Triage-based resource allocation and clinical treatment protocol on outcome and length of stay in the emergency department

Risk of mortality and cardiopulmonary arrest in critical patients presenting to the emergency department using machine learning and natural language processing

Emergency department triage is the first point in time when a patient's acuity level is determined. The time to assign a priority at triage is short and it is vital to accurately stratify patients at this stage, since under-triage can lead to increased morbidity, mortality and costs. Our aim was to present a model that can assist healthcare professionals in triage decision making, namely in the stratification of patients through the risk prediction of a composite critical outcome-mortality and cardiopulmonary arrest. Our study cohort consisted of 235826 adult patients triaged at a Portuguese Emergency Department from 2012 to 2016. Patients were assigned to emergent, very urgent or urgent priorities of the Manchester Triage System (MTS). Demographics, clinical variables routinely collected at triage and the patients' chief complaint were used. Logistic regression, random forests and extreme gradient boosting were developed using all available variables. The term frequency-inverse document frequency (TF-IDF) natural language processing weighting factor was applied to vectorize the chief complaint. Stratified random sampling was used to split the data into train (70%) and test (30%) data sets. Ten-fold cross validation was performed in train to optimize model hyper-parameters. The performance obtained with the best model was compared against the reference model-a regularized logistic regression trained using only triage priorities. Extreme gradient boosting exhibited good calibration properties and yielded areas under the receiver operating characteristic and precision-recall curves of 0.96 (95% CI 0.95-0.97) and 0.31 (95% CI 0.26-0.36), respectively. The predictors ranked with higher importance by this model were the Glasgow coma score, the patients' age, pulse oximetry and arrival mode. Compared to the reference, the extreme gradient boosting model using clinical variables and the chief complaint presented higher recall for patients assigned MTS-3 and can identify those who are at risk of the composite outcome.

Evaluation of adult stroke presentations at an Emergency Department in Queensland Australia

BACKGROUND

Stroke is a leading cause of mortality and morbidity which places high demands on emergency departments (EDs). Currently there is limited data on stroke presentations to Australian EDs and the time performance management of these presentations. Therefore, the aim of this study was to evaluate stroke presentations at an ED in Queensland, Australia in terms of demographics and time performance measures over a five year period.

METHODS

Retrospective analysis of ED presentations by patients ≥18 years with a final diagnosis of stroke between 1 July 2010 and 30 June 2015.

RESULTS

Over the five years there was a 51.4% increase in presentations diagnosed with stroke. The majority of these patients arrived by ambulance (71.0%) and were admitted (94.9%) with death in ED for 1.4% of presentations. From 2010 to 2015 for both haemorrhagic and ischaemic stroke there was a significant decrease in median LOS in ED (435 to 215 min, p < 0.05 and 451 to 238 min, p < 0.001 respectively) and in the proportion of patients in ED greater than four hours (82.4% to 44%, p < 0.05 and 92.4% to 45.8%,p < 0.0001 respectively).

CONCLUSION

Despite increased presentations of stroke, the ED improved in multiple time performance measures. Improving time-based targets in ED is particularly important for stroke presentations given the time critical nature of stroke management.

The Impact of Middle East Respiratory Syndrome Outbreak on Trends in Emergency Department Utilization Patterns

Changes occurred in the patterns of utilization of emergency medical services during the Middle East respiratory syndrome (MERS) outbreak. The purpose of this study was to analyze the patterns of adult and pediatric patients who visited the emergency department (ED) during the outbreak. This retrospective study was conducted by analyzing changes in the patterns of visits among adult and pediatric patients in the ED at one tertiary teaching hospital in Korea. The study was performed from June 1, 2013 to July 31, 2015. The MERS outbreak period was from June 1 to July 31, 2015, and we compared that period to the same periods in 2013 and 2014. We compared and analyzed the patients' characteristics, emergency severity index (ESI) level at the visit, cause of visit, diagnosis, final dispositions, injury/non-injury, length of stay at the ED (EDLOS), and hospitalization rate. A total of 9,107 patients visited the ED during this period. Of these patients, 2,572 (28.2%) were pediatric patients and 6,535 (71.8%) were adult patients. The most common cause of an ED visit was fever (adult patients: 21.6%, pediatric patients: 56.2%). The proportion of non-urgent visits involving an ESI level of 4 or 5 and the EDLOS decreased significantly in pediatric and adult patients in comparison to that during the past two years. This change was significant in pediatric patients. Among adult patients, the rate of injury decreased, whereas it increased among pediatric patients. During the MERS outbreak period, pediatric ED visits due to non-urgent cases decreased significantly and there were more pronounced differences in ED utilization patterns in pediatric patients than in adult patients.

Two Hour Evaluation and Referral Model for Shorter Turnaround Times in the emergency department

OBJECTIVE

The objective of this study was to assess the implementation of a novel ED model of care, which combines clinical streaming, team-based assessment and early senior consultation to reduce length of stay.

METHODS

A pre-post-intervention study was used to compare ED performance following an extensive clinical redesign programme. Clinical teams and work sequences were reconfigured to promote the role of the staff specialist, with a focus on earlier decisions regarding disposition. Primary outcome measures were ED length of stay and National Emergency Access Target (NEAT) compliance. Secondary outcomes included referral and workup times, wait times by triage category, ambulance offload times, ward discharges and unit transfers within 24 h of admission, representation within 48 h, and Medical Emergency Response Team (MERT) calls within 24 h of admission.

RESULTS

Two seasonally matched 26 week intervals were compared with adjustment for demographics, triage category and arrival by ambulance. Overall, there was an 18.4% rise in NEAT performance (95% confidence interval (CI): 17.7-19.1) while ED length of stay decreased by a total of 86.8 min (95% CI: 83.6-90.1). Time series analysis did not suggest any preexisting trends to explain these results. The average time to referral decreased by 74.7 min (95% CI: 69.8-79.6) and waiting times decreased across all triage categories. Rates of MERT activation and unplanned representation were unchanged.

CONCLUSION

A facilitated team leader role for senior doctors can help to reduce length of stay by via early disposition, without significant risks to the patient.

Assessing severity, immediacy, and ideal setting in ED patients: a pilot study on interrater reliability

OBJECTIVES

We conducted a pilot study to test the interrater reliability of emergency department (ED) physician assessments of 3 ED visit attributes-severity, immediacy, and ideal setting, with the long-term goal of developing a novel ED categorization system.

METHODS

Using 2010 National Hospital Ambulatory Care Survey data, we randomly selected 300 ED patient records for review by 6 emergency medicine physicians. Each record was assessed by 2 physicians for severity and immediacy using a 7-point scale; "ideal" setting was chosen among 6 possible settings. κ-Weighted and unweighted-and interclass correlation coefficients were used to test interrater agreement.

RESULTS

For severity, immediacy, and ideal setting, there was "fair" agreement in assessments with a weighted κ of 0.33 (95% confidence interval [CI], 0.27-0.40), 0.30 (95% CI, 0.23-0.36), and nonweighted κ of 0.28 (95% CI, 0.21-0.34), respectively. When both raters were "very certain" about their assessments, weighted κ increased to 0.42 (95% CI, 0.34-0.51) for severity and 0.35 (95% CI, 0.27-0.44) for immediacy. Interclass correlation coefficients showed similar results. There was agreement on ideal setting for 162 (54%) of 300 scenarios. Scenarios with poor agreement on ideal setting in general involved care for nonspecific symptoms rather than specific diagnoses.

CONCLUSIONS

Rater agreement among ED physicians when assessing clinical data on specific ED visits was fair for severity and immediacy ratings. Raters agreed on ideal treatment settings half the time. In general, there was greater agreement when a specific diagnosis was found rather than negative workups for symptoms. This demonstrates a validity issue when it comes to developing and using categorization systems for ED visits and assessing setting appropriateness.