Asthma vital signs at triage: home or admission (ASTHmA)

Predicting hospitalization of pediatric asthma patients in emergency departments using machine learning

MOTIVATION

The timely identification of patients for hospitalization in emergency departments (EDs) can facilitate efficient use of hospital resources. Machine learning can help the early prediction of ED disposition; however, application of machine learning models requires both computer science skills and domain knowledge. This presents a barrier for those who want to apply machine learning to real-world settings.

OBJECTIVES

The objective of this study was to construct a competitive predictive model with a minimal amount of human effort to facilitate decisions regarding hospitalization of patients.

METHODS

This study used the electronic health record data from five EDs in a single healthcare system, including an academic urban children's hospital ED, from January 2009 to December 2013. We constructed two machine learning models by using automated machine learning algorithm (autoML) which allows non-experts to use machine learning model: one with data only available at ED triage, the other adding information available one hour into the ED visit. Random forest and logistic regression were employed as bench-marking models. The ratio of the training dataset to the test dataset was 8:2, and the area under the receiver operating characteristic curve (AUC), accuracy, and F1 were calculated to assess the quality of the models.

RESULTS

Of the 9,069 ED visits analyzed, the study population was made up of males (62.7 %), median (IQR) age was 6 (4, 10) years, and public insurance coverage (66.0 %). The majority had an Emergency Severity Index score of 3 (52.9 %). The prevalence of hospitalization was 22.5 %. The AUCs were 0.914 and 0.942. AUCs were 0.831 and 0.886 for random forests, and 0.795 and 0.823 for logistic regression. Among the predictors, an outcome at a prior visit, ESI level, time to first medication, and time to triage were the most important features for the prediction of the need for hospitalization.

CONCLUSIONS

In comparison with the conventional approaches, the use of autoML improved the predictive ability for the need for hospitalization. The findings can optimize ED management, hospital-level resource utilization and improve quality. Furthermore, this approach can support the design of a more effective patient ED flow for pediatric asthma care.

Elevated Heart Rate and Risk of Revisit With Admission in Pediatric Emergency Patients

OBJECTIVE

The aim of this study was to identify emergency department (ED) heart rate (HR) values that identify children at elevated risk of ED revisit with admission.

METHODS

We performed a retrospective cohort study of patients 0 to 18 years old discharged from a tertiary-care pediatric ED from January 2013 to December 2014. We created percentile curves for the last recorded HR for age using data from calendar year 2013 and used receiver operating characteristic (ROC) curves to characterize the performance of the percentiles for predicting ED revisit with admission within 72 hours. In a held-out validation data set (calendar year 2014 data), we evaluated test characteristics of last-recorded HR-for-age cut points identified as promising on the ROC curves, as well as those identifying the highest 5% and 1% of last recorded HRs for age.

RESULTS

We evaluated 183,433 eligible ED visits. Last recorded HR for age had poor discrimination for predicting revisit with admission (area under the curve, 0.61; 95% confidence interval, 0.58-0.63). No promising cut points were identified on the ROC curves. Cut points identifying the highest 5% and 1% of last recorded HRs for age showed low sensitivity (10.1% and 2.5%) with numbers needed to evaluate of 62 and 50, respectively, to potentially prevent 1 revisit with admission.

CONCLUSIONS

Last recorded ED HR discriminates poorly between children who are and are not at risk of revisit with admission in a pediatric ED. The use of single-parameter HR in isolation as an automated trigger for mandatory reevaluation prior to discharge may not improve revisit outcomes.

Development of a pediatric asthma predictive index for hospitalization

BACKGROUND

Variation in emergency department (ED) management for asthma exacerbation leads to disparities in care. Current asthma severity scores are insufficient to be used for hospitalization decisions.

OBJECTIVE

To develop and internally validate an asthma predictive index for hospitalization (APIH) to guide practitioners in their admission decision for children with asthma exacerbations.

METHODS

Data were collected from 12,066 children between 5 and 18 years old diagnosed with asthma exacerbation in the ED. Epidemiologic findings, number of inhaled corticosteroid canisters, short-acting β-blocker canisters, oral steroids, coexisting atopy, family history of atopy, insurance, and prior asthma ED visits or hospitalizations were compared between patients hospitalized and discharged. We used univariate analysis and multivariate analysis to determine the best predictor variables for hospitalization. Our study internally validated the prediction index to estimate future performance of the prediction rule.

RESULTS

The highest risk factors associated with asthma hospitalization from the ED are oxygen saturation less than 94%, respiratory rate greater than 31/min, history of pneumonia, and asthma ED visits in past 12 months. With a reduced predictive model that combined these risk factors, the odds ratio was 44.9 (95% CI, 32.8-61.4), which is extremely significant. Our C index of discrimination of 0.77 was similar to the validation C index of 0.78, which confirms a solid prediction model.

CONCLUSION

We have developed and internally validated a pediatric hospitalization prediction index for acute asthma exacerbation in the ED. Further studies are needed to externally validate the APIH before its implementation into clinical practice.

Standardized Asthma Admission Criteria Reduce Length of Stay in a Pediatric Emergency Department

OBJECTIVES

Asthma is the most common chronic illness in children and accounts for > 600,000 emergency department (ED) visits each year. Reducing ED length of stay (LOS) for moderate to severe asthmatics improves ED throughput and patient care for this high-risk population. The objective of this study was to determine the impact of adding standardized, respiratory score-based admission criteria to an asthma pathway on ED LOS for admitted patients, time to bed request, overall percentage of admitted asthmatics, inpatient LOS, and percentage of pediatric intensive care unit (PICU) admissions.

METHODS

This was a retrospective study of a quality improvement intervention. Statistical process control methodologies were used to analyze measures 15 months before and after implementation of a modified asthma pathway (June 2010 to December 2012; pathway modification September 2011).

RESULTS

A total of 3,688 patients aged 1 through 18 years who presented to the ED with an asthma exacerbation during the study period were included. Patients were excluded if they were not eligible for the asthma pathway. Patient characteristics were similar before and after the intervention. Mean ED LOS and time to bed request for admitted asthmatics both decreased by 30 minutes. There was no change in percentage of asthma admissions (34%), mean inpatient LOS (1.4 days), or percentage of PICU admissions (2%).

CONCLUSIONS

Standardizing care for asthma patients to include objective admission criteria early in the ED course may optimize patient care and improve ED flow.

PRAM score as predictor of pediatric asthma hospitalization

OBJECTIVES

The objective was to determine the association between asthma severity as measured by the Pediatric Respiratory Assessment Measure (PRAM) score and the likelihood of admission for pediatric patients who present to the emergency department (ED) with moderate-to-severe asthma exacerbations and who receive intensive asthma therapy.

METHODS

This was a secondary analysis of a prospective study of triage nurse-initiated steroid therapy in pediatric asthma. Children aged 2 to 17 years inclusive, presenting with moderate-to-severe acute asthma exacerbations (defined as PRAM ≥ 4), were included. To be eligible for inclusion in the study, children must have received "intensive asthma therapy," defined as nurse-initiated initial bronchodilator and oral steroid therapy at arrival to triage. PRAM scores were measured hourly as per ED protocol. The primary outcome was inpatient hospitalization; secondary outcome was ED stay greater than 8 hours. Logistic regression models were used to predict admission based on PRAM score at triage and then hourly thereafter. The area under the receiver operating characteristic curve (AUC) was calculated for each hour.

RESULTS

A total of 297 patients were included in the analysis, with an admission rate of 11.4% for patients receiving intensive therapy. The 3-hour PRAM (AUC = 0.85) significantly improved prediction of admission compared to PRAM at triage (p = 0.04).

CONCLUSIONS

The 3-hour PRAM scores best predicts the need for hospitalization. These results may be applied in clinical settings to facilitate the decision to admit or initiate more aggressive adjunctive therapy to decrease the need for hospitalization.