Emergency Department Triage Research Articles

Accuracy of Prediction Models in Diagnosis of Acute Diverticulitis.

The diagnostic score models (DMs) for patients with acute diverticulitis (AcDi) have been rarely evaluated. Therefore, we tried to develop diagnostic models (DMs) to enhance the diagnostic accuracy (DA) of AcDi. In this AAP (acute abdominal pain) cohort, 30 AcDi patients were compared to 1,303 non-AcDi patients, with regard to their i) clinical symptoms (n=22), ii) signs and tests (n=14) as well as iii) laboratory analyses (n=3). The triage was performed at patient arrival to the emergency department (ED) (triage I) and at follow-up (triage II) before final decision. The triage included a suggested diagnosis of the AAP patient. Bivariate random effects meta-analysis was performed separately for 1) the pooled symptoms (n=22), 2) signs & tests (n=17) as well as 3) pooled DMs (I-V) with different cut-offs (with or without triage) to assess the diagnostic accuracy (DA) in detection of AcDi by HSROC (hierarchical summary receiver operating characteristic) curves. In the conventional receiver operating characteristic (ROC) analysis (for test optimization and finding optimal cut-off points), the area under curve (AUC) reached the following values for AcDi: i) DM without triage, AUC=0.843, ii) DM with triage I, AUC=0.866 and iii) DM with triage I and II, AUC=0.926. In the HSROC analysis, the AUC values for detection of AcDi were as follows; i) pooled clinical symptoms, AUC=0.540, ii) pooled clinical signs & tests, AUC=0.556 and iii) pooled DMs globally, AUC=0.853. In roccomp analysis for differences in AUC values: i) and iii) p<0.0001; between ii) and iii) p<0.0001. As confirmed by ROC and HSROC analysis, the new DMs with triage mode proved to be far superior in their DA for AcDi as compared to both symptoms and signs & tests. In the lack of earlier studies, these data report the first evidence that the DM including triage at an ED could improve the detection of AcDi.

In Vivo Performance of a Machine Learning Model Predicting Pediatric Sepsis at Triage

Introduction: Sepsis is a leading cause of pediatric mortality across the globe. Early recognition reduces mortality; and improve outcomes however, rapid detection remains difficult. Although physiologic mechanisms contribute to the complexity the epidemiology of pediatric Emergency Department (ED) visits also contributes. A variety of sepsis screening methods have been designed, from alerts based on triage temperature and heart rate to more complex algorithms. Evaluation of such tools has suggested improved identification, yet there is a lack of definitive data. Objective: The objective of this study was to evaluate the implementation and performance of the S2T2 (Sepsis Screening Triage Tool) in a pediatric ED. Methods: The S2T2 is a multiclass stochastic gradient boosting machine learning model recently developed at the study institution. It uses ED triage data and historical data mined from electronic health record to predict sepsis potential at triage. S2T2 was operationalized on 2/1/21; performance data for this study were collected over the first 7 months of implementation (to 8/31/21). Sensitivity and specificity were assessed by comparison with final International Classification of Disease-10 diagnoses codes. The pediatric ED at which this model was developed is a level-2 pediatric trauma center with an annual census of approximately 96,000. Results: In total, 43,337 patients were included, 41 with severe sepsis and 121 with sepsis. S2T2 demonstrated a sensitivity of 41.5% and specificity of 99.2% for severe sepsis, and a sensitivity of 25.6% and specificity of 99.2% for sepsis. Conclusion: S2T2 may aide in the identification of pediatric patients at risk for sepsis, potentially allowing for accelerated diagnosis, intervention, improved care, and better outcomes.

Unsupervised Multi-Latent Space RL Framework for Video Summarization in Ultrasound Imaging.

The COVID-19 pandemic has highlighted the need for a tool to speed up triage in ultrasound scans and provide clinicians with fast access to relevant information. To this end, we propose a new unsupervised reinforcement learning (RL) framework with novel rewards to facilitate unsupervised learning by avoiding tedious and impractical manual labelling for summarizing ultrasound videos. The proposed framework is capable of delivering video summaries with classification labels and segmentations of key landmarks which enhances its utility as a triage tool in the emergency department (ED) and for use in telemedicine. Using an attention ensemble of encoders, the high dimensional image is projected into a low dimensional latent space in terms of: a) reduced distance with a normal or abnormal class (classifier encoder), b) following a topology of landmarks (segmentation encoder), and c) the distance or topology agnostic latent representation (autoencoders). The summarization network is implemented using a bi-directional long short term memory (Bi-LSTM) which utilizes the latent space representation from the encoder. Validation is performed on lung ultrasound (LUS), that typically represent potential use cases in telemedicine and ED triage acquired from different medical centers across geographies (India and Spain). The proposed approach trained and tested on 126 LUS videos showed high agreement with the ground truth with an average precision of over 80% and average F1 score of well over 44 ±1.7 %. The approach resulted in an average reduction in storage space of 77% which can ease bandwidth and storage requirements in telemedicine.

“I Was Here First, Why Did They Go Before Me”: Examining Patients'Perceptions of Priority in a Psychometric Study of Emergency Department Triage

IntroductionUnrealistic patient expectations for wait times can lead to poor satisfaction. This study’s dual purpose was: (1) to address disparities between patients’ perceived priority level and the Emergency Severity Index (ESI) assigned by emergency room triage nurses; and (2) to evaluate validity and reliability of using the Patient Perception of Priority to be Seen Survey (PPPSS) to investigate patient expectations for emergency department urgency. MethodsA two-group pretest-posttest quasi-experimental approach compared patient urgency opinions to nurse urgency ratings with and without a scripted educational intervention. This tested how closely patient perceptions were related to triage nurse ratings. ResultsReliability for the PPPSS was acceptable (reliability = 0.75). Patients who were rated lower urgency on the ESI by triage nurses tended to self-report higher urgency (rho = −0.44, P < .01). Attitudes were more consistent in the posttest patient group who were exposed to the scripted verbal description of emergency department procedures (χ2 (1, N = 352) = 8.09, P < .01). Patients who disagreed with emergency nurse scores tended to be younger on average (eg, < 40 years old; rho = 0.69, P < .01). Male identified patients tended to be rated both by nurses and themselves as higher urgency (beta = 0.18, P = .02). DiscussionWe recommend the PPPSS for nurses and researchers to quickly assess patient expectations. Additionally, promoting patient understanding through a scripted educational strategy about the ESI system may also result in improvements in communication between patients and nurses.

Evaluating musculoskeletal urgent care center triage and transfer of emergency conditions for emergency surgical assessment and intervention.

Musculoskeletal urgent care centers (MUCCs) are an alternative to emergency departments (EDs) for patients to seek care for low acuity orthopedic injuries such as ankle sprains or joint pain, but are not equipped to manage orthopedic emergencies that require a higher level of care provided in the ED. This study aims to evaluate telephone and online triage practices as well as ED transfer procedures for MUCCs for patients presenting with an orthopedic condition requiring urgent surgical intervention. We called 595 MUCCs using a standardized script presenting as a critical patient with symptoms of lower extremity compartment syndrome. We compared direct ED referral frequency and triage frequency for MUCCs for patients insured by either Medicaid or by private insurance. We found that patients presenting with an apparent compartment syndrome were directly referred to the ED by < 1 in 5 MUCCs. Additionally, < 5% of patients were asked additional triage questions that would increase clinician suspicion for compartment syndrome and allow MUCCs to appropriately direct patients to the ED. MUCCs provide limited telephone and online triage for patients, which may result in delays of care for life or limb threatening injuries that require ED resources such as sedation, reductions, and emergency surgery. However, when MUCCs did conduct triage, it significantly increased the likelihood that patients were appropriately referred to the ED. Level of Evidence: Level II, prognostic study.

Accuracy of nurses’ performance in triage using the emergency severity index and its relationship with clinical outcome measures

Emergency department (ED) triage in hospitals is part of their emergency structure carried out by nurses in emergency units. There have not been many studies available on nurses' performance in triage based on the emergency severity index (ESI). This present study aimed to investigate the nurses’ performance in triage with regard to the emergency severity index and its relation to clinical outcome measures in the emergency department. This was a cross-sectional study. The hospitalization record of 600 patients who arrived at the emergency department of Sanandaj Social Security Hospital was randomly assessed based on the accuracy of triage performed by nurses. The data analysis procedure was done by employing STATA software version 12, as well as Fisher's exact test, independent t-test, and one-way ANOVA. Findings of the study revealed that nurses’ overall performance in triage showed that 82.67% of nurses had perfect triage accuracy, 12.17% had low-level triage accuracy and 5.17% had high-level triage accuracy. There was an association between nurses' performance in triage with the disposition of patients (p=0.029) and length of stay (p=0.009). Results of the study highlighted the importance of theoretical and practical triage training courses for nurses and provided a foundation for identifying effective factors for decreasing the length of stay and disposition of patients in emergency care units.

Strategies to improve the quality of nurse triage in emergency departments: A realist review protocol.

The purpose of this realist review was to assess what works, for whom and in what context, regarding strategies that influence nurses' behaviour to improve triage quality in emergency departments (ED). Realist review protocol. This protocol follows the PRISMA-P statement and will include any type of study on strategies to improve the triage process in the ED (using recognized and validated triage scales). The included studies were examined for scientific quality using the Mixed Methods Appraisal Tool. The framework for this realist review is based on the Behaviour Change Wheel (BCW) and the context-mechanism-outcome (CMO) models. Nurses and ED decision makers will be informed on the evidence regarding strategies to improve the quality of triage and the factors required to maximize their effectiveness. Research gaps may also be identified to guide future research projects on the adoption of best practices in ED nursing triage.

Effect of triage training on the knowledge application and practice improvement among the practicing nurses of the emergency departments of the National Referral Hospitals, 2018; a pre-post study in Asmara, Eritrea

BackgroundTriage starts at the front door of the Emergency Department (ED), and repeatedly performed by the responsible duty nurses with the aim of facilitating a timely and appropriate treatment of patients. A triage system called the Orotta Triage System was implemented in the emergency settings of the selected hospitals in 2006, with the emergency nurses trained to triage using the system. Since the introduction, a majority of nurses have been replaced by new untrained nurses. This study was conducted to assess the impact of an educational intervention on the triage nurses knowledge and performance.MethodsA single group pre-posttest study design was performed in the adult EDs of the National Referral Eritrean Referral Hospitals, from January to July of 2018. All staff members in the ED were involved. Data collection tools utilized were, a self-administered knowledge assessing questionnaire and a practice observation checklist. Analysis was done in SPSS (version 22) using repeated measures ANOVA. Statistical significance level was set at P < 0.05.ResultsThe mean knowledge scores at Time 1(prior to the intervention), Time 2 (following the intervention) and Time 3 (three month follow up) were 6.23 (SD = 2.29), 10.55 (SD = 1.79), and 9.39(SD = 2.67) respectively. During the pre-intervention phase, only one (3%) nurse was determined to have adequate knowledge. Two days post training (immediate post-intervention), the percentage possessing adequate knowledge increased to 39% but dropped back to 19% three months later. Mean knowledge difference scores (95% CI) of immediate post and pre-intervention (Diff. = 4.32, 1 95%CI: 3.08–5.56), three months later and pre-intervention (Diff. = 3.16, 95%CI: 1.71–4.62) and immediate post and three months later (Diff. = 1.16, 95%CI: 0.12–2.20) were found to be statistically significant. The median score of appropriate triage practice at pre-intervention (Md = 6, IQR = 3) was not significantly different (p = 0.053) from that at post-intervention (Md = 8, IQR = 5).ConclusionThe level of triage knowledge and appropriate application was low among the emergency nurses prior to training. The training provided an initial improvement in knowledge, but no significant improvement in triage nursing performance. To optimize ED triage performance, appropriate, timely in-service training is required to ensure new staff are educated and experienced staff have their knowledge and skills refreshed.

Improving detection of undiagnosed HIV through routine screening in a central London emergency department

HIV is a global public health issue. Routine testing for HIV should be performed on all 16–59 years old attending emergency departments (EDs) in high-prevalence areas in the UK.In August...

Redirecting Nonurgent Patients From the Pediatric Emergency Department to Their Pediatrician Office for a Same-Day Visit-A Quality Improvement Initiative.

Providing high-quality care in the appropriate setting to optimize value is a worthy goal of an efficient health system. Consequences of managing nonurgent complaints in the emergency department (ED) have been described including inefficiency, loss of the primary care-patient relationship, and delayed care for other ED patients. The purpose of this initiative was to redirect nonurgent patients arriving in the ED to their primary care office for a same-day visit, and the SMART AIM was to increase redirected patients from 0% of those eligible to 30% in a 12-month period. The setting was a pediatric ED (PED) and primary care office of a tertiary care pediatric medical system. The initiative utilized the electronic health record to identify and mediate the redirection of patients to the patient's primary care office after ED triage. The primary measurement was the percentage of eligible patients redirected. Additional measures included health benefits during the primary care visit (vaccines, well-visits) and a balancing measure of patients returned to the PED. The SMART AIM of >30% redirection was achieved and sustained with a final redirection rate of 46%. In total, 216 of 518 eligible patients were redirected, with zero untoward outcomes. The encounter time for redirected patients was similar for those who remained in the PED, and additional health benefits were appreciated for redirected patients. This initiative redirected nonurgent patients efficiently from a PED setting to their primary care office. The process is beneficial to patients and families and supports the patient-centered medical home. The balancing measure of no harm done to patients who accepted redirect reinforced the reliability of PED triage. The benefits achieved through the project highlight the value of the primary care-patient relationship and the continued need to improve access for patients and families.

A Computer-Based Decision Support System for Emergency Department Triage.

Bişkin Çetin, Songül PhD, RN; Cebeci, Fatma PhD, RN; Eray, Oktay MD; Bilge, Uğur; Coşkun, Mustafa MSEditor(s): Alexander, Susan DNP, ANP-BC, ADM-BC Author Information

Machine learning models predicting undertriage in telephone triage

Background Undertriaged patients have worse outcomes than appropriately triaged patients. Machine learning provides better triage prediction than conventional triage in emergency departments, but no machine learning-based undertriage prediction models have yet been developed for prehospital telephone triage. We developed and validated machine learning models for telephone triage. Materials and methods We conducted a retrospective cohort study with the largest after-hour house-call (AHHC) service dataset in Japan. Participants were ≥16 years and used the AHHC service between 1 November 2018 and 31 January 2021. We developed five prediction models based on support vector machine (SVM), lasso regression (LR), random forest (RF), gradient-boosted decision tree (XGB), and deep neural network (DNN). The primary outcome was undertriage, and predictors were telephone triage level and routinely available telephone-based data, including age, sex, 80 chief complaint categories and 10 comorbidities. We measured the area under the receiver operating characteristic curve (AUROC) for all the models. Results We identified 15,442 eligible patients (age: 38.4 ± 16.6, male: 57.2%), including 298 (1.9%; age: 58.2 ± 23.9, male: 55.0%) undertriaged patients. RF and XGB outperformed the other models, with the AUROC values (95% confidence interval; 95% CI) of the SVM, LR, RF, XGB and DNN for undertriage being 0.62 (0.55–0.69), 0.79 (0.74–0.83), 0.81 (0.76–0.86), 0.80 (0.75–0.84) and 0.77 (0.73–0.82), respectively. Conclusions We found that RF and XGB outperformed other models. Our findings suggest that machine learning models can facilitate the early detection of undertriage and early intervention to yield substantially improved patient outcomes. KEY MESSAGES Undertriaged patients experience worse outcomes than appropriately triaged patients; thus, we developed machine learning models for predicting undertriage in the prehospital setting. In addition, we identified the predictors of risk factors associated with undertriage. Random forest and gradient-boosted decision tree models demonstrated better prediction performance, and the models identified the risk factors associated with undertriage. Machine learning models aid in the early detection of undertriage, leading to significantly improved patient outcomes and identifying undertriage-associated risk factors, including chief complaint categories, could help prioritize conventional telephone triage protocol revision.

253 DELIRIUM IDENTIFICATION AT INITIAL TRIAGE IN AN IRISH EMERGENCY DEPARTMENT SETTING

Abstract Background Over 10% of older adults are affected by delirium on presentation to Emergency Departments (ED), with many more developing it during a prolonged ED stay. Early detection is key to delirium management, but the diagnosis is often missed, with over 50% of delirium going undetected in the ED. In 2019 the HSE guideline on Early Identification and Management of Delirium in the ED recommended that all those over 65 years be screened on presentation to ED using the 4AT, a validated instrument in delirium screening. Through our ED’s delirium working group, we conducted a baseline audit on current rates of screening for delirium, ahead of a quality improvement project on management of patients with, or at risk of delirium in our ED. Methods A retrospective review was conducted of consecutive patients &amp;gt;65yrs who presented to ED in one month with the following terms mentioned in the presenting complaint at triage: confusion/delirium/memory/speech/language disturbance/agitation i.e. terms that could indicate possible delirium as considered by the triage practitioner. We also recorded whether a 4AT was recorded. An additional 50 charts from the consecutive series were randomly selected and examined for probable delirium on presentation which was not captured at triage. Results n=23/1,597 (&amp;lt;1%) had possible delirium recorded at triage as per our criteria. In-depth case note review supported the diagnosis of delirium in 20 of the 23 initially identified at triage. Only 5 of these had a documented 4AT score. Of the additional 50 charts screened, a further 6 had likely delirium of whom n=3 had a 4AT score completed. N=16 required hospital admission. Conclusion Delirium screening and detection rates at ED triage are less than expected, and below the 2019 national screening recommendations. Implementing same in any busy ED is challenging. We are developing a multifaceted educational program to address this and plan a repeat audit following implementation.

An external validation study of the Score for Emergency Risk Prediction (SERP), an interpretable machine learning-based triage score for the emergency department

Emergency departments (EDs) are experiencing complex demands. An ED triage tool, the Score for Emergency Risk Prediction (SERP), was previously developed using an interpretable machine learning framework. It achieved a good performance in the Singapore population. We aimed to externally validate the SERP in a Korean cohort for all ED patients and compare its performance with Korean triage acuity scale (KTAS). This retrospective cohort study included all adult ED patients of Samsung Medical Center from 2016 to 2020. The outcomes were 30-day and in-hospital mortality after the patients’ ED visit. We used the area under the receiver operating characteristic curve (AUROC) to assess the performance of the SERP and other conventional scores, including KTAS. The study population included 285,523 ED visits, of which 53,541 were after the COVID-19 outbreak (2020). The whole cohort, in-hospital, and 30 days mortality rates were 1.60%, and 3.80%. The SERP achieved an AUROC of 0.821 and 0.803, outperforming KTAS of 0.679 and 0.729 for in-hospital and 30-day mortality, respectively. SERP was superior to other scores for in-hospital and 30-day mortality prediction in an external validation cohort. SERP is a generic, intuitive, and effective triage tool to stratify general patients who present to the emergency department.

Transitioning from clinical cardiology to industry: general considerations

Normal prothrombin time (PT) and partial thromboplastin time (PTT) are recommended for administration of recombinant tissue-plasminogen activator (rt-PA) in stroke, but waiting for results can delay use. We examined the...

The Impact of Cultural Embeddedness on the Implementation of an Artificial Intelligence Program at Triage: A Qualitative Study.

Triage requires rapid determination of acuity and resources. Current modalities allow for individual judgment, with varied application of algorithmic rules. Although artificial intelligence can improve triage accuracy, gaps remain in understanding implementation facilitators and barriers, especially those related to the cultural understandings by nurses of emergency department presentations. The purpose of this study was to explore the cultural and technological elements of the implementation of an artificial intelligence clinical decision support aid (i.e., KATE) in an emergency nursing triage process in an urban community hospital on the West Coast of the United States. An exploratory qualitative study using semi-structured small group and individual interviews and constant comparison analysis strategies. The sample comprised 13 emergency department triage nurses at one site. Campinha-Bacote's theory of cultural competence framed the study. Responses yielded the overall theme of We know these people and we know these things. Supporting categories included the problem of aire; just another checkbox; gut trumps data; higher acuity with no resources; and technology as a safety net. Participants reported reliance on clinical experience and cultural knowledge to assign acuity. The implementation of an artificial intelligence program was initially received skeptically due to the acontextual nature of AI, but grew to be perceived as a safety net for triage decision making among emergency nurses.

353 The Use of Simulation Ultrasound to Train Emergency Clinicians in Transvaginal Ultrasound

Pelvic ultrasound is useful for rapid triage and diagnosis of emergency department (ED) patients in their first trimester of pregnancy who present with vaginal bleeding or abdominal pain. The objective of this study was to measure comfort and competency levels with transabdominal and transvaginal ultrasound before and after a brief educational session using transvaginal simulation training to assess the efficacy of the intervention.

312 Racial Differences in Adult Emergency Department Triage Assignment Across An Urban-Rural Health System

Despite attempts to limit triage subjectivity through use of the emergency severity index (ESI) algorithm, it is possible for implicit or explicit bias to impact acuity assignment. Across our health system, ESI is assigned by trained emergency registered nurses (RNs). Documented demographic characteristics, such as race and ethnicity, are often based upon perception rather than direct patient query. We sought to assess the impact of perceived race on emergency department (ED) ESI score assigned at triage across our 9- ED health system.

Electronic Diagnostic Support in Emergency Physician Triage: Qualitative Study With Thematic Analysis of Interviews.

BackgroundNot thinking of a diagnosis is a leading cause of diagnostic error in the emergency department, resulting in delayed treatment, morbidity, and excess mortality. Electronic differential diagnostic support (EDS) results in small but significant reductions in diagnostic error. However, the uptake of EDS by clinicians is limited.ObjectiveWe sought to understand physician perceptions and barriers to the uptake of EDS within the emergency department triage process.MethodsWe conducted a qualitative study using a research associate to rapidly prototype an embedded EDS into the emergency department triage process. Physicians involved in the triage assessment of a busy emergency department were provided the output of an EDS based on the triage complaint by an embedded researcher to simulate an automated system that would draw from the electronic medical record. Physicians were interviewed immediately after their experience. Verbatim transcripts were analyzed by a team using open and axial coding, informed by direct content analysis.ResultsIn all, 4 themes emerged from 14 interviews: (1) the quality of the EDS was inferred from the scope and prioritization of the diagnoses present in the EDS differential; (2) the trust of the EDS was linked to varied beliefs around the diagnostic process and potential for bias; (3) clinicians foresaw more benefit to EDS use for colleagues and trainees rather than themselves; and (4) clinicians felt strongly that EDS output should not be included in the patient record.ConclusionsThe adoption of an EDS into an emergency department triage process will require a system that provides diagnostic suggestions appropriate for the scope and context of the emergency department triage process, transparency of system design, and affordances for clinician beliefs about the diagnostic process and addresses clinician concern around including EDS output in the patient record.

114 Validation and Comparison of Triage-Based Screening Strategies for Sepsis

Prompt treatment of sepsis requires rapid identification and diagnosis, a tough proposition given the syndrome’s frequently subtle presentation and the busy emergency department (ED) environment. This study aims to validate and compare the discrimination of published models for patients with potential sepsis at ED triage.