Search Results (32)

Background/Objectives: Recent advances in artificial intelligence (AI) and machine learning (ML) enable targeted optimization of emergency department (ED) operations. We examine how reworking an ED’s vertical processing pathway (VPP) using AI- and ML-driven recommendations affected patient throughput. Methods: We trained a non-linear ML model using triage data from 49,350 ED encounters to generate a personalized risk score that predicted whether an incoming patient is suitable for vertical processing. This model was integrated into a stochastic patient flow framework using queueing theory to derive an optimized VPP design. The resulting protocol prioritized a vertical assessment for patients with Emergency Severity Index (ESI) scores of 4 and 5, as well as 3 when the chief complaints involved skin, urinary, or eye issues. In periods of ED saturation, our data-driven protocol suggested that any waiting room patient should become VPP eligible. We implemented this protocol during a 13-week prospective trial and evaluated its effect on ED performance using before-and-after data. Results: Implementation of the optimized VPP protocol reduced the average ED length of stay (LOS) by 10.75 min (4.15%). Adjusted analyses controlling for potential confounders during the study period estimated a LOS reduction between 7.5 and 11.9 min (2.89% and 4.60%, respectively). No adverse effects were observed in the quality metrics, including 72 h ED revisit or hospitalization rates. Conclusions: A personalized, data-driven VPP protocol, enabled by ML predictions, significantly improved the ED throughput while preserving care quality. Unlike standard fast-track systems, this approach adapts to ED saturation and patient acuity. The methodology is customizable to patient populations and ED operational characteristics, supporting personalized patient flow optimization across diverse emergency care settings. Full article

Background/Objective: Sepsis is a disease with a high mortality rate, which emphasizes the importance of developing tools for the early identification of high-risk patients and to initiate timely treatments to reduce mortality. The SIL score is a scale that uses the shock index and arterial lactate level to identify early on the patients that are at a high risk of in-hospital mortality due to sepsis. The purpose of this study was to validate the SIL score as a tool for estimating the probability of sepsis in-hospital mortality from the triage room in emergency departments. Additionally, the advantages of the SIL score were evaluated in comparison with NEWS and SOFA. Methods: All of the patients with suspected sepsis were prospectively recruited from the triage room in an emergency department. The SIL score, as well as other evaluation scales, were calculated for these patients. The sensitivity, specificity, predictive values, and areas under the curve (AUC) of each scale were assessed to predict mortality. Results: This study included 315 patients. The total mortality of the cohort was 20.4%. Of the total population, 35.5% were in septic shock. The SIL, NEWS, and SOFA scores had similar sensitivities, approximately 60%; however, a higher specificity was documented in the SIL score over the other scales (67%). The SIL score demonstrated superior discriminatory ability compared to the NEWS and SOFA scores (AUC = 0.754, p = 0.01). Conclusions: The SIL score proved to be a useful tool for predicting in-hospital mortality due to sepsis. Its discriminatory ability surpasses that of other evaluated scales. Therefore, the SIL score can be successfully implemented in the triage room of emergency departments to improve the identification and early management of patients with sepsis. Full article

Introduction: The incidence of venous thromboembolism is estimated to be around 3% of cancer patients. However, a majority of incidental pulmonary embolism (iPE) can be overlooked by radiologists in asymptomatic patients, performing CT scans for disease surveillance, which may significantly impact the patient’s health and management. Routine imaging in oncology is usually reviewed with delayed hours after the acquisition of images. Nevertheless, the advent of AI in radiology could reduce the risk of the diagnostic delay of iPE by an optimal triage immediately at the acquisition console. This study aimed to determine the accuracy rate of an AI algorithm (CINA-iPE) in detecting iPE and the duration until the management of cancer patients in our center, in addition to describing the characteristics of patients with a confirmed pulmonary embolism (PE). Materials and Methods: This is a retrospective analysis of the role of Avicenna’s CE-certified and FDA-cleared CINA-iPE algorithm in oncology patients treated at Gustave Roussy Cancer Campus. The results obtained from the AI algorithm were compared with the attending radiologist’s report and were analyzed by both a radiology resident and a senior radiologist. In case of any discordant results, the reason for this discrepancy was further investigated. The duration between the exact time of the CT scan and analysis was assessed, as well as the duration from the result’s report and the start of active management. Results: Out of 3047 patients, 104 alerts were detected for iPE (prevalence of 1.3%), while 2942 had negative findings. In total, 36 of the 104 patients had confirmed PE, while 68 alerts were false positives. Only one patient reported as negative by the AI tool was deemed to have a PE by the radiologist. The sensitivity and specificity of the AI model were 97.3% and 97.74%, while the PPV and NPV were 34.62% and 99.97%, respectively. Most causes of FP were artifacts (22 cases, 32.3%) and lymph nodes (11 cases, 16.2%). Seven patients experienced delayed diagnosis, requiring them to return to the ER for treatment after being sent home following their scan. The remaining patients received prompt care immediately after their testing, with a mean delay time of 8.13 h. Conclusions: The addition of an AI system for the detection of unsuspected PEs on chest CT scans in routine oncology care demonstrated a promising efficacy in comparison to human performance. Despite a low prevalence, the sensitivity and specificity of the AI tool reached 97.3% and 97.7%, respectively, with detection of all the reported clinical PEs, except one single case. This study describes the potential synergy between AI and radiologists for an optimal diagnosis of iPE in routine clinical cancer care. Clinical relevance statement: In the oncology field, iPEs are common, with an increased risk of morbidity when missed with a delayed diagnosis. With the assistance of a reliable AI tool, the radiologist can focus on the challenging analysis of oncology results while dealing with urgent diagnosis such as PE by sending the patient straight to the ER (Emergency Room) for prompt treatment. Full article

Large Language Models (LLMs) are becoming increasingly adopted in various industries worldwide. In particular, there is emerging research assessing the reliability of LLMs, such as ChatGPT, in performing triaging decisions in emergent settings. A unique aspect of emergency triaging is the process of trauma triaging. This process requires judicious consideration of mechanism of injury, severity of injury, patient stability, logistics of location and type of transport in order to ensure trauma patients have access to appropriate and timely trauma care. Current issues of overtriage and undertriage highlight the potential for the use of LLMs as a complementary tool to assist in more accurate triaging of the trauma patient. Despite this, there remains a gap in the literature surrounding the utility of LLMs in the trauma triaging process. This narrative review explores the current evidence for the potential for implementation of LLMs in trauma triaging. Overall, the literature highlights multifaceted applications of LLMs, especially in emergency trauma settings, albeit with clear limitations and ethical considerations, such as artificial hallucinations, biased outputs and data privacy issues. There remains room for more rigorous research into refining the consistency and capabilities of LLMs, ensuring their effective integration in real-world trauma triaging to improve patient outcomes and resource utilisation. Full article

This study was designed to examine the changes in emergency room visits in otolaryngology, head and neck surgery, during the COVID-19 pandemic. The study included 11,277 patients who presented to a tertiary care hospital (ER) and an emergency practice (EP) during on-call hours in the first half of 2018, 2019, and 2020. The epidemiologic parameters, diagnoses, and level of urgency were recorded using a four-step scale. A comparison was made between the pre-pandemic years and 2020. The findings revealed a significant decrease in the frequency of ER visits in the second quarter of 2020 compared to 2019 (ER: 30.8%, EP: 37.8%), mainly due to the fact that there were significantly fewer patients, with low levels of urgency. Certain diagnoses, such as epistaxis (−3.0%) and globus sensation (−3.2%), were made at similar frequencies to 2019, while inflammatory diseases like skin infections (−51.2%), tonsillitis (−55.6%), sinusitis (−59%), and otitis media (−70.4%) showed a significant reduction. The study concludes that patients with a low triage level were less likely to visit the ER during the early stages of the pandemic, but some diagnoses were still observed at comparable rates. This suggests a disparity in perception between patients and ER staff regarding urgency. Many of the issues discussed were also emphasized in the 2024 proposal by the German Ministry of Health to reform emergency care in Germany. Full article

Background: The underutilization of primary care services is a possible factor influencing inappropriate emergency service presentations. The objective of this study was to evaluate the proportion and characteristics of patients inappropriately accessing emergency room services from the perspective of primary care underutilization. Methods: This cross-sectional study included patients who visited the emergency room of a County Hospital, initially triaged with green, blue, or white codes, during a 2-week period in May 2017. Two primary care physicians performed a structured analysis to correlate the initial diagnosis in the emergency room with the final diagnosis to establish whether the patient’s medical complaints could have been resolved in primary care. Results: A total of 1269 adult patients were included in this study. In total, the medical problems of 71.7% of patients could have been resolved by a primary care physician using clinical skills, extended resources, or other ambulatory care and out-of-hours services. Conclusions: Low awareness of out-of-hours centers and a lack of resources for delivering more complex services in primary care can lead to inappropriate presentations to the emergency services. Future research on this topic needs to be conducted at the national level. Full article

Prehospital field triage often fails to accurately identify the need for emergent surgical or non-surgical procedures, resulting in inefficient resource utilization and increased costs. This study aimed to analyze prehospital factors associated with the need for emergent procedures (such as surgery or interventional angiography) within 6 h of hospital admission. Additionally, our goal was to develop a prehospital triage tool capable of estimating the likelihood of requiring an emergent procedure following hospital admission. We conducted a retrospective observational study, analyzing both prehospital and in-hospital data obtained from the Lombardy Trauma Registry. We conducted a multivariable logistic regression analysis to identify independent predictors of emergency procedures within the first 6 h from admission. Subsequently, we developed and internally validated a triage score composed of factors associated with the probability of requiring an emergency procedure. The study included a total of 3985 patients, among whom 295 (7.4%) required an emergent procedure within 6 h. Age, penetrating injury, downfall, cardiac arrest, poor neurological status, endotracheal intubation, systolic pressure, diastolic pressure, shock index, respiratory rate and tachycardia were identified as predictors of requiring an emergency procedure. A triage score generated from these predictors showed a good predictive power (AUC of the ROC curve: 0.81) to identify patients requiring an emergent surgical or non-surgical procedure within 6 h from hospital admission. The proposed triage score might contribute to predicting the need for immediate resource availability in trauma patients. Full article

Background: Accurate and efficient triage is crucial for prioritizing care and managing resources in emergency rooms. This study investigates the effectiveness of ChatGPT, an advanced artificial intelligence system, in assisting health providers with decision-making for patients presenting with metastatic prostate cancer, focusing on the potential to improve both patient outcomes and resource allocation. Methods: Clinical data from patients with metastatic prostate cancer who presented to the emergency room between 1 May 2022 and 30 April 2023 were retrospectively collected. The primary outcome was the sensitivity and specificity of ChatGPT in determining whether a patient required admission or discharge. The secondary outcomes included the agreement between ChatGPT and emergency medicine physicians, the comprehensiveness of diagnoses, the accuracy of treatment plans proposed by both parties, and the length of medical decision making. Results: Of the 147 patients screened, 56 met the inclusion criteria. ChatGPT had a sensitivity of 95.7% in determining admission and a specificity of 18.2% in discharging patients. In 87.5% of cases, ChatGPT made the same primary diagnoses as physicians, with more accurate terminology use (42.9% vs. 21.4%, p = 0.02) and more comprehensive diagnostic lists (median number of diagnoses: 3 vs. 2, p < 0.001). Emergency Severity Index scores calculated by ChatGPT were not associated with admission (p = 0.12), hospital stay length (p = 0.91) or ICU admission (p = 0.54). Despite shorter mean word count (169 ± 66 vs. 272 ± 105, p < 0.001), ChatGPT was more likely to give additional treatment recommendations than physicians (94.3% vs. 73.5%, p < 0.001). Conclusions: Our hypothesis-generating data demonstrated that ChatGPT is associated with a high sensitivity in determining the admission of patients with metastatic prostate cancer in the emergency room. It also provides accurate and comprehensive diagnoses. These findings suggest that ChatGPT has the potential to assist health providers in improving patient triage in emergency settings, and may enhance both efficiency and quality of care provided by the physicians. Full article

(1) Background: Patients who deserve intensive care unit (ICU) admission may be denied due to a lack of resources, complicating ICU triage decisions for intensive care unit (ICU) clinicians. Among the resources that may be unavailable are trained personnel and monitored beds. In South Africa, the distribution of healthcare resources is reflected in the availability of ICU beds, with more ICU beds available in more affluent areas. Data on ICU refusal rates, reasons for refusal, patient characteristics, and outcomes are scarce in resource-constrained rural settings. Hence, this study sheds light on the ICU refusal rates, reasons for refusal, characteristics, and outcomes of refused patients at NMAH. (2) Methods: This was a three-month retrospective cross-sectional record review of refused and admitted patients from January to March 2022. COVID-19 patients and those younger than 13 years old were excluded. Refusal rates, reasons for refusal, characteristics, and outcomes of refused patients were analysed quantitatively using SPSS VS 20 software. Reasons for refusal were categorised as “too well”, “too sick”, and “suitable for admission but no resources”. (3) Results: A total of 135 patients were discussed for ICU admission at NMAH during the study period; 73 (54.07%) were refused admission, and 62 (45.92%) were admitted. Being considered too sick to benefit from ICU was the most common reason for refusal (53.23%). Too well and no resources contributed 27.42% and 19.35%, respectively. Patients with poor functional status, comorbidities, medical diagnoses, and those referred from the ward or accident and emergency unit rather than the operating room were more likely to be refused ICU admission. Refused patients had a seven-day mortality rate of 47%. (4) Conclusions and recommendations: The study found an unmet need for critical care services at our institution, as well as a need for tools to help clinicians make objective triage decisions for critically ill patients. Therefore, the study suggests a need to improve the quality of services provided outside of the ICU, particularly for patients who were refused ICU admission, to improve their outcomes. Full article

Trauma is a major cause of mortality throughout the world. Traumatic pain—acute, sudden, or chronic—is defined as “an unpleasant sensory and emotional experience associated with actual or potential tissue damage”. Patients’ perceptions of pain assessment and management have become an important criterion and relevant outcome measure for healthcare institutions. Several studies show that 60–70% of ER patients experience pain, and more than half of them express a feeling of sorrow, which can be moderate or severe, at triage. The few studies that have analyzed how pain is assessed and managed in these departments agree that approximately 70% of patients receive no analgesia or receive it with remarkable delay. Specifically, less than half of the patients receive treatment for pain during admission and 60% of discharged patients have higher intensity pain than at admission. Trauma patients are also the ones who most commonly report low satisfaction with pain management. Associated with this lack of satisfaction, we can describe the poor use of tools for measuring and recording pain, poor communication among caregivers, inadequate training in pain assessment and management, and widespread misconceptions among nurses about the reliability of patients’ estimation of pain. The aim of this article is to review the scientific literature to explore the methodologies of pain management in trauma patients attending the emergency room and analyzing their weaknesses as a starting point to improve the approach to this, unfortunately too often, underestimated issue. A literature search was performed using the major databases to identify relevant studies in indexed scientific journals. The literature showed that the multimodal approach in trauma patients is the best approach to pain management. It is becoming increasingly crucial to manage the patient on multiple fronts. Drugs acting on different pathways can be administered together at lower doses, minimizing risks. Every emergency department must have staff trained in the assessment and immediate management of pain symptoms as this allows the reduction of mortality and morbidity and shortens hospital stays, contributing to early mobilization, reduced hospital costs, and enhanced patient satisfaction and quality of life. Full article

Background: In a pandemic situation such as the one of the COVID-19 pandemic, nosocomial transmissions attempted to be prevented by initially classifying them in triage. Therefore, emergency departments (EDs) installed isolation rooms at their entrance. Additionally, a system for pre-emptive quarantine at the triage stage was established nationwide for patients with COVID-19-related symptoms. Methods: Data were retrospectively collected from 28,609 patients who visited the regional emergency medical center of Yeungnam University Hospital in Daegu Metropolitan City in 2021. The study population was divided into experimental and control groups comprising patients with and without COVID-19-related symptoms, respectively. The difference in the percentage of patients visiting from outside the city was investigated between the two groups. The critically ill patient (CP) ratio was analyzed in the experimental group to verify the appropriateness of visiting a higher-level ED and was further divided into sub-regions to determine their reason for visiting an ED beyond their residential region. Results: Most lower-level EDs did not have isolation rooms. About 20.1% and 17.3% of patients in the experimental and control groups visited a higher-level ED with an isolation room beyond their residential region, respectively. The absence of an isolation room in the ED in their residential region was one reason for traveling beyond their residential region, with an odds ratio of 4.44 (95% confidence interval: 0.53–8.35). Conclusion: In the process of implementing the “pre-emptive quarantine” system, it was revealed that the cooperation of the lower-level EDs was not effective during the implementation of the “pre-emptive quarantine” system. Consequently, a higher number of patients with COVID-19-related symptoms had to locate an ED with an isolation room and travel a longer distance than general patients. The participation of more EDs is required. Full article

Emergency department (ED) overcrowding is a global health issue that is associated with poor quality of care and affects the timeliness of treatment initiation. The purpose of this systematic review is to assess the association between overcrowding and delay in treatment. A systematic review was conducted using four databases (CINAHL, PubMed, Scopus, Cochrane Library), following the preferred reporting items for systematic reviews and meta-analysis (PRISMA). A structured search was conducted to identify peer-reviewed articles aimed at assessing the relationship between overcrowding and delay in treatment, published between January 2000 and January 2021. Only studies that were conducted in the ED settings were included, and that includes both triage and observation rooms. The studies were appraised using two quality appraisal tools including the critical appraisal skills programme (CASP) for cohort studies and the Joanna Briggs Institute (JBI) checklist tool for cross-sectional studies. A total of 567 studies screened, and 10 met the inclusion criteria. Of these studies, 8 were cohorts and 2 were cross-sectionals. The majority reported that overcrowding is associated with a delay in the initiation of antibiotics for patients with sepsis and pneumonia. The review identified that overcrowding might impact time-to-treatment and, thus, the quality of care delivered to the patient. However, further research aimed at finding feasible solutions to overcrowding is encouraged. Full article

The COVID-19 pandemic has become increasingly worse worldwide since it was discovered in China in late December 2019. Easy contact transmission between people and a low to moderate mortality rate may cause failure in medical health services if there is no proper personal protective equipment for personnel. During the pandemic, patients with acute ischemic stroke with large-vessel occlusion who required immediate treatment through mechanical thrombectomy (MT) were still being sent to the emergency room. Knowing how to maintain effective treatment standards has become our concern. We used a retrospective, single-center study to select COVID-19 (-) patients with acute ischemic stroke undergoing mechanical thrombectomy during the years 2020–2021. Patients with acute ischemic stroke with large-vessel occlusion received mechanical thrombectomy were compared with patients admitted from December 2020 to May 2021 (the pre-COVID-19 group) and those from June 2021 to November 2021 (the during COVID-19 group). Furthermore, the time disparity of mechanical thrombectomy was compared between these two groups. Of patients confirmed with acute ischemic stroke (AIS) with large-vessel occlusion (LVO) during the study period, 62 were included. Compared with the pre-COVID-19 group (34 patients; median age, 70.5 years), the during COVID-19 group (28 patients; median age, 71.5 years) showed no major median time difference in door-to-computed-tomography-angiography (CTA) time (19.0 min vs. 20.0 min, p = 0.398) and no major median time difference in door-to-groin-puncture time (118.0 min vs. 109.0 min, p = 0.281). In our study, with a prepared protocol for the pandemic having been established in the healthcare system, we could see no difference between the pre-pandemic and during-pandemic time periods when using mechanical thrombectomy to treat COVID-19 (-) patients of AIS with LVO. By means of a quick-PCR test during triage, there was no time delay to perform MT or any lowering of safety protocol for workers in the healthcare system. Full article

Beginning in December 2019, the world faced a critical new public health stressor with the emergence of SARS-CoV-2. Its spread was extraordinarily rapid, and in a matter of weeks countries across the world were affected, notably in their ability to manage health care needs. While many sectors of public structures were impacted by the pandemic, it particularly highlighted shortcomings in medical care infrastructures around the world that underscored the need to reorganize medical systems, as they were vastly unprepared and ill-equipped to manage a pandemic and simultaneously provide general and specialized medical care. This paper presents modalities in approaches to the pandemic by various countries, and the triaged reorganization of medical sections not considered first-line in the pandemic that was in many cases transformed into wards for treating COVID-19 cases. As new viruses and structural variants emerge, it is important to find solutions to streamline medical care in hospitals, which includes the expansion of digital network medicine (i.e., telemedicine and mobile health apps) for patients to continue to receive appropriate care without risking exposure to contagions. Mobile health app development continues to evolve with specialized diagnostics capabilities via external attachments that can provide rapid information sharing between patients and care providers while eliminating the need for office visits. Telemedicine, still in the early stages of adoption, especially in the developing world, can ensure access to medical information and contact with care providers, with the potential to release emergency rooms from excessive cases, and offer multidisciplinary access for patients and care providers that can also be a means to avoid contact during a pandemic. As this pandemic illustrated, an overhaul to streamline health care is essential, and a move towards greater use of mobile health and telemedicine will greatly benefit public health to control the spread of new variants and future outbreaks. Full article

Traumatic brain injury (TBI) remains a critical public health challenge. Although studies have found several prognostic factors for TBI, a useful early predictive tool for mortality has yet to be developed in the triage of the emergency room. This study aimed to use machine learning algorithms of artificial intelligence (AI) to develop predictive models for TBI patients in the emergency room triage. We retrospectively enrolled 18,249 adult TBI patients in the electronic medical records of three hospitals of Chi Mei Medical Group from January 2010 to December 2019, and undertook the 12 potentially predictive feature variables for predicting mortality during hospitalization. Six machine learning algorithms including logistical regression (LR) random forest (RF), support vector machines (SVM), LightGBM, XGBoost, and multilayer perceptron (MLP) were used to build the predictive model. The results showed that all six predictive models had high AUC from 0.851 to 0.925. Among these models, the LR-based model was the best model for mortality risk prediction with the highest AUC of 0.925; thus, we integrated the best model into the existed hospital information system for assisting clinical decision-making. These results revealed that the LR-based model was the best model to predict the mortality risk in patients with TBI in the emergency room. Since the developed prediction system can easily obtain the 12 feature variables during the initial triage, it can provide quick and early mortality prediction to clinicians for guiding deciding further treatment as well as helping explain the patient’s condition to family members. Full article