Prognostic clinical decision support for pneumonia in the emergency department: A randomized trial.

BACKGROUND: Hospitalization rates for childhood pneumonia vary widely. Risk-based clinical decision support (CDS) interventions may reduce unwarranted variation. METHODS: We conducted a pragmatic randomized trial in two US pediatric emergency departments (EDs) comparing electronic health record (EHR)-integrated prognostic CDS versus usual care for promoting appropriate ED disposition in children (<18 years) with pneumonia. Encounters were randomized 1:1 to usual care versus custom CDS featuring a validated pneumonia severity score predicting risk for severe in-hospital outcomes. Clinicians retained full decision-making authority. The primary outcome was inappropriate ED disposition, defined as early transition to lower- or higher-level care. Safety and implementation outcomes were also evaluated. RESULTS: The study enrolled 536 encounters (269 usual care and 267 CDS). Baseline characteristics were similar across arms. Inappropriate disposition occurred in 3% of usual care encounters and 2% of CDS encounters (adjusted odds ratio: 0.99, 95% confidence interval: [0.32, 2.95]) Length of stay was also similar and adverse safety outcomes were uncommon in both arms. The tool's custom user interface and content were viewed as strengths by surveyed clinicians (>70% satisfied). Implementation barriers include intrinsic (e.g., reaching the right person at the right time) and extrinsic factors (i.e., global pandemic). CONCLUSIONS: EHR-based prognostic CDS did not improve ED disposition decisions for children with pneumonia. Although the intervention's content was favorably received, low subject accrual and workflow integration problems likely limited effectiveness. Clinical Trials Registration: NCT06033079.

User-Centered Design and Implementation of an Interoperable FHIR Application for Pediatric Pneumonia Prognostication in a Randomized Trial.

OBJECTIVE: To support a pragmatic, electronic health record (EHR)-based randomized controlled trial, we applied user-centered design (UCD) principles, evidence-based risk communication strategies, and interoperable software architecture to design, test, and deploy a prognostic tool for children in emergency departments (EDs) with pneumonia. METHODS: Risk for severe in-hospital outcomes was estimated using a validated ordinal logistic regression model to classify pneumonia severity. To render the results usable for ED clinicians, we created an integrated SMART on FHIR web application built for interoperable use in two pediatric EDs using different EHR vendors: Epic and Cerner. We followed a UCD framework, including problem analysis and user research, conceptual design and early prototyping, user interface development, formative evaluation, and post-deployment summative evaluation. RESULTS: Problem analysis and user research from 39 clinicians and nurses revealed user preferences for risk aversion, accessibility, and timing of risk communication. Early prototyping and iterative design incorporated evidence-based design principles, including numeracy, risk framing, and best-practice visualization techniques. After rigorous unit and end-to-end testing, the application was successfully deployed in both EDs, which facilitatd enrollment, randomization, model visualization, data capture, and reporting for trial purposes. CONCLUSIONS: The successful implementation of a custom application for pneumonia prognosis and clinical trial support in two health systems on different EHRs demonstrates the importance of UCD, adherence to modern clinical data standards, and rigorous testing. Key lessons included the need for understanding users' real-world needs, regular knowledge management, application maintenance, and the recognition that FHIR applications require careful configuration for interoperability.

Health Literacy-Informed Communication to Reduce Discharge Medication Errors in Hospitalized Children: A Randomized Clinical Trial.

Importance: Inadequate communication between caregivers and clinicians at hospital discharge contributes to medication dosing errors in children. Health literacy-informed communication strategies during medication counseling can reduce dosing errors but have not been tested in the pediatric hospital setting. Objective: To test a health literacy-informed communication intervention to decrease liquid medication dosing errors compared with standard counseling in hospitalized children. Design, Setting, and Participants: This parallel, randomized clinical trial was performed from June 22, 2021, to August 20, 2022, at a tertiary care, US children's hospital. English- and Spanish-speaking caregivers of hospitalized children 6 years or younger prescribed a new, scheduled liquid medication at discharge were included in the analysis. Interventions: Permuted block (n = 4) randomization (1:1) to a health literacy-informed discharge medication communication bundle (n = 99) compared with standard counseling (n = 99). A study team member delivered the intervention consisting of a written, pictogram-based medication instruction sheet, teach back (caregivers state information taught), and demonstration of dosing with show back (caregivers show how they would draw the liquid medication in the syringe). Main Outcome and Measures: Observed dosing errors, assessed using a caregiver-submitted photograph of their child's medication-filled syringe and expressed as the percentage difference from the prescribed dose. Secondary outcomes included caregiver-reported medication knowledge. Outcome measurements were blinded to participant group assignment. Results: Among 198 caregivers randomized (mean [SD] age, 31.4 [6.5] years; 186 women [93.9%]; 36 [18.2%] Hispanic or Latino and 158 [79.8%] White), the primary outcome was available for 151 (76.3%). The observed mean (SD) percentage dosing error was 1.0% (2.2 percentage points) among the intervention group and 3.3% (5.1 percentage points) among the standard counseling group (absolute difference, 2.3 [95% CI, 1.0-3.6] percentage points; P < .001). Twenty-four of 79 caregivers in the intervention group (30.4%) measured an incorrect dose compared with 39 of 72 (54.2%) in the standard counseling group (P = .003). The intervention enhanced caregiver-reported medication knowledge compared with the standard counseling group for medication dose (71 of 76 [93.4%] vs 55 of 69 [79.7%]; P = .03), duration of administration (65 of 76 [85.5%] vs 49 of 69 [71.0%]; P = .04), and correct reporting of 2 or more medication adverse effects (60 of 76 [78.9%] vs 13 of 69 [18.8%]; P < .001). There were no differences in knowledge of medication name, indication, frequency, or storage. Conclusions and Relevance: A health literacy-informed discharge medication communication bundle reduced home liquid medication administration errors and enhanced caregiver medication knowledge compared with standard counseling. Routine use of these standardized strategies can promote patient safety following hospital discharge. Trial Registration: ClinicalTrials.gov Identifier: NCT05143047.

Validation of Childhood Pneumonia Prognostic Models for Use in Emergency Care Settings.

BACKGROUND: Unwarranted variation in disposition decisions exist among children with pneumonia. We validated three prognostic models for predicting pneumonia severity among children in the emergency department (ED) and hospital. METHODS: We performed a two-center, prospective study of children 6 months to <18 years presenting to the ED with pneumonia from January 2014 to May 2019. We evaluated three previously developed disease-specific prognostic models which use demographic, clinical, and diagnostic predictor variables, with each model estimating risk for Very Severe (mechanical ventilation or shock), Severe (ICU without very severe features), and Moderate/Mild (Hospitalization without severe features or ED discharge) pneumonia. Predictive accuracy was measured using discrimination (concordance or c-statistic) and re-calibration. RESULTS: There were 1088 children included in one or more of the three models. Median age was 3.6 years and the majority of children were male (53.7%) and identified as non-Hispanic White (63.7%). The distribution for the ordinal severity outcome was mild or moderate (79.1%), severe (15.9%), and very severe (4.9%). The three models each demonstrated excellent discrimination (C-statistic range across models [0.786-0.803]) with no appreciable degradation in predictive accuracy from the derivation cohort. CONCLUSIONS: All three prognostic models accurately identified risk for three clinically meaningful levels of pneumonia severity and demonstrated very good predictive performance. Physiologic variables contributed the most to model prediction. Application of these objective tools may help standardize and improve disposition and other management decisions for children with pneumonia.

Positive Predictive Value of ICD-10 Codes to Identify Acute Suicidal and Self Harm Behaviors.

OBJECTIVE: The accuracy of diagnosis codes to identify suicidal behaviors, including suicide ideation (SI) and self-harm (SH) events, is unknown. The objective of this study was to determine the positive predictive value (PPV) of International Classification of Disease, 10th Revision codes to identify SI/SH events that may be used in studies using administrative and claims data. METHODS: We performed a secondary analysis of a cross-sectional study of children 5 to 17 years of age hospitalized at 2 US children's hospitals with a discharge diagnosis of a neuropsychiatric event, including an SI or SH event. A true International Classification of Disease, 10th Revision SI or SH diagnosis was defined as SI or SH present on admission and directly related to hospitalization as compared with physician record review. PPV with 95% confidence intervals (CIs) were calculated overall and stratified by diagnosis order and age (5 to 11 years vs 12 to 17 years). RESULTS: There were 376 children or adolescents with a discharge diagnosis of an SI or SH event. The median age was 14 years, and the majority of individuals were female (58%), non-Hispanic White (69%), and privately insured (57%). A total of 332 confirmed SI/SH cases were identified with a PPV of 0.88 (95% CI 0.85-0.91). PPVs were similar when stratified by diagnosis order: primary 0.94 (95% 0.88-0.97) versus secondary 0.86 (95% CI 81-90). PPVs were also similar in adolescents (0.89, CI 0.85-0.92) compared with children (0.84, 95% CI 0.74-0.91). CONCLUSIONS: The use of these validated code sets to identify SI or SH events may minimize misclassification in future studies of suicidal and self-harm hospitalizations.

Characteristics Associated With Serious Self-Harm Events in Children and Adolescents.

OBJECTIVES: To identify patterns of psychiatric comorbidity among children and adolescents with a serious self-harm event. METHODS: We studied children aged 5 to 18 years hospitalized with a neuropsychiatric event at 2 children's hospitals from April 2016 to March 2020. We used Bayesian profile regression to identify distinct clinical profiles of risk for self-harm events from 32 covariates: age, sex, and 30 mental health diagnostic groups. Odds ratios (ORs) and 95% credible intervals (CIs) were calculated compared with a reference profile with the overall baseline risk of the cohort. RESULTS: We included 1098 children hospitalized with a neuropsychiatric event (median age 14 years [interquartile range (IQR) 11-16]). Of these, 406 (37%) were diagnosed with a self-harm event. We identified 4 distinct profiles with varying risk for a self-harm diagnosis. The low-risk profile (median 0.035 [IQR 0.029-0.041]; OR 0.08, 95% CI 0.04-0.15) was composed primarily of children aged 5 to 9 years without a previous psychiatric diagnosis. The moderate-risk profile (median 0.30 [IQR 0.27-0.33]; reference profile) included psychiatric diagnoses without depressive disorders. Older female adolescents with a combination of anxiety, depression, substance, and trauma disorders characterized the high-risk profile (median 0.69 [IQR 0.67-0.70]; OR 5.09, 95% CI 3.11-8.38). Younger males with mood and developmental disorders represented the very high-risk profile (median 0.76 [IQR 0.73-0.79]; OR 7.21, 95% CI 3.69-15.20). CONCLUSIONS: We describe 4 separate profiles of psychiatric comorbidity that can help identify children at elevated risk for a self-harm event and subsequent opportunities for intervention.

Antibiotic clinical decision support for pneumonia in the ED: A randomized trial.

BACKGROUND: Electronic health record-based clinical decision support (CDS) is a promising antibiotic stewardship strategy. Few studies have evaluated the effectiveness of antibiotic CDS in the pediatric emergency department (ED). OBJECTIVE: To compare the effectiveness of antibiotic CDS vs. usual care for promoting guideline-concordant antibiotic prescribing for pneumonia in the pediatric ED. DESIGN: Pragmatic randomized clinical trial. SETTING AND PARTICIPANTS: Encounters for children (6 months-18 years) with pneumonia presenting to two tertiary care children s hospital EDs in the United States. INTERVENTION: CDS or usual care was randomly assigned during 4-week periods within each site. The CDS intervention provided antibiotic recommendations tailored to each encounter and in accordance with national guidelines. MAIN OUTCOME AND MEASURES: The primary outcome was exclusive guideline-concordant antibiotic prescribing within the first 24 h of care. Safety outcomes included time to first antibiotic order, encounter length of stay, delayed intensive care, and 3- and 7-day revisits. RESULTS: 1027 encounters were included, encompassing 478 randomized to usual care and 549 to CDS. Exclusive guideline-concordant prescribing did not differ at 24 h (CDS, 51.7% vs. usual care, 53.3%; odds ratio [OR] 0.94 [95% confidence interval [CI]: 0.73, 1.20]). In pre-specified stratified analyses, CDS was associated with guideline-concordant prescribing among encounters discharged from the ED (74.9% vs. 66.0%; OR 1.53 [95% CI: 1.01, 2.33]), but not among hospitalized encounters. Mean time to first antibiotic was shorter in the CDS group (3.0 vs 3.4 h; p = .024). There were no differences in safety outcomes. CONCLUSIONS: Effectiveness of ED-based antibiotic CDS was greatest among those discharged from the ED. Longitudinal interventions designed to target both ED and inpatient clinicians and to address common implementation challenges may enhance the effectiveness of CDS as a stewardship tool.

Parental Perceptions of Penicillin Allergy Risk Stratification and Delabeling.

BACKGROUND: Penicillin (PCN) allergy labels are widely recognized to be highly inaccurate. Little is known about parental perceptions of the PCN allergy evaluation and removal process, especially in the hospital setting. METHODS: Focus groups were held with parents of children and adolescents with a PCN allergy label discharged from a large academic children's hospital between January 1, 2019, and April 15, 2020. The open-ended, semistructured moderator guide included questions about PCN allergy testing and evaluation, accuracy of the PCN allergy diagnosis, amoxicillin oral challenges, delabeling process, and preferred setting for PCN allergy delabeling evaluation (outpatient clinic, hospital, etc). Study investigators coded the transcripts and identified underlying themes using inductive and deductive thematic analysis. RESULTS: A total of 21 parents and 2 adolescents participated across 4 focus groups. We developed a theoretical framework depicting key elements of parents' and adolescents' experiences with PCN allergies, consisting of 4 major interconnected themes: (1) family context; (2) the invitation to delabel; (3) decision context; and (4) the PCN delabeling outcome. PCN allergies remained a concern for families even if their children passed an oral challenge. Some parents preferred testing to be performed in the hospital and felt this was a safer location for the procedure. CONCLUSIONS: Parents are amenable to hospital based PCN allergy evaluation and delabeling. Further studies should incorporate parental and patient preferences to implement safe and effective PCN allergy delabeling processes in the hospital setting.

Feasibility of a Centralized, Pharmacy-Led Penicillin Allergy Delabeling Program.

BACKGROUND: Penicillin allergy labels are often inaccurate in children and removing unnecessary labels results in improved outcomes and lower health care costs. Although the hospital setting is a frequent point of contact for children, strategies to evaluate penicillin allergies in the hospital are lacking. METHODS: We performed a prospective pilot study to determine the feasibility of a centralized, pharmacy-led approach to penicillin allergy evaluation. Children with a reported history of penicillin allergy admitted to our children's hospital were risk-stratified and those stratified as low-risk underwent a single-dose oral challenge by a central pharmacist, regardless of the need for antibiotics. After the completion of each patient's delabeling process, surveys were distributed to health care personnel involved in the patient's care to collect perceptions on the acceptability, appropriateness, and feasibility of this intervention. Measures were scored by using a 5-point Likert scale. RESULTS: Of the 23 patients who screened as low-risk, 20 underwent a penicillin allergy evaluation and an oral challenge. Of these, the penicillin allergy label was removed in 19 (95%) patients (Fig 1). The median age was 7 years (range 11 months-18 years). Participants rated the risk stratification and delabeling favorably overall, with high ratings on all 3 implementation measures: acceptability (mean 4.55, ± standard deviation [STD] 0.65), appropriateness (mean 4.58, STD ± 0.6), and feasibility (mean 4.51, STD ± 0.73). Measures of acceptability, appropriateness, and feasibility remained high when stratified by health care worker type and provider type. CONCLUSIONS: Our findings provide support for systemic implementation of penicillin allergy delabeling strategies in hospitalized children.

Associations between comorbidity-related functional limitations and pneumonia outcomes.

BACKGROUND: Underlying comorbidities are common in children with pneumonia. OBJECTIVE: To determine associations between comorbidity-related functional limitations and risk for severe pneumonia outcomes. DESIGN, SETTING, AND PARTICIPANTS: We prospectively enrolled children <18 years with and without comorbidities presenting to the emergency department with clinical and radiographic pneumonia at two institutions. Comorbidities included chronic conditions requiring daily medications, frequent healthcare visits, or which limited age-appropriate activities. Among children with comorbidities, functional limitations were defined as none or mild, moderate, and severe. MAIN OUTCOMES AND MEASURES: Outcomes included an ordinal severity outcome, categorized as very severe (mechanical ventilation, shock, or death), severe (intensive care without very severe features), moderate (hospitalization without severe features), or mild (discharged home), and length of stay (LOS). Multivariable ordinal logistic regression was used to examine associations between comorbidity-related functional limitations and outcomes, while accounting for relevant covariates. RESULTS: A cohort of 1116 children, including 452 (40.5%) with comorbidities; 200 (44.2%) had none or mild functional limitations, 93 (20.6%) moderate, and 159 (35.2%) had severe limitations. In multivariable analysis, comorbidity-related functional limitations were associated with the ordinal severity outcome and LOS (p < .001 for both). Children with severe functional limitations had tripling of the odds of a more severe ordinal (adjusted odds ratio [aOR]: 3.01, 95% confidence interval [2.05, 4.43]) and quadrupling of the odds for longer LOS (aOR: 4.72 [3.33, 6.70]) as compared to children without comorbidities. CONCLUSION: Comorbidity-related functional limitations are important predictors of disease outcomes in children with pneumonia. Consideration of functional limitations, rather than the presence of comorbidity alone, is critical when assessing risk of severe outcomes.

Identifying Acute Neuropsychiatric Events in Children and Adolescents.

OBJECTIVES: The objective of this study was to develop and validate an approach to accurately identify incident pediatric neuropsychiatric events (NPEs) requiring hospitalization by using administrative data. METHODS: We performed a cross-sectional, multicenter study of children 5 to 18 years of age hospitalized at two US children's hospitals with an NPE. We developed and evaluated 3 NPE identification algorithms: (1) primary or secondary NPE International Classification of Diseases, 10th Revision diagnosis alone, (2) NPE diagnosis, the NPE was present on admission, and the primary diagnosis was not malignancy- or surgery-related, and (3) identical to algorithm 2 but without requiring the NPE be present on admission. The positive predictive value (PPV) of each algorithm was calculated overall and by diagnosis field (primary or secondary), clinical significance, and NPE subtype. RESULTS: There were 1098 NPE hospitalizations included in the study. A total of 857 confirmed NPEs were identified for algorithm 1, yielding a PPV of 0.78 (95% confidence interval [CI] 0.76-0.80). Algorithm 2 (n = 846) had an overall PPV of 0.89 (95% CI 0.87-0.91). For algorithm 3 (n = 938), the overall PPV was 0.86 (95% CI 0.83-0.88). PPVs varied by diagnosis order, NPE clinical significance, and subtype. The PPV for critical clinical significance was 0.99 (0.97-0.99) for all 3 algorithms. CONCLUSIONS: We identified a highly accurate method to identify neuropsychiatric adverse events in children and adolescents. The use of these approaches will improve the rigor of future studies of NPE, including the necessary evaluations of medication adverse events, infections, and chronic conditions.

Association Between Procalcitonin and Antibiotics in Children With Community-Acquired Pneumonia.

OBJECTIVE: To determine whether empirical antibiotic initiation and selection for children with pneumonia was associated with procalcitonin (PCT) levels when results were blinded to clinicians. METHODS: We enrolled children <18 years with radiographically confirmed pneumonia at 2 children's hospitals from 2014 to 2019. Blood for PCT was collected at enrollment (blinded to clinicians). We modeled associations between PCT and (1) antibiotic initiation and (2) antibiotic selection (narrow versus broad-spectrum) using multivariable logistic regression models. To quantify potential stewardship opportunities, we calculated proportions of noncritically ill children receiving antibiotics who also had a low likelihood of bacterial etiology (PCT <0.25 ng/mL) and those receiving broad-spectrum therapy, regardless of PCT level. RESULTS: We enrolled 488 children (median PCT, 0.37 ng/mL; interquartile range [IQR], 0.11-2.38); 85 (17%) received no antibiotics (median PCT, 0.32; IQR, 0.09-1.33). Among the 403 children receiving antibiotics, 95 (24%) received narrow-spectrum therapy (median PCT, 0.24; IQR, 0.08-2.52) and 308 (76%) received broad-spectrum (median PCT, 0.46; IQR, 0.12-2.83). In adjusted analyses, PCT values were not associated with antibiotic initiation (odds ratio [OR], 1.02, 95% confidence interval [CI], 0.97%-1.06%) or empirical antibiotic selection (OR 1.07; 95% CI, 0.97%-1.17%). Of those with noncritical illness, 246 (69%) were identified as potential targets for antibiotic stewardship interventions. CONCLUSION: Neither antibiotic initiation nor empirical antibiotic selection were associated with PCT values. Whereas other factors may inform antibiotic treatment decisions, the observed discordance between objective likelihood of bacterial etiology and antibiotic use suggests important opportunities for stewardship.

Association of Race/Ethnicity and Social Determinants with Rehospitalization for Mental Health Conditions at Acute Care Children's Hospitals.

OBJECTIVE: To evaluate associations of race/ethnicity and social determinants with 90-day rehospitalization for mental health conditions to acute care nonpsychiatric children's hospitals. STUDY DESIGN: We conducted a retrospective cohort analysis of mental health hospitalizations for children aged 5-18 years from 2016 to 2018 at 32 freestanding US children's hospitals using the Children's Hospital Association's Pediatric Health Information System database to assess the association of race/ethnicity and social determinants (insurance payer, neighborhood median household income, and rurality of patient home location) with 90-day rehospitalization. Risk factors for rehospitalization were modeled using mixed-effects multivariable logistic regression. RESULTS: Among 23 556 index hospitalizations, there were 1382 mental health rehospitalizations (5.9%) within 90 days. Non-Hispanic Black children were 26% more likely to be rehospitalized than non-Hispanic White children (aOR 1.26, 95% CI 1.08-1.48). Those with government insurance were 18% more likely to be rehospitalized than those with private insurance (aOR 1.18, 95% CI 1.04-1.34). In contrast, those living in a suburban location were 22% less likely to be rehospitalized than those living in an urban location (suburban: aOR 0.78, 95% CI 0.63-0.97). CONCLUSIONS: Non-Hispanic Black children and those with public insurance were at greatest risk for 90-day rehospitalization, and risk was lower in those residing in suburban locations. Future work should focus on upstream interventions that will best attenuate social disparities to promote equity in pediatric mental healthcare.

Pneumonia Severity in Children: Utility of Procalcitonin in Risk Stratification.

OBJECTIVES: To determine if serum procalcitonin, an indicator of bacterial etiology in pneumonia in all ages and a predictor of severe pneumonia in adults, is associated with disease severity in children with community-acquired pneumonia. METHODS: We prospectively enrolled children 2 months to <18 years with clinical and radiographic pneumonia at 2 children's hospitals (2014-2019). Procalcitonin samples were obtained at presentation. An ordinal outcome scale of pneumonia severity was defined: very severe (intubation, shock, or death), severe (intensive care admission without very severe features and/or high-flow nasal cannula), moderate (hospitalization without severe or very severe features), and mild (discharge). Hospital length of stay (LOS) was also examined. Ordinal logistic regression was used to model associations between procalcitonin and outcomes. We estimated adjusted odds ratios (aORs) for a variety of cut points of procalcitonin ranging from 0.25 to 3.5 ng/mL. RESULTS: The study included 488 children with pneumonia; 30 (6%) were classified as very severe, 106 (22%) as severe, 327 (67%) as moderate, and 25 (5%) as mild. Median procalcitonin in the very severe group was 5.06 (interquartile range [IQR] 0.90-16.83), 0.38 (IQR 0.11-2.11) in the severe group, 0.29 (IQR 0.09-1.90) in the moderate group, and 0.21 (IQR 0.12-1.2) in the mild group. Increasing procalcitonin was associated with increasing severity (range of aORs: 1.03-1.25) and increased LOS (range of aORs: 1.04-1.36). All comparisons were statistically significant. CONCLUSIONS: Higher procalcitonin was associated with increased severity and LOS. Procalcitonin may be useful in helping clinicians evaluate pneumonia severity.

Social Disadvantage, Access to Care, and Disparities in Physical Functioning Among Children Hospitalized with Respiratory Illness.

BACKGROUND AND OBJECTIVES: Understanding disparities in child health-related quality of life (HRQoL) may reveal opportunities for targeted improvement. This study examined associations between social disadvantage, access to care, and child physical functioning before and after hospitalization for acute respiratory illness. METHODS: From July 1, 2014, to June 30, 2016, children ages 8-16 years and/or caregivers of children 2 weeks to 16 years admitted to five tertiary care children's hospitals for three common respiratory illnesses completed a survey on admission and within 2 to 8 weeks after discharge. Survey items assessed social disadvantage (minority race/ ethnicity, limited English proficiency, low education, and low income), difficulty/delays accessing care, and baseline and follow-up HRQoL physical functioning using the Pediatric Quality of Life Inventory (PedsQL, range 0-100). We examined associations between these three variables at baseline and follow-up using multivariable, mixed-effects linear regression models with multiple imputation sensitivity analyses for missing data. RESULTS: A total of 1,325 patients and/or their caregivers completed both PedsQL assessments. Adjusted mean baseline PedsQL scores were significantly lower for patients with social disadvantage markers, compared with those of patients with none (78.7 for >3 markers versus 85.5 for no markers, difference -6.1 points (95% CI: -8.7, -3.5). The number of social disadvantage markers was not associated with mean follow-up PedsQL scores. Difficulty/delays accessing care were associated with lower PedsQL scores at both time points, but it was not a significant effect modifier between social disadvantage and PedsQL scores. CONCLUSIONS: Having social disadvantage markers or difficulty/delays accessing care was associated with lower baseline physical functioning; however, differences were reduced after hospital discharge.

Natural Language Processing and Machine Learning to Enable Clinical Decision Support for Treatment of Pediatric Pneumonia.

Pneumonia is the most frequent cause of infectious disease-related deaths in children worldwide. Clinical decision support (CDS) applications can guide appropriate treatment, but the system must first recognize the appropriate diagnosis. To enable CDS for pediatric pneumonia, we developed an algorithm integrating natural language processing (NLP) and random forest classifiers to identify potential pediatric pneumonia from radiology reports. We deployed the algorithm in the EHR of a large children's hospital using real-time NLP. We describe the development and deployment of the algorithm, and evaluate our approach using 9-months of data gathered while the system was in use. Our model, trained on individual radiology reports, had an AUC of 0.954. The intervention, evaluated on patient encounters that could include multiple radiology reports, achieved a sensitivity, specificity, and positive predictive value of0.899, 0.949, and 0.781, respectively.

Home Smoke Exposure and Health-Related Quality of Life in Children with Acute Respiratory Illness.

OBJECTIVE: This study aims to assess whether secondhand smoke (SHS) exposure has an impact on health-related quality of life (HRQOL) in children with acute respiratory illness (ARI). METHODS: This study was nested within a multicenter, prospective cohort study of children (two weeks to 16 years) with ARI (emergency department visits for croup and hospitalizations for croup, asthma, bronchiolitis, and pneumonia) between July 1, 2014 and June 30, 2016. Subjects were surveyed upon enrollment for sociodemographics, healthcare utilization, home SHS exposure (0 or ≥1 smoker in the home), and child HRQOL (Pediatric Quality of Life Physical Functioning Scale) for both baseline health (preceding illness) and acute illness (on admission). Data on insurance status and medical complexity were collected from the Pediatric Hospital Information System database. Multivariable linear mixed regression models examined associations between SHS exposure and HRQOL. RESULTS: Home SHS exposure was reported in 728 (32%) of the 2,309 included children. Compared with nonexposed children, SHS-exposed children had significantly lower HRQOL scores for baseline health (mean difference -3.04 [95% CI -4.34, -1.74]) and acute illness (-2.16 [-4.22, -0.10]). Associations were strongest among children living with two or more smokers. HRQOL scores were lower among SHS-exposed children for all four conditions but only significant at baseline for bronchiolitis (-2.94 [-5.0, -0.89]) and pneumonia (-4.13 [-6.82, -1.44]) and on admission for croup (-5.71 [-10.67, -0.75]). CONCLUSIONS: Our study demonstrates an association between regular SHS exposure and decreased HRQOL with a dose-dependent response for children with ARI, providing further evidence of the negative impact of SHS.