hospital admission rates. As overall EMS systemic corticosteroid administration rates were low, further work is required to understand optimal implementation of EMS protocol changes to better assess potential benefits to patients.

Evaluation of the implementation of evidence-based pediatric asthma exacerbation treatments in a regional consortium of emergency medical Services Agencies.

OBJECTIVE: Asthma exacerbations are a frequent reason for pediatric emergency medical services (EMS) encounters. The objective of this study was to examine the implementation of evidence-based treatments for pediatric asthma in a regional consortium of EMS agencies. METHODS: This retrospective study applied the Reach, Effectiveness, Adoption, Implementation, and Maintenance (RE-AIM) implementation framework to data from an EMS agency consortium in the Cincinnati, Ohio region. The study analyzed one year before an oral systemic corticosteroid (OCS) option was added to the agencies' protocol, and five years after the protocol change. We constructed logistic regression models for the primary outcome of Reach, defined as the proportion of pediatric asthma patients who received a systemic corticosteroid. We modeled Maintenance (Reach measured monthly over time) using time series models. RESULTS: A total of 713 patients were included, 133 pre- and 580 post-protocol change. In terms of Reach, 3% (n = 4) of eligible patients received a systemic corticosteroid pre-OCS versus 20% (n = 116) post-OCS. Multivariable modeling of Reach revealed the study period, EMS transport time, months since implementation of OCS, and number of bronchodilators administered by EMS as significant covariates for the administration of a systemic corticosteroid. For Maintenance, it took approximately two years to reach maximal administration of systemic corticosteroids. CONCLUSIONS: Indicators of asthma severity and time since the protocol change were significantly associated with EMS administration of systemic corticosteroids to pediatric asthma patients. The two-year time for maximal Reach suggests further work is required to understand how to best implement evidence-based pediatric asthma treatments in EMS.

Examination of disparities in prehospital encounters for pediatric asthma exacerbations.

Introduction: There are disparities in multiple aspects of pediatric asthma care; however, prehospital care disparities are largely undescribed. This study's objective was to examine racial and geographic disparities in emergency medical services (EMS) medication administration to pediatric patients with asthma. Methods: This is a substudy of the Early Administration of Steroids in the Ambulance Setting: An Observational Design Trial, which includes data from pediatric asthma patients ages 2-18 years. We examined rates of EMS administration of systemic corticosteroids and inhaled bronchodilators by patient race. We geocoded EMS scene addresses, characterized the locations' neighborhood-based conditions and resources relevant to children using the Child Opportunity Index (COI) 2.0, and analyzed associations between EMS scene address COI with medications administered by EMS. Results: A total of 765 patients had available racial data and 825 had scene addresses that were geocoded to a COI. EMS administered at least 1 bronchodilator to 84.7% (n = 492) of non-White patients and 83.2% of White patients (n = 153), P = 0.6. EMS administered a systemic corticosteroid to 19.4% (n = 113) of non-White patients and 20.1% (n = 37) of White patients, P = 0.8. There was a significant difference in bronchodilator administration between COI categories of low/very low versus moderate/high/very high (85.0%, n = 485 vs. 75.9%, n = 192, respectively, P = 0.003). Conclusions: There were no racial differences in EMS administration of medications to pediatric asthma patients. However, there were significantly higher rates of EMS bronchodilator administration for encounters in low/very low COIs. That latter finding may reflect inequities in asthma exacerbation severity for patients living in disadvantaged areas.

EMS Administration of Systemic Corticosteroids to Pediatric Asthma Patients: An Analysis by Severity and Transport Interval.

INTRODUCTION: Pediatric asthma exacerbations are a common cause of emergency medical services (EMS) encounters. Bronchodilators and systemic corticosteroids are mainstays of asthma exacerbation therapy, yet data on the efficacy of EMS administration of systemic corticosteroids are mixed. This study's objective was to assess the association between EMS administration of systemic corticosteroids to pediatric asthma patients on hospital admission rates based on asthma exacerbation severity and EMS transport intervals. METHODS: This is a sub-analysis of the Early Administration of Steroids in the Ambulance Setting: An Observational Design Trial (EASI AS ODT). EASI AS ODT is a non-randomized, stepped wedge, observational study examining outcomes one year before and one year after seven EMS agencies incorporated an oral systemic corticosteroid option into their protocols for the treatment of pediatric asthma exacerbations. We included EMS encounters for patients ages 2-18 years confirmed by manual chart review to have asthma exacerbations. We compared hospital admission rates across asthma exacerbation severities and EMS transport intervals using univariate analyses. We geocoded patients and created maps to visualize the general trends of patient characteristics. RESULTS: A total of 841 pediatric asthma patients met inclusion criteria. While most patients were administered inhaled bronchodilators by EMS (82.3%), only 21% received systemic corticosteroids, and only 19% received both inhaled bronchodilators and systemic corticosteroids. Overall, there was no significant difference in hospitalization rates between patients who did and did not receive systemic corticosteroids from EMS (33% vs. 32%, p = 0.78). However, although not statistically significant, for patients who received systemic corticosteroids from EMS, there was an 11% decrease in hospitalizations for mild exacerbation patients and a 16% decrease in hospitalizations for patients with EMS transport intervals greater than 40 min. CONCLUSION: In this study, systemic corticosteroids were not associated with a decrease in hospitalizations of pediatric patients with asthma overall. However, while limited by small sample size and lack of statistical significance, our results suggest there may be a benefit in certain subgroups, particularly patients with mild exacerbations and those with transport intervals longer than 40 min. Given the heterogeneity of EMS agencies, EMS agencies should consider local operational and pediatric patient characteristics when developing standard operating protocols for pediatric asthma.

Prehospital Management of Pediatric Behavioral Health Emergencies: A Scoping Review.

Pediatric behavioral health emergencies (BHE) are increasing in prevalence, yet there are no evidence-based guidelines or protocols for prehospital management. The primary objective of this scoping review is to identify prehospital-specific pediatric BHE research and publicly available emergency medical services (EMS) protocols for pediatric BHE. Secondary objectives include identifying the next priorities for research and EMS protocol considerations for children with neurodevelopmental conditions. This is a scoping review comprised of a research literature search for publications from 2012-2022 and an internet search for publicly available EMS protocols from the United States. Included publications contain data on the epidemiology of pediatric BHE or describe prehospital management of pediatric BHE. EMS protocols were included if they had advisements specific to pediatric BHE. A total of 50 research publications and EMS protocols from 43 states were screened. Seven publications and four protocols were included in this study. Research studies indicated an increase in pediatric BHE over the last decade, but few papers discuss current prehospital management (n=4). Two EMS protocols were specific to pediatric BHE or pediatric agitation, and the other two EMS protocols focused on adult populations with integrated pediatric recommendations. All four EMS protocols encouraged nonpharmaceutical interventions prior to the use of pharmacologic restraints. Although there is a substantial rise in pediatric BHE, there is sparse research data and clinical EMS protocols to support best practices for prehospital pediatric BHE management. This scoping review identifies important future research aims to inform best practices for the prehospital management of pediatric BHE.

A spatial and contextual exposome-wide association study and polyexposomic score of COVID-19 hospitalization.

Environmental exposures have been linked to COVID-19 severity. Previous studies examined very few environmental factors, and often only separately without considering the totality of the environment, or the exposome. In addition, existing risk prediction models of severe COVID-19 predominantly rely on demographic and clinical factors. To address these gaps, we conducted a spatial and contextual exposome-wide association study (ExWAS) and developed polyexposomic scores (PES) of COVID-19 hospitalization leveraging rich information from individuals' spatial and contextual exposome. Individual-level electronic health records of 50 368 patients aged 18 years and older with a positive SARS-CoV-2 PCR/Antigen lab test or a COVID-19 diagnosis between March 2020 and October 2021 were obtained from the OneFlorida+ Clinical Research Network. A total of 194 spatial and contextual exposome factors from 10 data sources were spatiotemporally linked to each patient based on geocoded residential histories. We used a standard two-phase procedure in the ExWAS and developed and validated PES using gradient boosting decision trees models. Four exposome measures significantly associated with COVID-19 hospitalization were identified, including 2-chloroacetophenone, low food access, neighborhood deprivation, and reduced access to fitness centers. The initial prediction model in all patients without considering exposome factors had a testing-area under the curve (AUC) of 0.778. Incorporation of exposome data increased the testing-AUC to 0.787. Similar findings were observed in subgroup analyses focusing on populations without comorbidities and aged 18-24 years old. This spatial and contextual exposome study of COVID-19 hospitalization confirmed previously reported risk factor but also generated novel predictors that warrant more focused evaluation.

Cancer incidence after asthma diagnosis: Evidence from a large clinical research network in the United States.

BACKGROUND: Prior studies on the association between asthma and cancer show inconsistent results. This study aimed to generate additional evidence on the association between asthma and cancer, both overall, and by cancer type, in the United States. METHOD: We conducted a retrospective cohort study using 2012-2020 electronic health records and claims data in the OneFlorida+ clinical research network. Our study population included a cohort of adult patients with asthma (n = 90,021) and a matching cohort of adult patients without asthma (n = 270,063). We built Cox proportional hazards models to examine the association between asthma diagnosis and subsequent cancer risk. RESULTS: Our results showed that asthma patients were more likely to develop cancer compared to patients without asthma in multivariable analysis (hazard ratio [HR] = 1.36, 99% confidence interval [CI] = 1.29-1.44). Elevated cancer risk was observed in asthma patients without (HR = 1.60; 99% CI: 1.50-1.71) or with (HR = 1.11; 99% CI: 1.03-1.21) inhaled steroid use. However, in analyses of specific cancer types, cancer risk was elevated for nine of 13 cancers in asthma patients without inhaled steroid use but only for two of 13 cancers in asthma patients with inhaled steroid use, suggesting a protective effect of inhaled steroid use on cancer. CONCLUSION: This is the first study to report a positive association between asthma and overall cancer risk in the US population. More in-depth studies using real-word data are needed to further explore the causal mechanisms of asthma on cancer risk.

Pediatric Bradycardia Is Undertreated in the Prehospital Setting: A Retrospective Multi-Agency Analysis.

BACKGROUND: Bradycardia is the most common terminal cardiac electrical activity in children, and early recognition and treatment is necessary to avoid cardiac arrest. Interventions such as oxygen, chest compressions, epinephrine, and atropine recommended by American Heart Association (AHA) Pediatric Advanced Life support (PALS) guidelines have been shown to improve outcomes (including higher survival rates) for inpatient pediatric patients with bradycardia. However, little is known about the epidemiology of pediatric prehospital bradycardia. We sought to investigate the incidence and management of pediatric bradycardia in the prehospital setting by emergency medical services (EMS). METHODS: This was a retrospective study of 911 scene response prehospital encounters for patients ages 0-18 years in 2019 from the United States ESO Research Data Collaborative. We defined age-based bradycardia per the 2015 AHA PALS guidelines. We performed general descriptive statistics and a univariate analysis examining any PALS-recommended interventions in the presence of altered mental status, hypotension for age, and a first heart rate less than 60. RESULTS: Of 7,422,710 encounters in the 2019 ESO Data Collaborative, 1,209 patients met inclusion criteria. Most (58.5%) were male, and the median age was 2 years (interquartile range 0-13 years). One-quarter (24.7%) of patients received fluids, and bag-valve mask ventilation was the most common airway intervention (12.1% of patients). Receipt of any PALS-recommended interventions was associated with age-adjusted hypotension (odds ratio (OR) 4.0, 95% confidence interval (CI) 3.9-5.4) and altered mental status (OR 15.5, 95% CI 10.7-22.3), but not a first heart rate less than 60 bpm (OR 0.9, 95% CI 0.6-1.1). CONCLUSIONS: To our knowledge, this study is the first to examine the incidence and management of prehospital pediatric bradycardia. Incidence was rare, but adherence to PALS guidelines was variable. Further research and education are needed to ensure proper prehospital treatment of pediatric bradycardia.

Using Natural Language Processing to Examine Social Determinants of Health in Prehospital Pediatric Encounters and Associations with EMS Transport Decisions.

BACKGROUND: Social determinants of health (SDOH) influence access to health care and are associated with inequities in patient outcomes, yet few studies have explored SDOH among pediatric EMS patients. The objective of this study was to examine the presence of SDOH in EMS clinician free text notes and quantify the association of SDOH with EMS pediatric transport decisions. METHODS: This was a retrospective analysis of primary 9-1-1 responses for patients ages 0-17 years from the 2019 ESO Data Collaborative research dataset. We excluded cardiac arrests and patients in law enforcement custody. Using natural language processing (NLP) we extracted the following SDOH categories: income insecurity, food insecurity, housing insecurity, insurance insecurity, poor social support, and child protective services. Univariate and multivariable associations between the presence of SDOH in EMS records and EMS transport decisions were assessed using logistic regression. RESULTS: We analyzed 325,847 pediatric EMS encounters, of which 35% resulted in non-transport. The median age was 10 years and 52% were male. Slightly over half (53%) were White, 31% were Black, and 11% were Hispanic. Child protective services (n = 2,620) and housing insecurity (n = 1,136) were the most common SDOH categories found in the EMS free text narratives. In the multivariable model, child protective services involvement (odds ratio (OR)=2.04 [95% confidence interval (CI) 1.84-2.05]), housing insecurity (OR = 1.46 [95% CI 1.26-1.70]), insurance security (OR = 2.44 [95% CI 1.93-3.09]), and poor social support (OR = 10.48 [95% CI 1.42-77.29]) were associated with greater odds of EMS transport. CONCLUSIONS: SDOH documentation in the EMS narrative was rare among pediatric encounters; however, children with documented SDOH were more likely to be transported. Additional exploration of the root causes and outcomes associated with SDOH among children encountered by EMS are warranted.

The Child Opportunity Index and Pediatric Emergency Medical Services Utilization.

Background: The delivery of emergency medical services (EMS) is a resource-intensive process, and prior studies suggest that EMS utilization in children may vary by socioeconomic status. The Child Opportunity Index (COI) provides a multidimensional measure of neighborhood-level resources and conditions that affect the health of children. We evaluated EMS utilization and measures of acuity among children by COI.Methods: We performed a cross-sectional study using encounters for patients less than 18 years of age from 10,067 EMS agencies in 47 US states and territories contributing to the National Emergency Medical Services Information System 2019 dataset. We compared patient demographics, EMS encounter characteristics, and care provided to children stratified by ZIP code using the COI 2.0.Results: We included 1,293,038 EMS encounters (median age 10 years, IQR 3-15 years). The distributions of encounters in the five tiers of COI were 30.6%, 20.1%, 18.0%, 16.3% and 15.1%, (from Very Low to Very High, respectively). The distribution of diagnoses between groups was similar. Most measures of EMS acuity/resource use were similar between groups, including non-transport status, cardiac arrest, vital sign abnormalities, and EMS-administered procedures and medications. Among children with respiratory-related encounters, children in the Very Low group had a greater need for nebulized medications (26.4% vs 18.3% in Very High COI children). Among children with trauma, a lower proportion in the Very Low group were given analgesia (4.0% vs 7.4% in the Very High group), though pain scores were similar in all groups.Conclusion: Pediatric EMS encounters from lower COI neighborhoods occur more frequently relative to encounters from higher COI neighborhoods. Despite these differences, children from lower COI strata generally have similar encounter characteristics to those in other COI strata, suggestive of a greater number of true out-of-hospital emergencies among children from these areas. Notable differences in care included use of respiratory medication to children with respiratory diagnoses, and administration of pain medication to children with trauma.

Emergency Medical Services Leadership Perspectives on Implementation of Evidence-Based Guidelines: A Qualitative Study.

Introduction: Prehospital evidence-based guidelines (EBGs) are developed to optimize clinical outcomes for emergency medical services (EMS) patients. However, widespread implementation of EBGs is often inconsistent. Therefore, this study aimed to assess the baseline knowledge and practices of EMS leaders related to EBG implementation.Methods: This was a qualitative study using focus groups to assess prehospital implementation awareness and knowledge. Participants were EMS EBG authors, EMS medical directors, and EMS professional organization leaders. Focus groups were held via video conference, audio recorded, and transcribed. Thematic coding used domains and constructs of the Consolidated Framework for Implementation Research (CFIR).Results: Six focus groups were conducted with a total of 18 participants. A total of 1,044 codes were analyzed. "Process" was the CFIR domain with the most codes (n = 350, 33.5%), followed by the "inner setting" (the EMS agency; n = 250, 23.9%), "characteristics of the intervention" (n = 203, 19.4%), "outer setting" (the health care system and community the EMS agency serves, and the broader national EMS professional context; n = 141, 13.5%), and "characteristics of individuals" (n = 100, 9.6%). The ten most frequent constructs across all domains were: reflecting and evaluating, executing, cosmopolitanism, planning, external policy and incentives, design quality and packaging, learning climate, culture, complexity, and other personal attributes.Conclusion: EMS leadership and stakeholder views on EBG implementation identified dominant themes related to the process of implementation and the culture and learning/implementation climate of EMS agencies. Opinions were mixed on the utility of the CFIR as a potential guide for EMS implementation. Further work is required to gain the frontline EMS clinician perspective on implementation and tie key themes to quantitative prehospital implementation outcomes.

Identification of Factors Associated with Return of Spontaneous Circulation after Pediatric Out-of-Hospital Cardiac Arrest Using Natural Language Processing.

INTRODUCTION: Prior studies examining prehospital characteristics related to return of spontaneous circulation (ROSC) in pediatric out-of-hospital cardiac arrest (OHCA) are limited to structured data. Natural language processing (NLP) could identify new factors from unstructured data using free-text narratives. The purpose of this study was to use NLP to examine EMS clinician free-text narratives for characteristics associated with prehospital ROSC in pediatric OHCA. METHODS: This was a retrospective analysis of patients ages 0-17 with OHCA in 2019 from the ESO Data Collaborative. We performed an exploratory analysis of EMS narratives using NLP with an a priori token library. We then constructed biostatistical and machine learning models and compared their performance in predicting ROSC. RESULTS: There were 1,726 included EMS encounters for pediatric OHCA; 60% were male patients, and the median age was 1 year (IQR 0-9). Most cardiac arrest events (61.3%) were unwitnessed, 87.3% were identified as having medical causes, and 5.9% had initial shockable rhythms. Prehospital ROSC was achieved in 23.1%. Words most positively correlated with ROSC were "ROSC" (r = 0.42), "pulse" (r = 0.29), "drowning" (r = 0.13), and "PEA" (r = 0.12). Words negatively correlated with ROSC included "asystole" (r = -0.25), "lividity" (r = -0.14), and "cold" (r = -0.14). The terms "asystole," "pulse," "no breathing," "PEA," and "dry" had the greatest difference in frequency of appearance between encounters with and without ROSC (p < 0.05). The best-performing model for predicting prehospital ROSC was logistic regression with random oversampling using free-text data only (area under the receiver operating characteristic curve 0.92). CONCLUSIONS: EMS clinician free-text narratives reveal additional characteristics associated with prehospital ROSC in pediatric OHCA. Incorporating those terms into machine learning models of prehospital ROSC improves predictive ability. Therefore, NLP holds promise as a tool for use in predictive models with the goal to increase evidence-based management of pediatric OHCA.

Prehospital Pediatric Asthma Care during COVID-19: Changes to EMS Treatment Protocols and Downstream Clinical Effects.

INTRODUCTION: During the COVID-19 pandemic, many emergency medical services (EMS) agencies modified treatment guidelines for clinical care and standard operating procedures. For the prehospital care of pediatric asthma exacerbations, modifications included changes to bronchodilator administration, systemic corticosteroid administration, and introduction of alternative medications. Since timely administration of bronchodilators and systemic corticosteroids has been shown to improve pediatric asthma clinical outcomes, we investigated the association of COVID-19 protocol modifications in the prehospital management of pediatric asthma on hospital admission rates and emergency department (ED) length-of-stay. METHODS: This is a multicenter, retrospective, observational cohort study comparing prehospital pediatric asthma patients treated by EMS clinicians from four EMS systems before and after implementation of COVID-19 interim EMS protocol modifications. We included children ages 2-18 years who were treated and transported by ground EMS for respiratory-related prehospital primary complaints, and who also had asthma-related ED discharge diagnoses. Patient data and outcomes were compared from 12 months prior to and 12 months after the implementation of interim COVID-19 prehospital protocol modifications using univariate and multivariable statistics. RESULTS: A total of 430 patients met inclusion criteria with a median age of 8 years. There was a slight male predominance (57.9%) and the majority of patients were African American (78.4%). There were twice as many patients treated prior to the COVID-19 protocol modifications (N = 287) compared to after (N = 143). There was a significant decrease in EMS bronchodilator administration from 76% to 59.4% of patients after COVID-19 protocol guidelines were implemented (p < 0.0001). Mixed effects models for hospital admission (to both pediatric inpatient units and pediatric intensive care units) as well as ED length-of-stay did not show any significant effect after the COVID-19 protocol change period (p = 0.18 and p = 0.55, respectively). CONCLUSIONS: Despite a decrease in prehospital bronchodilator administration after COVID-19 changes to prehospital pediatric asthma management protocols, hospital admission rates and ED length-of-stay did not significantly increase. However, this finding is tempered by the marked decrease in study patients treated after COVID-19 prehospital protocol modifications. Given the potential for future waves of COVID-19 variants, further studies with larger patient populations are warranted.

Pediatric and adult asthma clinical phenotypes: a real world, big data study based on acute exacerbations.

INTRODUCTION: Asthma is a heterogeneous disease with a range of observable phenotypes. To date, the characterization of asthma phenotypes is mostly limited to allergic versus non-allergic disease. Therefore, the aim of this big data study was to computationally derive asthma subtypes from the OneFlorida Clinical Research Consortium. METHODS: We obtained data from 2012-2020 from the OneFlorida Clinical Research Consortium. Longitudinal data for patients greater than two years of age who met inclusion criteria for an asthma exacerbation based on International Classification of Diseases codes. We used matrix factorization to extract information and K-means clustering to derive subtypes. The distributions of demographics, comorbidities, and medications were compared using Chi-square statistics. RESULTS: A total of 39,807 pediatric patients and 23,883 adult patients met inclusion criteria. We identified five distinct pediatric subtypes and four distinct adult subtypes. Pediatric subtype P1 had the highest proportion of black patients, but the lowest use of inhaled corticosteroids and allergy medications. Subtype P2 had a predominance of patients with gastroesophageal reflux disease, whereas P3 had a predominance of patients with allergic disorders. Adult subtype A2 was the most severe and all patients were on biologic agents. Most of subtype A3 patients were not taking controller medications, whereas most patients (>90%) in subtypes A2 and A4 were taking corticosteroids and allergy medications. CONCLUSION: We found five distinct pediatric asthma subtypes and four distinct adult asthma subtypes. Future work should externally validate these subtypes and characterize response to treatment by subtype to better guide clinical treatment of asthma.

Implementation of a pediatric asthma management program in rural primary care clinics.

OBJECTIVE: Rural communities experience a significant asthma burden. We pilot tested the implementation of Easy Breathing, a decision support program for improving primary care provider adherence to asthma guidelines in a rural community, and characterized asthma risk factors for enrollees. METHODS: We implemented Easy Breathing in two rural primary care practices for two years. Patient demographics, exposure histories, asthma severity, asthma medications, and treatment plans were collected. Providers' adherence to guidelines included the frequency of children with persistent asthma who were prescribed guidelines-based therapy and the frequency of children with a written asthma treatment plan on file. Clinicians provided feedback on the feasibility and acceptability of Easy Breathing using a validated survey tool and through semi-structured interviews. RESULTS: Two providers implemented the program. Enrollment included 518 children, of whom 135 (26%) had physician-confirmed asthma. After enrollment into Easy Breathing, 75% of children with asthma received a written asthma treatment plan All children with persistent asthma were prescribed an anti-inflammatory drug as part of their treatment plan. Providers (n = 2) rated Easy breathing as highly acceptable (M = 4.5), feasible (M = 4.5), and appropriate (M = 4.5). Qualitative feedback was positive, with suggestions to integrate the paper-based program into the electronic health record system for broader uptake. Enrollees with asthma were more likely to have a family history of asthma and endorse exposure to tobacco smoke and cockroaches. CONCLUSIONS: Easy Breathing shows promise as a decision support system that can be implemented in rural, medically underserved communities via primary care.