Rapid Triage Research Articles

EP036 Rapid clinical photography triage for suspected cancer referrals – A pilot study

EP036 Rapid clinical photography triage for suspected cancer referrals – A pilot study

Optimising Musculoskeletal Patient Flow Through Digital Triage and Supported Self-Management: A Service Evaluation Set Within Community Musculoskeletal Care.

Musculoskeletal (MSK) conditions are one of the leading causes of years of living with disability in the UK, resulting in pressure on the health system and the UK economy. In response to the increasing levels of patients accessing NHS care with MSK conditions across Sandwell and West Birmingham (SWB), a digital triage and self-management tool was implemented in 2023. To optimise safety, efficiency, and choice within the community MSK service from the first contact through to specialist MSK care through digital triage and supported self-management. SWB's community MSK service implemented two digital tools in January 2023. Objectives included 1. Increase safety, through providing 24/7 access to rapid digital MSK triage; 2. Optimise workforce by releasing clinicians back to face-to-face care, increasing clinical capacity, 3. Increase patient choice by offering digitally supported self-management to appropriate low risk patients. 4804 patients self-referred to the MSK service through the digital triage tool within the first 12 months. 378 of these patients were offered, accepted, and accessed self-management support using the digital self-management app. These innovations led to the release of 1240 clinical hours for face-to-face care, an average 8-week reduction in waiting times and high patient satisfaction (80% good/very good). Evaluation over the first 12 month showed that the digital innovations were safe, led to enhanced access to and choice of care pathways, optimised use of clinical staff, and received positive patient feedback. Research is needed in this newly emerging area of practice to support further adoption across the healthcare system.

A Pilot Rapid Triage Process for Prehospital ST-Segment Myocardial Infarction Patients Direct to the Catheterization Lab

A Pilot Rapid Triage Process for Prehospital ST-Segment Myocardial Infarction Patients Direct to the Catheterization Lab

Neural Network Ensemble to Detect Dicentric Chromosomes in Metaphase Images

The Dicentric Chromosome Assay (DCA) is widely used in biological dosimetry, where the number of dicentric chromosomes induced by ionizing radiation (IR) exposure is quantified to estimate the absorbed radiation dose an individual has received. Dicentric chromosome scoring is a laborious and time-consuming process which is performed manually in most cytogenetic biodosimetry laboratories. Further, dicentric chromosome scoring constitutes a bottleneck when several hundreds of samples need to be analyzed for dose estimation in the aftermath of large-scale radiological/nuclear incident(s). Recently, much interest has focused on automating dicentric chromosome scoring using Artificial Intelligence (AI) tools to reduce analysis time and improve the accuracy of dicentric chromosome detection. Our study aims to detect dicentric chromosomes in metaphase plate images using an ensemble of artificial neural network detectors suitable for datasets that present a low number of samples (in this work, only 50 images). In our approach, the input image is first processed by several operators, each producing a transformed image. Then, each transformed image is transferred to a specific detector trained with a training set processed by the same operator that transformed the image. Following this, the detectors provide their predictions about the detected chromosomes. Finally, all predictions are combined using a consensus function. Regarding the operators used, images were binarized separately applying Otsu and Spline techniques, while morphological opening and closing filters with different sizes were used to eliminate noise, isolate specific components, and enhance the structures of interest (chromosomes) within the image. Consensus-based decisions are typically more precise than those made by individual networks, as the consensus method can rectify certain misclassifications, assuming that individual network results are correct. The results indicate that our methodology worked satisfactorily in detecting a majority of chromosomes, with remarkable classification performance even with the low number of training samples utilized. AI-based dicentric chromosome detection will be beneficial for a rapid triage by improving the detection of dicentric chromosomes and thereby the dose prediction accuracy.

A new prehospital cardiac risk assessment index derived from vital signs by first contact emergency medical service, including prehospital oxygen saturation, for accurate prehospital triage of acute m

Abstract Background: Rapid and accurate triage is essential to improve the prognosis of patients with severe acute myocardial infarction (AMI). However, prehospital triage using vital signs, including prehospital oxygen saturation (SpO2), by first medical contact has not been evaluated. Purpose: The purpose of this study was to develop a new risk stratification index for AMI using vital signs including SpO2 for rapid and accurate prehospital triage. Methods: From January 2013 to June 2022, 3006 AMI patients who were directly transported by ambulance were enrolled from the Mie ACS registry. Based on observed risk relationships in 3,006 AMI patients, we developed and evaluated a prehospital cardiac risk assessment index (P-CRAI) using age, heart rate, and systolic blood pressure (SBP) and SpO2 to predict 30-day mortality: (heart rate×[age/10]2)/SBP＋1.1(100-SpO2). We also analyzed whether P-CRAI predicted the need for mechanical circulatory support (MCS) or ventilator use. Results: In the receiver operating characteristic (ROC) curve analysis, P-CRAI 38.1 has a sensitivity of 84.4%, specificity of 72.7%, and accuracy of 84.3% for predicting 30-day mortality, and P-CRAI was a strong predictor of 30-day mortality compared with the other indices and variables (Figure 1A). When divided into two groups with P-CRAI 38, Kaplan-Meier survival curves showed significant differences in 30-day survival between the high and low groups (83.7% vs. 98.7%, P<0.001, Figure 1B). P-CRAI≥38 was the strongest independent predictor of 30-day mortality with a hazard ratio of 7.64 compared to the other factors by multivariate Cox regression analysis. The spline curve of 30-day mortality by P-CRAI shows a correlation with prognosis (Figure 2A). In this study, we then used the bootstrap method to generate a calibration curve and validate P-CRAI. The results showed an excellent fit and that P-CRAI accurately estimated patient prognosis (Figure 2B). In addition, P-CRAI was a robust predictor of the very early events of death at 24 hours and MCS or ventilator use by ROC curve analysis. (c-statistic 0.835 and 0.726, respectively, P<0.01). Conclusion: The P-CRAI was found to be a useful tool for prehospital triage of AMI patients, accurately predicting 30-day mortality and the need for MCS.Figure 1.Figure 2.

Serial troponin sampling over 60-minutes allows early distinction between myocardial infarction and chronic myocardial injury in patients presenting to emergency departments

Abstract Background High-sensitivity cardiac troponins (hs-cTn) are key clinical biomarkers in the assessment and diagnosis of patients with suspected acute coronary syndromes presenting to Emergency Departments (ED). These tests facilitate rapid triage through 0h/1h blood sampling regimens. Most patients will not have myocardial infarction (MI) diagnosed, having either hs-cTn levels below the upper reference limit (URL) or stable elevations. The latter group of complex, often multimorbid, patients is termed chronic myocardial injury (CMI) according to the 4th Universal Definition of MI (4thUDMI). These patients have long-term morbidity and mortality rates higher than those with type 1 MI. Early distinction of CMI from MI remains challenging with debate regarding optimal hs-cTnT delta cut-offs; both 3ng/L and 5ng/L over one-hour have been proposed. Methods and Results We prospectively collected 0-, 30- and 60-minutes (+/- 5 min) hs-cTnT samples from 185 patients presenting to Liverpool Hospital ED (Sydney, Australia) between March and August 2023. Diagnoses were adjudicated according to the 4thUDMI as follows: 16 (8.6%) MI ruled-in, 66 (35.7%) CMI and 103 (55.7%) MI ruled-out. Linear regression was used to calculate individual hs-cTnT slopes for each patient. Between CMI and MI, each 1 ng/L/hour increase in the slope of hs-cTnT resulted in a two-fold (95% CI: 1.5 to 2.9) greater likelihood of MI being diagnosed (P < 0.001). A stable hs-cTnT trajectory was observed in CMI, which ranged between 0 and 3 ng/L/hour in all patients with an initial hs-cTnT level ≤ 50 ng/L. Chronic myocardial injury patients with an initial hs-cTnT level > 50ng/L (n=12), exhibited more kinetic slopes ranging up to 8ng/L/hour (P <0.001). Unexpectedly, three MI patients had a non-linear slope, of whom two patients would not have displayed a significant rise had the additional 30-minute sample not been collected. These outlying patients presented at 9-12 hours and over 12 hours from symptom onset. Conclusion This study offers a novel characterisation of CMI, which has not previously been investigated in an unselected ED cohort using three serial samples over one hour. It validates a hs-cTnT delta of 3ng/L/hour in the recent ESC guidelines. However, there is a need for greater characterisation of short-term hs-cTn variability for more personalised MI risk stratification and to guide more targeted observation and further investigation of CMI patients.

Application of FISH based G2-PCC assay for the cytogenetic assessment of high radiation dose exposures: Potential implications for rapid triage biodosimetry.

The main goal of this study is to test the utility of calyculin A induced G2-PCC assay as a biodosimetry triage tool for assessing a wide range of low and acute high radiation dose exposures of photons. Towards this initiative, chromosome aberrations induced by low and high doses of x-rays were evaluated and characterized in G2-prematurely condensed chromosomes (G2-PCCs) by fluorescence in situ hybridization (FISH) using human centromere and telomere specific PNA (peptide nucleic acid) probes. A dose dependent increase in the frequency of dicentric chromosomes was observed in the G2-PCCs up to 20 Gy of x-rays. The combined yields of dicentrics and rings in the G2-PCCs showed a clear dose dependency up to 20 Gy from 0.02/cell for 0.1 Gy to 14.98/cell for 20 Gy. Centric rings were observed more frequently than acentric ring chromosomes in the G2-PCCs at all the radiation doses from 1 Gy to 20 Gy. A head-to-head comparison was also performed by FISH on the yields of chromosome aberrations induced by different doses of x-rays (0 Gy -7.5 Gy) in colcemid arrested metaphase chromosomes and calyculin A induced G2-PCCs. In general, the frequencies of dicentrics, rings and acentric fragments were slightly higher in G2-PCCs than in colcemid arrested metaphase chromosomes at all the radiation doses, but the differences were not statistically significant. To reduce the turnaround time for absorbed radiation dose estimation, attempt was made to obtain G2-PCCs by reducing the culture time to 36 hrs. The absorbed doses estimated in x-rays irradiated (0,1,2 and 4 Gy) G2-PCCs after 36 hrs of culture were grossly like that of G2-PCCs and colcemid arrested metaphase chromosomes prepared after 48 hrs of culture. Our study indicates that the shortened version of calyculin A induced G2-PCC assay coupled with the FISH staining technique can serve as an effective triage biodosimetry tool for large-scale radiological/nuclear incidents.

Host Response Markers of Inflammation and Endothelial Activation Associated with COVID-19 Severity and Mortality: A GeoSentinel Prospective Observational Cohort.

The effect of the COVID-19 pandemic on healthcare systems emphasized the need for rapid and effective triage tools to identify patients at risk of severe or fatal infection. Measuring host response markers of inflammation and endothelial activation at clinical presentation may help to inform appropriate triage and care practices in patients with SARS-CoV-2 infection. We enrolled patients with COVID-19 across five GeoSentinel clinical sites (in Italy, Belgium, Canada, and the United States) from September 2020 to December 2021, and analyzed the association of plasma markers, including soluble urokinase-type plasminogen activator receptor (suPAR), soluble tumor necrosis factor receptor-1 (sTREM-1), interleukin-6 (IL-6), interleukin-8 (IL-8), complement component C5a (C5a), von Willebrand factor (VWF-a2), and interleukin-1 receptor antagonist (IL-1Ra), with 28-day (D28) mortality and 7-day (D7) severity (discharged, hospitalized on ward, or died/admitted to the ICU). Of 193 patients, 8.9% (16 of 180) died by D28. Higher concentrations of suPAR were associated with increased odds of mortality at D28 and severity at D7 in univariable and multivariable regression models. The biomarkers sTREM-1 and IL-1Ra showed bivariate associations with mortality at D28 and severity at D7. IL-6, VWF, C5a, and IL-8 were not as indicative of progression to severe disease or death. Conclusions: Our findings confirm previous studies' assertions that point-of-care tests for suPAR and sTREM-1 could facilitate the triage of patients with SARS-CoV-2 infection, which may help guide hospital resource allocation.

Remote Diagnosis of Retinal Detachment in an Emergency Department Using Nonmydriatic Hybrid Ocular Imaging.

Background: Ocular emergencies are commonly evaluated in general emergency departments (ED) where ophthalmologists are rarely available. Nonmydriatic ocular imaging combining color fundus photographs and optical coherence tomography (NMFP-OCT) can help with rapid remote triage by ophthalmologists. We evaluated the rate at which retinal detachments (RDs) can be diagnosed with NMFP-OCT in the ED. Methods: Quality improvement project with prospective collection of data on RD patients who had NMFP-OCT obtained by ED staff over 1 year. Photographs were interpreted remotely by ophthalmologists and all patients underwent an in-person ophthalmologic examination in the ED to confirm the presence of a RD. Results: A total of 63 eyes (58 patients) had a RD, among which 53 (84.1%) had strong suggestion of RD on ocular imaging (34 [54%] were seen on both color and OCT nerve/macula; 11 [17.5%] were seen on color but missed on OCT; 8 [12.7%] were missed on color but seen on OCT). Ten RDs (15.9%) were missed on both color and OCT because of peripheral location of the RD (4, 40%), vitreous hemorrhage (4, 40%), or poor image quality (2, 20%). A total of 40 out of 58 patients were not seen by an eye care provider prior to reaching our ED and 10 had an inappropriate stroke workup for acute vision loss of presumed vascular origin. Conclusion: NMFP-OCT of the posterior pole obtained by ED staff revealed the RD in 84.1% of eyes, allowing for rapid remote triage of patients with visual symptoms and avoiding unnecessary testing when the diagnosis of RD is confirmed.

Additional predictors of stroke and transient ischaemic attack in BEFAST positive patients in out-of-hours emergency primary care

Introduction In patients suspected of stroke or transient ischemic attack (TIA), rapid triaging is imperative to improve clinical outcomes. For this purpose, balance-eye-face-arm-speech-time (BEFAST) items are used in out-of-hours primary care (OHS-PC). We explored the risk of stroke and TIA among BEFAST positive patients calling to the OHS-PC, and assessed whether additional predictors could improve risk stratification. Methods This is a cross-sectional study of retrospectively gathered routine care data from telephone triage tape-recordings of patients calling the OHS-PC with neurological deficit symptoms, classified as BEFAST positive. Four models–with the predictors age, sex, a history of cardiovascular or cerebrovascular disease, and cardiovascular risk factors–were fitted using logistic regression to predict the outcome stroke or TIA. Likelihood ratio testing was used to select the best model, which was subsequently internally validated. Results The risk of stroke or TIA diagnosis was 52% among 1,289 BEFAST positive patients, median age 72 years, 56% female sex. Of patients with the outcome stroke/TIA, 24% received a low urgency allocation, while 92% had signs or symptoms when calling. Only the addition of age and sex improved predicting stroke or TIA (internally validated c-statistic 0.72, 95%CI 0.69–0.75). The predicted risk of stroke or TIA remained below 20% in those aged below 40. Females aged 70 or over and males aged 55 or over, had a predicted risk above 50%. Discussion Urgency allocation appears to be suboptimal in BEFAST positive patients calling the OHS-PC. Risk stratification could be improved in this setting by adding age and sex.

The effects of applying artificial intelligence to triage in the emergency department: A systematic review of prospective studies.

Accurate and rapid triage can reduce undertriage and overtriage, which may improve emergency department flow. This study aimed to identify the effects of a prospective study applying artificial intelligence-based triage in the clinical field. Systematic review of prospective studies. CINAHL, Cochrane, Embase, PubMed, ProQuest, KISS, and RISS were searched from March 9 to April 18, 2023. All the data were screened independently by three researchers. The review included prospective studies that measured outcomes related to AI-based triage. Three researchers extracted data and independently assessed the study's quality using the Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) protocol. Of 1633 studies, seven met the inclusion criteria for this review. Most studies applied machine learning to triage, and only one was based on fuzzy logic. All studies, except one, utilized a five-level triage classification system. Regarding model performance, the feed-forward neural network achieved a precision of 33% in the level 1 classification, whereas the fuzzy clip model achieved a specificity and sensitivity of 99%. The accuracy of the model's triage prediction ranged from 80.5% to 99.1%. Other outcomes included time reduction, overtriage and undertriage checks, mistriage factors, and patient care and prognosis outcomes. Triage nurses in the emergency department can use artificial intelligence as a supportive means for triage. Ultimately, we hope to be a resource that can reduce undertriage and positively affect patient health. We have registered our review in PROSPERO (registration number: CRD 42023415232).

Addition of the clinical frailty scale to triage tools and early warning scores improves mortality prognostication at 30 days: A prospective observational multicenter study.

Frailty, assessed with clinical frailty scale (CFS), alone or in combination with aggregated vital signs, has been proposed as a measure to better predict mortality of older patients in the emergency department (ED), but the added predictive value to conventional triage is unclear. This was a secondary analysis of a prospective observational study in three EDs in Sweden that evaluated the prognostic performance of the CFS alone or in combination with the national early warning score (NEWS), triage early warning score (TEWS) or the rapid emergency triage and treatment system (RETTS) triage tool using logistic regression. The primary outcome was 30-day mortality with 7- and 90-day mortality and admission as secondary outcomes reported as area under the receiver operating curve (AuROC) scores with 95% confidence intervals (CIs). The sensitivity, specificity, accuracy, predictive values, and likelihood ratios are reported for all models. A total of 1832 patients were included with 17 (0.9%), 57 (3.1%), and 121 (6.6%) patients dying within 7, 30, and 90 days, respectively. The admission rate was 43% (795/1832). Frailty (CFS>4) was significantly associated with 30-day mortality (odds ratio 6, 95% CI 3‒12, p<0.01). Prognostication of 30-day mortality was similar for all CFS-based models and better compared with models without CFS. The AuROC (95% CI) improved for RETTS from 0.67 (0.61‒0.74) to 0.83 (0.79‒0.88) (p=0.008), for NEWS from 0.53 (0.45‒0.61) to 0.82 (0.77‒0.87) (p<0.001), and for TEWS from 0.63 (0.55‒0.71) to 0.82 (0.77‒0.87) (p=0.002). Frailty measured with the CFS in combination with RETTS or structured vital sign assessment using NEWS or TEWS was better at prognosticating 30-day mortality compared to RETTS or early warnings score alone. Improved prognostication provides more realistic expectations and allows for informed discussions with patients and initiation of individualized treatment plans early in the ED process.

How Super Is Supertrack? Expediting Care of Fast-track Patients through a Pediatric Emergency Department.

Fast-track models decrease patient crowding in emergency departments (EDs) by redirecting low-acuity patients to an expedited care pathway. In 2016, this institution's pediatric ED created a fast-track pathway for patients evaluated in a rapid assessment triage area who needed further management in the primary ED. This "Supertrack" designation was intended for patients requiring up to 1 hour of additional care, though means of ensuring these patients were discharged within their anticipated timeframe were lacking. We aimed to increase the percentage of Supertrack patients discharged within 1 hour of their ED bed assignment from 17% to 50%. Interventions included the creation of objective Supertrack criteria, departmental-wide progress reports, personalized reminders, intake huddles, and documentation prompts. We visualized data from Plan, Do, Study, Act (PDSA) cycles with statistical process control charts to determine special cause variation. The percentage of Supertrack patients discharged within their anticipated timeframe increased from 17% to 27% without an increase in return ED visits. The average time Supertrack patients spent in the ED decreased from 121 to 103 minutes. Personalized reminders demonstrated a significant but short-lived improvement. We improved the flow of Supertrack patients by decreasing their length of stay and increasing how many were discharged within their anticipated timeframe. Limitations included an unexpected surge in patients with respiratory complaints and staffing and structural constraints preventing the designation of a discrete Supertrack assessment space with dedicated providers. These findings are helpful for institutions seeking to develop an effective fast-track model with limited space and resources.

Added predictive value of prehospital measurement of point-of-care lactate in an adult general EMS population in Sweden: a multi-centre observational study

BackgroundEmergency medical services (EMS) personnel must rapidly assess and transport patients with time-sensitive conditions to optimise patient outcomes. Serum lactate, a valuable in-hospital biomarker, has become more accessible in EMS settings through point-of-care (POC) testing. Although POC lactate levels are valuable in specific patient groups, its broader application in EMS remains unclear. This study assessed the additional predictive value of POC lactate levels in a general adult EMS population.MethodsThis prospective observational study (March 2018 to September 2019) involved two EMS organisations in Västra Götaland, Sweden. Patients were triaged using the Rapid Triage and Treatment System (RETTS). POC lactate levels were measured using StatStrip Xpress devices. Non-consecutive patients who received EMS and were aged 18 years and above were available for inclusion if triaged into RETTS levels: red, orange, yellow, or green if respiratory rate of ≥ 22 breaths/min. Outcomes were adverse outcomes, including a time-sensitive diagnosis, sequential organ failure assessment (SOFA) score ≥ 2, and 30-day mortality. Statistical analyses included descriptive statistics, imputation, and regression models to assess the impact of the addition of POC lactate levels to a base model (comprising patient age, sex, presence of past medical conditions, vital signs, pain, EMS response time, assessed triage condition, and triage level) and a RETTS triage model.ResultsOf 4,546 patients (median age 75 [57, 84] years; 49% male), 32.4% had time-sensitive conditions, 12.5% met the SOFA criteria, and 7.4% experienced 30-day mortality. The median POC lactate level was 1.7 (1.2, 2.5) mmol/L. Patients with time-sensitive conditions had higher lactate levels (1.9 mmol/L) than those with non-time-sensitive conditions (1.6 mmol/L). The probability of a time-sensitive condition increased with increasing lactate level. The addition of POC lactate marginally enhanced the predictive models, with a 1.5% and 4% increase for the base and RETTS triage models, respectively. POC lactate level as a sole predictor showed chance-only level predictive performance.ConclusionsPrehospital POC lactate assessment provided limited additional predictive value in a general adult EMS population. However, it may be beneficial in specific patient subgroups, emphasizing the need for its judicious use in prehospital settings.

Deep Learning Phenotyping of Tricuspid Regurgitation for Automated High Throughput Assessment of Transthoracic Echocardiography.

Diagnosis of tricuspid regurgitation (TR) requires careful expert evaluation. This study developed an automated deep learning pipeline for assessing TR from transthoracic echocardiography. An automated deep learning workflow was developed using 47,312 studies (2,079,898 videos) from Cedars-Sinai Medical Center (CSMC) between 2011 and 2021. The pipeline was tested on a temporally distinct test set of 2,462 studies (108,138 videos) obtained in 2022 at CSMC and a geographically distinct cohort of 5,549 studies (278,377 videos) from Stanford Healthcare (SHC). In the CSMC test dataset, the view classifier demonstrated an AUC of 1.000 (0.999 - 1.000) and identified at least one A4C video with colour Doppler across the tricuspid valve in 2,410 of 2,462 studies with a sensitivity of 0.975 (0.968-0.982) and a specificity of 1.000 (1.00-1.000). In the CSMC test cohort, moderate-or-severe TR was detected with an AUC of 0.928 (0.913 - 0.943) and severe TR was detected with an AUC of 0.956 (0.940 - 0.969). In the SHC cohort, the view classifier correctly identified at least one TR colour Doppler video in 5,268 of the 5,549 studies, resulting in an AUC of 0.999 (0.998 - 0.999), a sensitivity of 0.949 (0.944 - 0.955) and specificity of 0.999 (0.999 - 0.999). The AI model detected moderate-or-severe TR with an AUC of 0.951 (0.938 - 0.962) and severe TR with an AUC of 0.980 (0.966 - 0.988). We developed an automated pipeline to identify clinically significant TR with excellent performance. This approach carries potential for automated TR detection and stratification for surveillance and screening. Can an automated deep learning model assess tricuspid regurgitation severity from echocardiography? We developed and validated an automated tricuspid regurgitation detection algorithm pipeline across two healthcare systems with high volume echocardiography labs. The algorithm correctly identifies apical-4-chamber view videos with colour Doppler across the tricuspid valve and grades clinically significant TR with strong agreement to expert clinical readers. A deep learning pipeline could automate TR screening, facilitating reproducible accurate assessment of TR severity, allowing rapid triage or re-review and expand access in low-resource or primary care settings.

Diagnosis of acute aortic syndromes with ultrasound and d-dimer: the PROFUNDUS study

BackgroundIn patients complaining common symptoms such as chest/abdominal/back pain or syncope, acute aortic syndromes (AAS) are rare underlying causes. AAS diagnosis requires urgent advanced aortic imaging (AAI), mostly computed tomography angiography. However, patient selection for AAI poses conflicting risks of misdiagnosis and overtesting. ObjectivesWe assessed the safety and efficiency of a diagnostic protocol integrating clinical data with point-of-care ultrasound (POCUS) and d-dimer (single/age-adjusted cutoff), to select patients for AAI. MethodsThis prospective study involved 12 Emergency Departments from 5 countries. POCUS findings were integrated with a guideline-compliant clinical score, to define the integrated pre-test probability (iPTP) of AAS. If iPTP was high, urgent AAI was requested. If iPTP was low and d-dimer was negative, AAS was ruled out. Patients were followed for 30 days, to adjudicate outcomes. ResultsWithin 1979 enrolled patients, 176 (9 %) had an AAS. POCUS led to net reclassification improvement of 20 % (24 %/-4 % for events/non-events, P < 0.001) over clinical score alone. Median time to AAS diagnosis was 60 min if POCUS was positive vs 118 if negative (P = 0.042). Within 941 patients satisfying rule-out criteria, the 30-day incidence of AAS was 0 % (95 % CI, 0–0.41 %); without POCUS, 2 AAS were potentially missed. Protocol rule-out efficiency was 48 % (95 % CI, 46–50 %) and AAI was averted in 41 % of patients. Using age-adjusted d-dimer, rule-out efficiency was 54 % (difference 6 %, 95 % CI, 4–9 %, vs standard cutoff). ConclusionsThe integrated algorithm allowed rapid triage of high-probability patients, while providing safe and efficient rule-out of AAS. Age-adjusted d-dimer maximized efficiency.CLINICAL TRIAL REGISTRATION: Clinicaltrials.gov, NCT04430400

Machine learning based prediction models for analyzing risk factors in patients with acute abdominal pain: a retrospective study.

Acute abdominal pain (AAP) is a common symptom presented in the emergency department (ED), and it is crucial to have objective and accurate triage. This study aims to develop a machine learning-based prediction model for AAP triage. The goal is to identify triage indicators for critically ill patients and ensure the prompt availability of diagnostic and treatment resources. In this study, we conducted a retrospective analysis of the medical records of patients admitted to the ED of Wuhan Puren Hospital with acute abdominal pain in 2019. To identify high-risk factors, univariate and multivariate logistic regression analyses were used with thirty-one predictor variables. Evaluation of eight machine learning triage prediction models was conducted using both test and validation cohorts to optimize the AAP triage prediction model. Eleven clinical indicators with statistical significance (p < 0.05) were identified, and they were found to be associated with the severity of acute abdominal pain. Among the eight machine learning models constructed from the training and test cohorts, the model based on the artificial neural network (ANN) demonstrated the best performance, achieving an accuracy of 0.9792 and an area under the curve (AUC) of 0.9972. Further optimization results indicate that the AUC value of the ANN model could reach 0.9832 by incorporating only seven variables: history of diabetes, history of stroke, pulse, blood pressure, pale appearance, bowel sounds, and location of the pain. The ANN model is the most effective in predicting the triage of AAP. Furthermore, when only seven variables are considered, including history of diabetes, etc., the model still shows good predictive performance. This is helpful for the rapid clinical triage of AAP patients and the allocation of medical resources.

Bayesian modeling framework for optimizing pre-hospital stroke triage decisions

Ischemic stroke is responsible for significant morbidity and mortality in the United States and worldwide. Stroke treatment optimization requires emergency medical personnel to make rapid triage decisions concerning destination hospitals that may differ in their ability to provide highly time-sensitive pharmaceutical and surgical interventions. These decisions are particularly crucial in rural areas, where transport decisions can have a large impact on treatment times – often involving a trade-off between delay in pharmaceutical therapy or a delay in endovascular thrombectomy. In this work, we explore a Bayesian modeling framework to address this decision-making process, showing how these techniques may be used to fully account for diagnostic and therapeutic uncertainty. We demonstrate how these techniques can contextualize triage decision at a fine-grained spatial scale. We further show the application of this modeling approach in the US State of Iowa, using data from the Virtual International Stroke Trials Archive (VISTA), and describe potential next steps for improved triage. ABBREVIATION LVO: large vessel occlusion; non-LVO, non-large vessel occlusion; IVT: intravenous tissue plasminogen activator; EVT: endovascular thrombectomy; CSC: comprehensive stroke centers; PSC: primary stroke centers; DS: drip and ship; MS, mothership; EMS: Emergency Medical Service; BGLM: Bayesian Generalized Linear Model; BGAM: Bayesian Generalized Additive Model; BART: Bayesian Additive Regression Trees; VISTA: Virtual International Stroke Trials Archive; NIHSS: National Institute of Health Stroke Severity Scale; ASPECTS: Alberta Stroke Programme Early CT Score; mRS, modified Rankin score; ROCAUC: Area under the receiver operating characteristic curve; ELPD: Expected Log pointwise Predictive Density; SE: Standard Error; ICA: Internal Carotid Artery; M1: Middle Cerebral Artery segment 1; M2: Middle Cerebral Artery segment 2; TIA: Transient Ischemic Attack; Cr-I: Credible Intervals; LKW: Last Known Well

Rapid recognition and optimal management of hemophilia in the emergency department: A quality improvement project.

This study aimed to assess the effectiveness of a continuous quality improvement initiative at the University of Florida Health Physicians practice in reducing the time to administer factor replacement therapy (FRT) for hemophilia patients presenting with bleeding in the emergency department (ED). The study, a quasi-experimental, interventional design, was conducted between January 2020 and January 2023. The intervention, implemented in September 2021, involved training ED physicians, creating a specialized medication order set within the electronic health record (EHR), and a rapid triage system. The effectiveness was measured by comparing the time from ED arrival to factor administration before and after the intervention and benchmarking it against the National Bleeding Disorders Foundation's Medical and Scientific Advisory Council (MASAC)-recommended 1-hour timeline for factor administration. An interrupted time series (ITS) analysis with a generalized least squares model assessed the intervention's impact. A total of 43 ED visits (22 pre-intervention and 21 post-intervention) were recorded. Post-intervention, the average time from ED arrival to factor administration decreased from 5.63 to 3.15hours. There was no significant increase (27%vs. 29%) in the patients receiving factor within 1-hour of ED arrival. The ITS analysis predicted a 20-hour reduction in the average quarterly time to administer factor by the end of the study, an 84% decrease. The quality improvement program decreased the time to administer FRT for patients with hemophilia in the ED. However, the majority of patients did not achieve the 1-hour MASAC-recommended timeline for factor administration after ED arrival.

ADOPTERs of Innovation in a Crisis: The History of Vera Gedroits, Kanehiro Takaki and the Russo-Japanese War of 1904-1905.

The 1904-1905 Russo-Japanese War was the first "modern" conflict, using rapid-firing artillery and machine guns, fought over imperial ambitions in Korea and Manchuria. During the war, Princess Vera Gedroits pioneered early laparotomy for penetrating abdominal wounds with unprecedented success. Her techniques were then adopted by the Russian Society of Military Doctors. However, Allied forces took 10 years to adopt operative management of penetrating abdominal wounds over conservative management. Gedroits was later appointed in Kyiv as the world's first female Professor of Surgery. Kanehiro Takaki, a Japanese Naval surgeon, showed in 1884 a diet of barley, meat, milk, bread, and beans, rather than polished white rice, eliminated beriberi in the Japanese Navy. Despite this success, the Japanese Army failed to change the white rice rations until March 1905. During the 1904-1905 Russo-Japanese War, an estimated 250,000 Japanese soldiers developed beriberi, of whom 27,000 died. Japan's 1905 defeat of Russia sowed the seeds of discontent with Tsar Nicholas' rule, culminating in the 1917 Russian Revolution. Although the Russian Navy was destroyed, Japan ceded North Sakhalin Island to Russia in peace negotiations, and Russia seized Manchuria, South Sakhalin, and the Kuril Islands in 1945. We highlight the contributions of Gedroits and Takaki, 2 intellectual prodigies who respectively pioneered rapid triage and surgical management of trauma and a cure for beriberi. We aim to show how both these surgeons challenged entrenched dogma and the cultural and political zeitgeist, and risked their professional reputations and their lives in being ADOPTERs of innovation during a crisis.