Triage and ATS: Collateral damage in the quest to improve ED performance

Five Level Triage vs. Four Level Triage in a Quaternary Emergency Department: National Analysis on Waiting Time, Validity, and Crowding-The CREONTE (Crowding and RE-Organization National TriagE) Study Group

Background and Objectives: Triage systems help provide the right care at the right time for patients presenting to emergency departments (EDs). Triage systems are generally used to subdivide patients into three to five categories according to the system used, and their performance must be carefully monitored to ensure the best care for patients. Materials and Methods: We examined ED accesses in the context of 4-level (4LT) and 5-level triage systems (5LT), implemented from 1 January 2014 to 31 December 2020. This study assessed the effects of a 5LT on wait times and under-triage (UT) and over-triage (OT). We also examined how 5LT and 4LT systems reflected actual patient acuity by correlating triage codes with severity codes at discharge. Other outcomes included the impact of crowding indices and 5LT system function during the COVID-19 pandemic in the study populations. Results: We evaluated 423,257 ED presentations. Visits to the ED by more fragile and seriously ill individuals increased, with a progressive increase in crowding. The length of stay (LOS), exit block, boarding, and processing times increased, reflecting a net raise in throughput and output factors, with a consequent lengthening of wait times. The decreased UT trend was observed after implementing the 5LT system. Conversely, a slight rise in OT was reported, although this did not affect the medium-high-intensity care area. Conclusions: Introducing a 5LT improved ED performance and patient care.

Early prediction of hospital admission of emergency department patients

OBJECTIVE

The early prediction of hospital admission is important to ED patient management. Using available electronic data, we aimed to develop a predictive model for hospital admission.

METHODS

We analysed all presentations to the ED of a tertiary referral centre over 7 years. To our knowledge, our data set of nearly 600 000 presentations is the largest reported. Using demographic, clinical, socioeconomic, triage, vital signs, pathology data and keywords in electronic notes, we trained a machine learning (ML) model with presentations from 2015 to 2020 and evaluated it on a held-out data set from 2021 to mid-2022. We assessed electronic medical records (EMRs) data at patient arrival (baseline), 30, 60, 120 and 240 min after ED presentation.

RESULTS

The training data set included 424 354 data points and the validation data set 53 403. We developed and trained a binary classifier to predict inpatient admission. On a held-out test data set of 121 258 data points, we predicted admission with 86% accuracy within 30 min of ED presentation with 94% discrimination. All models for different time points from ED presentation produced an area under the receiver operating characteristic curve (AUC) ≥0.93 for admission overall, with sensitivity/specificity/F1-scores of 0.83/0.90/0.84 for any inpatient admission at 30 min after presentation and 0.81/0.92/0.84 at baseline. The models retained lower but still high AUC levels when separated for short stay units or inpatient admissions.

CONCLUSION

We combined available electronic data and ML technology to achieve excellent predictive performance for subsequent hospital admission. Such prediction may assist with patient flow.

Triage in Australian emergency departments: Results of a New South Wales survey

AIM

To describe current models of triage, the preparation and education of triage nurses, and methods of auditing triage practice in New South Wales emergency departments.

BACKGROUND

Triage is a critical component of emergency department practice; affecting patient safety and access to emergency care. Within Australia, triage is an autonomous role predominantly conducted by trained emergency nurses. Patient safety and timely access to emergency care relies upon the experience, education and training of emergency triage nurses. To date, little is known about triage models of care, the preparation and education of triage nurses, and assessment of triage practice and decision accuracy.

METHOD

Descriptive, exploratory study design employing a self-reporting cross-sectional survey of clinical nurse consultants and educators in New South Wales.

RESULTS

The survey results reveal variability in models of triage, and the eligibility, preparation and education requirements of triage nurses; that appear geographically related. Auditing of triage practice was commonly undertaken retrospectively; feedback to triage nurses was infrequent. The survey found evidence of locally developed guidelines directing triage category allocation for specific conditions or symptoms.

CONCLUSION

The purpose of triage is to ensure that the level of emergency care provided is commensurate with clinical urgency. Variability in the preparation, education and evaluation of triage nurses may in and of itself, contribute to poor patient outcomes. Further, workforce size and geography may impede auditing and the provision of feedback, which are critical to improving triage practice and triage nurse performance. It is imperative that the Emergency Triage Education Kit be revised and maintained in tandem with future revisions of the Australasian Triage Scale.