Clinicians' attitudes towards supplemental oxygen for trauma patients - A survey.

INTRODUCTION: The Advanced Trauma Life Support guidelines (ATLS; 2018, 10th ed.) recommend an early and liberal supplemental oxygen for all severely injured trauma patients to prevent hypoxaemia. As of 2024, these guidelines remain the most current. This may lead to hyperoxaemia, which has been associated with increased mortality and respiratory complications. We aimed to investigate the attitudes among clinicians, defined as physicians and prehospital personnel, towards the use of supplemental oxygen in trauma cases. MATERIALS AND METHODS: A European, web-based, cross-sectional survey was conducted consisting of 23 questions. The primary outcome was the question: "In your opinion, should all severely injured trauma patients always be given supplemental oxygen, regardless of arterial oxygen saturation measured by pulse oximetry?". RESULTS: The survey was answered by 707 respondents, which corresponded to a response rate of 52 %. The respondents were predominantly male (76 %), with the largest representation from Denmark (82 %), and primarily educated as physicians (62 %). A majority of respondents (73 % [95 % CI: 70 to 76 %]) did not support that supplemental oxygen should always be provided to all severely injured trauma patients without consideration of their arterial oxygen saturation as measured by pulse oximetry (SpO2), with no significant difference between physicians and non-physicians (p = 0.08). Based on the respondents' preferred dosages, the median initial administered dosage of supplemental oxygen for spontaneously breathing trauma patients with a normal SpO2 in the first few hours after trauma was 0 (interquartile range [IQR] 0-3) litres per minute, with 58 % of respondents opting not to provide any supplemental oxygen. The lowest acceptable SpO2 goal in the first few hours after trauma was 94 % (IQR 92-95). In clinical scenarios with TBI, higher dosage of supplemental oxygen and fraction of inspired oxygen (FiO2) were preferred, as well as targeting partial pressure of oxygen in arterial blood as opposed to adjusting the FiO2 directly, compared to no TBI. CONCLUSION: Almost three out of four clinicians did not support the administration of supplemental oxygen to all severely injured trauma patients, regardless of SpO2. This corresponds to a more restrictive approach than recommended in the current ATLS (2018, 10th ed.) guidelines.

Risk factors for wrong-patient medication orders in the emergency department.

Objectives: This paper investigates the risk factors for wrong-patient medication orders in an emergency department (ED) by studying intercepted ordering errors identified by the "retract-and-reorder" (RaR) metric (orders that were retracted and reordered for a different patient by the same provider within 10 min). Materials and Methods: Medication ordering data of an academic ED were analyzed to identify RaR events. The association of RaR events with similarity of patient names and birthdates, matching sex, age difference, the month, weekday, and hour of the RaR event, the elapsed hours since ED shift start, and the proximity of exam rooms in the electronic medical record (EMR) dashboard's layout was evaluated. Results: Over 5 years (2017-2021), 1031 RaR events were identified among a total of 561 099 medication orders leading to a proportional incidence of 184 per 100 000 ED orders (95% CI: 172; 195). RaR orders were less likely to be performed by nurses compared to physicians (OR 0.54 [0.47; 0.61], P < .001). Furthermore, RaR pairs were more likely to have the same sex (OR 1.26 [95% CI 1.10; 1.43], P = .001) and the proximity of the exam rooms was closer (-0.62 [95% CI -0.77; -0.47], P = .001) compared to control pairs. Patients' names, birthdates, age, and the other factors showed no significant association (P > .005). Discussion and Conclusion: This study found no significant influence from factors such as similarity of patient names, age, or birthdates. However, the proximity of exam rooms in the user interface of the EMR as well as patients' same sex emerged as risk factors.

Using Resuscitative Endovascular Balloon Occlusion of the Aorta (REBOA) as a Rescue Strategy in Severe Postpartum Hemorrhage: A Case Report.

Postpartum hemorrhage (PPH) is a leading cause of maternal morbidity and mortality. Routine treatment of PPH includes uterotonics, tranexamic acid, curettage, uterine (balloon) tamponade, compression sutures, uterine artery ligation, and, if available, transcatheter arterial embolization (TAE). In cases of severe PPH refractory to standard medical and surgical management, hysterectomy is usually the ultima ratio, and is equally associated with a higher rate of complications. In addition, this sudden loss of fertility, especially in young women, can be devastating. Here, we report a case of a 29-year-old woman who suffered from severe PPH with a blood loss > 1500 mL and hemodynamic instability after delivery of her first baby at a smaller hospital. She was consequently successfully treated with resuscitative endovascular balloon occlusion of the aorta (REBOA) by first placing a balloon catheter into the infra-renal aorta and subsequent TAE after failure of all other available treatment options prior to hysterectomy. TAE has been suggested in PPH treatment to avoid hysterectomies and thus to preserve patients' reproductive function. If hemodynamic stabilization cannot be achieved with mass transfusion, REBOA seems to be an effective rescue strategy with which to achieve hemodynamic stabilization and gain additional time for embolization. Although REBOA is already recommended in several PPH guidelines, this approach seems relatively unknown in German-speaking countries.

Hyperoxaemia in acute trauma is common and associated with a longer hospital stay: a multicentre retrospective cohort study.

BACKGROUND: Trauma poses a significant global health challenge. Despite advancements in the management of severely injured patients, (poly)trauma continues to be a primary contributor to morbidity and mortality worldwide. In the context of trauma resuscitation, supplemental oxygen is commonly administered generously as suggested by guidelines. Yet, it remains uncertain whether the trauma population might derive advantages from a more conservative approach to supplemental oxygen. METHODS: In this retrospective cohort study from two Swiss trauma centers, severely injured adult (> 16 years) trauma patients with an Injury Severity Score (ISS) ≥ 16 were divided into four groups according to the first blood gas analysis taken: hypoxaemia (PaO2 < 10.7 kPa/80 mmHg), normoxaemia (PaO2 10.7-16.0 kPa/80-120 mmHg), which served as reference, moderate hyperoxaemia (PaO2 > 16.0-40 kPa/120-300 mmHg) and severe hyperoxaemia (PaO2 > 40 kPa/300 mmHg). The primary outcome was 28-day mortality. Length of hospital stay (LOS) and length of intensive care unit stay (LOS-ICU) were analyzed as secondary outcomes. RESULTS: Of 1,189 trauma patients, 41.3% had hyperoxaemia (18.8% with severe hyperoxaemia) and 19.3% had hypoxaemia. No difference was found for 28-day mortality (hypoxaemia: 15.7%, normoxaemia: 14.1%, hyperoxaemia: 13.8%, severe hyperoxaemia: 16.0%, p = 0.846). Patients with severe hyperoxaemia had a significant prolonged LOS (median 12.5 [IQR 7-18.5] days vs. 10 [7-17], p = 0.040) and extended LOS-ICU (3.8 [1.8-9] vs. 2 [1-5] days, p = 0.149) compared to normoxaemic patients. In multivariable analysis, oxygen group was not associated with the primary outcome 28-day mortality or LOS-ICU. Severe hyperoxaemia patients had a tendency towards longer hospital stay (adjusted coefficient 2.23 days [95% CI: - 0.32; 4.79], p = 0.087). CONCLUSION: Hyperoxaemia was not associated with an increased 28-day mortality when compared to normoxaemia. However, both moderate and severe hyperoxaemia is frequently observed in trauma patients, and the presence of severe hyperoxaemia showed a tendency with extended hospital stay compared to normoxaemia patients. Robust randomized controlled trials are imperative to thoroughly evaluate the potential correlation between hyperoxaemia and outcomes in trauma patients . Trial Registration Retrospectively registered.

Effects of interacting with a large language model compared with a human coach on the clinical diagnostic process and outcomes among fourth-year medical students: study protocol for a prospective, randomised experiment using patient vignettes.

INTRODUCTION: Versatile large language models (LLMs) have the potential to augment diagnostic decision-making by assisting diagnosticians, thanks to their ability to engage in open-ended, natural conversations and their comprehensive knowledge access. Yet the novelty of LLMs in diagnostic decision-making introduces uncertainties regarding their impact. Clinicians unfamiliar with the use of LLMs in their professional context may rely on general attitudes towards LLMs more broadly, potentially hindering thoughtful use and critical evaluation of their input, leading to either over-reliance and lack of critical thinking or an unwillingness to use LLMs as diagnostic aids. To address these concerns, this study examines the influence on the diagnostic process and outcomes of interacting with an LLM compared with a human coach, and of prior training vs no training for interacting with either of these 'coaches'. Our findings aim to illuminate the potential benefits and risks of employing artificial intelligence (AI) in diagnostic decision-making. METHODS AND ANALYSIS: We are conducting a prospective, randomised experiment with N=158 fourth-year medical students from Charité Medical School, Berlin, Germany. Participants are asked to diagnose patient vignettes after being assigned to either a human coach or ChatGPT and after either training or no training (both between-subject factors). We are specifically collecting data on the effects of using either of these 'coaches' and of additional training on information search, number of hypotheses entertained, diagnostic accuracy and confidence. Statistical methods will include linear mixed effects models. Exploratory analyses of the interaction patterns and attitudes towards AI will also generate more generalisable knowledge about the role of AI in medicine. ETHICS AND DISSEMINATION: The Bern Cantonal Ethics Committee considered the study exempt from full ethical review (BASEC No: Req-2023-01396). All methods will be conducted in accordance with relevant guidelines and regulations. Participation is voluntary and informed consent will be obtained. Results will be published in peer-reviewed scientific medical journals. Authorship will be determined according to the International Committee of Medical Journal Editors guidelines.

Virtual reality simulation to enhance advanced trauma life support trainings - a randomized controlled trial.

BACKGROUND: Advanced Trauma Life Support (ATLS) is the gold standard of initial assessment of trauma patients and therefore a widely used training program for medical professionals. Practical application of the knowledge taught can be challenging for medical students and inexperienced clinicians. Simulation-based training, including virtual reality (VR), has proven to be a valuable adjunct to real-world experiences in trauma education. Previous studies have demonstrated the effectiveness of VR simulations for surgical and technical skills training. However, there is limited evidence on VR simulation training specifically for trauma education, particularly within the ATLS curriculum. The purpose of this pilot study is to evaluate the feasibility, effectiveness, and acceptance of using a fully immersive VR trauma simulation to prepare medical students for the ATLS course. METHODS: This was a prospective randomised controlled pilot study on a convenience sample of advanced medical students (n = 56; intervention group with adjunct training using a commercially available semi-automated trauma VR simulation, n = 28, vs control group, n = 28) taking part in the ATLS course of the Military Physician Officer School. Feasibility was assessed by evaluating factors related to technical factors of the VR training (e.g. rate of interruptions and premature termination). Objective and subjective effectiveness was assessed using confidence ratings at four pre-specified points in the curriculum, validated surveys, clinical scenario scores, multiple choice knowledge tests, and ATLS final clinical scenario and course pass rates. Acceptance was measured using validated instruments to assess variables of media use (Technology acceptance, usability, presence and immersion, workload, and user satisfaction). RESULTS: The feasibility assessment demonstrated that only one premature termination occurred and that all remaining participants in the intervention group correctly stabilised the patient. No significant differences between the two groups in terms of objective effectiveness were observed (p = 0.832 and p = 0.237 for the pretest and final knowledge test, respectively; p = 0.485 for the pass rates for the final clinical scenario on the first attempt; all participants passed the ATLS course). In terms of subjective effectiveness, the authors found significantly improved confidence post-VR intervention (p < .001) in providing emergency care using the ATLS principles. Perceived usefulness in the TEI was stated with a mean of 4 (SD 0.8; range 0-5). Overall acceptance and usability of the VR simulation was rated as positive (System Usability Scale total score mean 79.4 (SD 11.3, range 0-100). CONCLUSIONS: The findings of this prospective pilot study indicate the potential of using VR trauma simulations as a feasible and acceptable supplementary tool for the ATLS training course. Where objective effectiveness regarding test and scenario scores remained unchanged, subjective effectiveness demonstrated improvement. Future research should focus on identifying specific scenarios and domains where VR can outperform or enhance traditional learning methods in trauma simulation.

Enhancing patient safety: detection of in-hospital hazards and effect of training on detection (by training in a low-fidelity simulation Room of Improvement based on hospital-specific CIRS cases).

IMPORTANCE: Adequate situational awareness in patient care increases patient safety and quality of care. To improve situational awareness, an innovative, low-fidelity simulation method referred to as Room of Improvement, has proven effective in various clinical settings. OBJECTIVE: To investigate the impact after 3 months of Room of Improvement training on the ability to detect patient safety hazards during an intensive care unit shift handover, based on critical incident reporting system (CIRS) cases reported in the same hospital. METHODS: In this educational intervention, 130 healthcare professionals observed safety hazards in a Room of Improvement in a 2 (time 1 vs time 2)×2 (alone vs in a team) factorial design. The hazards were divided into immediately critical and non-critical. RESULTS: The results of 130 participants were included in the analysis. At time 1, no statistically significant differences were found between individuals and teams, either overall or for non-critical errors. At time 2, there was an increase in the detection rate of all implemented errors for teams compared with time 1, but not for individuals. The detection rate for critical errors was higher than for non-critical errors at both time points, with individual and group results at time 2 not significantly different from those at time 1. An increase in the perception of safety culture was found in the pre-post test for the questions whether the handling of errors is open and professional and whether errors are discussed in the team. DISCUSSION: Our results indicate a sustained learning effect after 12 weeks, with collaboration in teams leading to a significantly better outcome. The training improved the actual error detection rates, and participants reported improved handling and discussion of errors in their daily work. This indicates a subjectively improved safety culture among healthcare workers as a result of the situational awareness training in the Room of Improvement. As this method promotes a culture of safety, it is a promising tool for a well-functioning CIRS that closes the loop.

Do all Emergency Room Patients With Influenza-like Symptoms Need Blood Cultures? A Retrospective Cohort Study of 2 Annual Influenza Seasons.

In this retrospective cohort study, we evaluated risk factors for bacteremia in emergency department patients presenting with influenza-like symptoms during influenza epidemic seasons. In patients without fever, chronic heart or chronic liver disease, blood culture collection might be omitted.

Accuracy between prehospital and hospital diagnosis in helicopter emergency medical services and its consequences for trauma care.

PURPOSE: For optimal prehospital trauma care, it is essential to adequately recognize potential life-threatening injuries in order to correctly triage patients and to initiate life-saving measures. The aim of the present study was to determine the accuracy of prehospital diagnoses suspected by helicopter emergency medical services (HEMS). METHODS: This retrospective multicenter study included patients from the Swiss Trauma Registry with ISS ≥ 16 or AIS head ≥ 3 transported by Switzerland's largest HEMS and subsequently admitted to one of twelve Swiss trauma centers from 01/2020 to 12/2020. The primary outcome was the comparison of injuries suspected prehospital with the final diagnoses obtained at the hospital using the abbreviated injury scale (AIS) per body region. As secondary outcomes, prehospital interventions were compared to corresponding relevant diagnoses. RESULTS: Relevant head trauma was the most commonly injured body region and was identified in 96.3% (95% CI: 92.1%; 98.6%) of the cases prehospital. Relevant injuries to the chest, abdomen, and pelvis were also common but less often identified prehospital [62.7% (95% CI: 54.2%; 70.6%), 45.5% (95% CI: 30.4%; 61.2%), and 61.5% (95% CI: 44.6%; 76.6%)]. Overall, 7 of 95 (7.4%) patients with pneumothorax received a chest decompression and in 22 of 39 (56.4%) patients with an instable pelvic fracture a pelvic binder was applied prehospital. CONCLUSION: Approximately half of severe chest, abdominal, and pelvic diagnoses made in hospital went undetected in the challenging prehospital environment. This underlines the difficult circumstances faced by the rescue teams. Potentially life-saving interventions such as prehospital chest decompression and increased use of a pelvic binder were identified as potential improvements to prehospital care.

Contrast-enhanced point of care ultrasound for the evaluation of stable blunt abdominal trauma by the emergency physician: A prospective diagnostic study.

Objectives: Clinical examination alone cannot reliably rule out significant traumatic abdominal injury. Computed tomography (CT) has become the primary method for evaluating blunt abdominal trauma and clinicians rely heavily on it to rule out abdominal injury. Ultrasound examination may miss significant abdominal injury particularly in stable patients. The use of a contrast agent improves ultrasound sensitivity to visceral abdominal injuries. The objective of this diagnostic study is to compare bedside contrast enhanced ultrasound (CEUS) performed by emergency physicians to CT in hemodynamically stable adults for the assessment of blunt abdominal trauma and evaluate CEUS accuracy outcomes. Methods: Hemodynamically stable patients with blunt trauma were prospectively enrolled in the trauma bay. After initial evaluation, we included patients at risk of abdominal injury and for whom an abdominal CT was planned by the trauma leader. Ultrasonography was performed prospectively and at the bedside by the emergency physician followed by abdominal CT used as a reference standard. Results: Thirty-three patients were enrolled in the study; among them, 52% showed positive traumatic findings in abdominal CT scans, and 42% were diagnosed with solid organ lesions. Compared to CT, a focused abdominal sonography (FOCUS) examination, looking for free fluid or perirenal hematoma, showed limited performance for traumatic findings with a sensitivity of 65% (95% confidence interval [CI]: 38%-86%), a specificity of 75% (95% CI: 48%-93%), a negative likelihood ratio (NLR) of 0.47 (95% CI: 0.23-0.95), and a positive likelihood ratio (PLR) of 2.59 (95% CI: 1.03-6.48). When combining FOCUS with CEUS, the sensitivity of the sonography increased to 94% (95% CI: 71%-100%) with a specificity of 75% (95% CI: 48%-93%). The PLR was 3.76 (95% CI: 1.6-8.87) and the NLR was 0.08 (95% CI: 0.01-0.54). In our population, abdominal sonography with contrast failed to identify a single positive abdominal CT with a grade 1 kidney injury. Conclusions: A FOCUS examination shows limited sensitivity and specificity to detect positive abdominal CT in stable adults with abdominal trauma. With the addition of contrast and careful inspection of solid organs, abdominal sonography with contrast performed by the emergency physician improves the ability to rule out traumatic findings on abdominal CT. CEUS performed by emergency physicians may miss injuries, especially in the absence of free fluid, in cases of low-grade injuries, simultaneous injuries, or poor-quality examinations.

Supplementary value and diagnostic performance of computed tomography scout view in the detection of thoracolumbar spine injuries.

PURPOSE: Assessing the diagnostic performance and supplementary value of whole-body computed tomography scout view (SV) images in the detection of thoracolumbar spine injuries in early resuscitation phase and identifying frequent image quality confounders. METHODS: In this retrospective database analysis at a tertiary emergency center, three blinded senior experts independently assessed SV to detect thoracolumbar spine injuries. The findings were categorized according to the AO Spine classification system. Confounders impacting SV image quality were identified. The suspected injury level and severity, along with the confidence level, were indicated. Diagnostic performance was estimated using the caret package in R programming language. RESULTS: We assessed images of 199 patients, encompassing 1592 vertebrae (T10-L5), and identified 56 spinal injuries (3.5%). Among the 199 cases, 39 (19.6%) exhibited at least one injury in the thoracolumbar spine, with 12 (6.0%) of them displaying multiple spinal injuries. The pooled sensitivity, specificity, and accuracy were 47%, 99%, and 97%, respectively. All experts correctly identified the most severe injury of AO type C. The most common image confounders were medical equipment (44.6%), hand position (37.6%), and bowel gas (37.5%). CONCLUSION: SV examination holds potential as a valuable supplementary tool for thoracolumbar spinal injury detection when CT reconstructions are not yet available. Our data show high specificity and accuracy but moderate sensitivity. While not sufficient for standalone screening, reviewing SV images expedites spinal screening in mass casualty incidents. Addressing modifiable factors like medical equipment or hand positioning can enhance SV image quality and assessment.

[Medical extended reality in digital emergency medicine : From education to clinical application]. / Medical Extended Reality in der digitalen Notfallmedizin : Von der Ausbildung zur klinischen Anwendung.

BACKGROUND: Emergency medicine faces the challenge of providing optimal care with limited resources. Especially in rare but critical situations (high-acuity low occurrence [HALO] situations), sound expertise is essential. Previous training approaches are time-limited and resource-intensive. AIM OF THE WORK: Medical extended reality (MXR) offers promising solutions. This article gives insight into the different areas of MXR and shows the application of MXR in emergency medicine using the HALO-MXR concept as an example. RESULTS AND DISCUSSION: MXR encompasses augmented reality (AR), virtual reality (VR) and mixed reality (MR). AR overlays digital information on the real world, enhancing perception and enabling interactive elements. VR creates an artificial three-dimensional (3D) environment in which the user is immersed. MR combines real and virtual elements. MXR offers advantages such as location-independent learning, virtual mentoring and scalability. However, it cannot replace existing training formats, but should be embedded in an overall concept. The HALO-MXR concept at Inselspital Bern includes e­learning, simulation-based training in VR and on-site, and HALO-Assist support through augmented reality. HALO-Assist provides around-the-clock AR support for HALO procedures via audio and video communication as well as overlayed annotations, objects and flowcharts. CONCLUSION: The integration of MXR into emergency medicine promises more efficient use of resources and enhanced training opportunities. The HALO-MXR concept demonstrates how MXR effectively combines simulation-based training in VR and AR assist to enhance the application of HALO procedures.

The forgotten cohort-lessons learned from prehospital trauma death: a retrospective cohort study.

BACKGROUND: Trauma related deaths remain a relevant public health problem, in particular in the younger male population. A significant number of these deaths occur prehospitally without transfer to a hospital. These patients, sometimes termed "the forgotten cohort", are usually not included in clinical registries, resulting in a lack of information about prehospitally trauma deaths. The aim of the present study was to compare patients who died prehospital with those who sustained life-threatening injuries in order to analyze and potentially improve prehospital strategies. METHODS: This cohort study included all primary operations carried out by Switzerland's largest helicopter emergency medical service (HEMS) between January 1, 2011, and December 31, 2021. We included all adult trauma patients with life-threatening or fatal conditions. The outcome of this study is the vital status of the patient at the end of mission, i.e. fatal or life-threatening. Injury, rescue characteristics, and interventions of the forgotten trauma cohort, defined as patients with a fatal injury (NACA score of VII), were compared with life-threatening injuries (NACA score V and VI). RESULTS: Of 110,331 HEMS missions, 5534 primary operations were finally analyzed, including 5191 (93.8%) life-threatening and 343 (6.2%) fatal injuries. More than two-thirds of patients (n = 3772, 68.2%) had a traumatic brain injury without a significant difference between the two groups (p > 0.05). Thoracic trauma (44.6% vs. 28.7%, p < 0.001) and abdominal trauma (22.2% vs. 16.1%, p = 0.004) were more frequent in fatal missions whereas pelvic trauma was similar between the two groups (13.4% vs. 12.9%, p = 0.788). Pneumothorax decompression rate (17.2% vs. 3.7%, p < 0.001) was higher in the forgotten cohort group and measures for bleeding control (15.2% vs. 42.7%, p < 0.001) and pelvic belt application (2.9% vs. 13.1% p < 0.001) were more common in the life-threating injury group. CONCLUSION: Chest decompression rates and measures for early hemorrhage control are areas for potential improvement in prehospital care.

A Multiclass Radiomics Method-Based WHO Severity Scale for Improving COVID-19 Patient Assessment and Disease Characterization From CT Scans.

OBJECTIVES: The aim of this study was to evaluate the severity of COVID-19 patients' disease by comparing a multiclass lung lesion model to a single-class lung lesion model and radiologists' assessments in chest computed tomography scans. MATERIALS AND METHODS: The proposed method, AssessNet-19, was developed in 2 stages in this retrospective study. Four COVID-19-induced tissue lesions were manually segmented to train a 2D-U-Net network for a multiclass segmentation task followed by extensive extraction of radiomic features from the lung lesions. LASSO regression was used to reduce the feature set, and the XGBoost algorithm was trained to classify disease severity based on the World Health Organization Clinical Progression Scale. The model was evaluated using 2 multicenter cohorts: a development cohort of 145 COVID-19-positive patients from 3 centers to train and test the severity prediction model using manually segmented lung lesions. In addition, an evaluation set of 90 COVID-19-positive patients was collected from 2 centers to evaluate AssessNet-19 in a fully automated fashion. RESULTS: AssessNet-19 achieved an F1-score of 0.76 ± 0.02 for severity classification in the evaluation set, which was superior to the 3 expert thoracic radiologists (F1 = 0.63 ± 0.02) and the single-class lesion segmentation model (F1 = 0.64 ± 0.02). In addition, AssessNet-19 automated multiclass lesion segmentation obtained a mean Dice score of 0.70 for ground-glass opacity, 0.68 for consolidation, 0.65 for pleural effusion, and 0.30 for band-like structures compared with ground truth. Moreover, it achieved a high agreement with radiologists for quantifying disease extent with Cohen κ of 0.94, 0.92, and 0.95. CONCLUSIONS: A novel artificial intelligence multiclass radiomics model including 4 lung lesions to assess disease severity based on the World Health Organization Clinical Progression Scale more accurately determines the severity of COVID-19 patients than a single-class model and radiologists' assessment.

Is language an issue? Accuracy of the German computerized diagnostic decision support system ISABEL and cross-validation with the English counterpart.

OBJECTIVES: Existing computerized diagnostic decision support tools (CDDS) accurately return possible differential diagnoses (DDx) based on the clinical information provided. The German versions of the CDDS tools for clinicians (Isabel Pro) and patients (Isabel Symptom Checker) from ISABEL Healthcare have not been validated yet. METHODS: We entered clinical features of 50 patient vignettes taken from an emergency medical text book and 50 real cases with a confirmed diagnosis derived from the electronic health record (EHR) of a large academic Swiss emergency room into the German versions of Isabel Pro and Isabel Symptom Checker. We analysed the proportion of DDx lists that included the correct diagnosis. RESULTS: Isabel Pro and Symptom Checker provided the correct diagnosis in 82 and 71 % of the cases, respectively. Overall, the correct diagnosis was ranked in 71 , 61 and 37 % of the cases within the top 20, 10 and 3 of the provided DDx when using Isabel Pro. In general, accuracy was higher with vignettes than ED cases, i.e. listed the correct diagnosis more often (non-significant) and ranked the diagnosis significantly more often within the top 20, 10 and 3. On average, 38 ± 4.5 DDx were provided by Isabel Pro and Symptom Checker. CONCLUSIONS: The German versions of Isabel achieved a somewhat lower accuracy compared to previous studies of the English version. The accuracy decreases substantially when the position in the suggested DDx list is taken into account. Whether Isabel Pro is accurate enough to improve diagnostic quality in clinical ED routine needs further investigation.

Artificial intelligence for reducing the radiation burden of medical imaging for the diagnosis of coronavirus disease.

Medical imaging has been intensively employed in screening, diagnosis and monitoring during the COVID-19 pandemic. With the improvement of RT-PCR and rapid inspection technologies, the diagnostic references have shifted. Current recommendations tend to limit the application of medical imaging in the acute setting. Nevertheless, efficient and complementary values of medical imaging have been recognized at the beginning of the pandemic when facing unknown infectious diseases and a lack of sufficient diagnostic tools. Optimizing medical imaging for pandemics may still have encouraging implications for future public health, especially for long-lasting post-COVID-19 syndrome theranostics. A critical concern for the application of medical imaging is the increased radiation burden, particularly when medical imaging is used for screening and rapid containment purposes. Emerging artificial intelligence (AI) technology provides the opportunity to reduce the radiation burden while maintaining diagnostic quality. This review summarizes the current AI research on dose reduction for medical imaging, and the retrospective identification of their potential in COVID-19 may still have positive implications for future public health.

Effects of a computerised diagnostic decision support tool on diagnostic quality in emergency departments: study protocol of the DDx-BRO multicentre cluster randomised cross-over trial.

INTRODUCTION: Computerised diagnostic decision support systems (CDDS) suggesting differential diagnoses to physicians aim to improve clinical reasoning and diagnostic quality. However, controlled clinical trials investigating their effectiveness and safety are absent and the consequences of its use in clinical practice are unknown. We aim to investigate the effect of CDDS use in the emergency department (ED) on diagnostic quality, workflow, resource consumption and patient outcomes. METHODS AND ANALYSIS: This is a multicentre, outcome assessor and patient-blinded, cluster-randomised, multiperiod crossover superiority trial. A validated differential diagnosis generator will be implemented in four EDs and randomly allocated to a sequence of six alternating intervention and control periods. During intervention periods, the treating ED physician will be asked to consult the CDDS at least once during diagnostic workup. During control periods, physicians will not have access to the CDDS and diagnostic workup will follow usual clinical care. Key inclusion criteria will be patients' presentation to the ED with either fever, abdominal pain, syncope or a non-specific complaint as chief complaint. The primary outcome is a binary diagnostic quality risk score composed of presence of an unscheduled medical care after discharge, change in diagnosis or death during time of follow-up or an unexpected upscale in care within 24 hours after hospital admission. Time of follow-up is 14 days. At least 1184 patients will be included. Secondary outcomes include length of hospital stay, diagnostics and data regarding CDDS usage, physicians' confidence calibration and diagnostic workflow. Statistical analysis will use general linear mixed modelling methods. ETHICS AND DISSEMINATION: Approved by the cantonal ethics committee of canton Berne (2022-D0002) and Swissmedic, the Swiss national regulatory authority on medical devices. Study results will be disseminated through peer-reviewed journals, open repositories and the network of investigators and the expert and patients advisory board. TRIAL REGISTRATION NUMBER: NCT05346523.

Prognostic models in COVID-19 infection that predict severity: a systematic review.

Current evidence on COVID-19 prognostic models is inconsistent and clinical applicability remains controversial. We performed a systematic review to summarize and critically appraise the available studies that have developed, assessed and/or validated prognostic models of COVID-19 predicting health outcomes. We searched six bibliographic databases to identify published articles that investigated univariable and multivariable prognostic models predicting adverse outcomes in adult COVID-19 patients, including intensive care unit (ICU) admission, intubation, high-flow nasal therapy (HFNT), extracorporeal membrane oxygenation (ECMO) and mortality. We identified and assessed 314 eligible articles from more than 40 countries, with 152 of these studies presenting mortality, 66 progression to severe or critical illness, 35 mortality and ICU admission combined, 17 ICU admission only, while the remaining 44 studies reported prediction models for mechanical ventilation (MV) or a combination of multiple outcomes. The sample size of included studies varied from 11 to 7,704,171 participants, with a mean age ranging from 18 to 93 years. There were 353 prognostic models investigated, with area under the curve (AUC) ranging from 0.44 to 0.99. A great proportion of studies (61.5%, 193 out of 314) performed internal or external validation or replication. In 312 (99.4%) studies, prognostic models were reported to be at high risk of bias due to uncertainties and challenges surrounding methodological rigor, sampling, handling of missing data, failure to deal with overfitting and heterogeneous definitions of COVID-19 and severity outcomes. While several clinical prognostic models for COVID-19 have been described in the literature, they are limited in generalizability and/or applicability due to deficiencies in addressing fundamental statistical and methodological concerns. Future large, multi-centric and well-designed prognostic prospective studies are needed to clarify remaining uncertainties.

Stability of Drugs Stored in Helicopters for Use by Emergency Medical Services: A Prospective Observational Study.

STUDY OBJECTIVE: Drugs stored in rescue helicopters may be subject to extreme environmental conditions. The aim of this study was to measure whether drugs stored under the real-life conditions of a Swiss helicopter emergency medical service (HEMS) would retain their potency over the course of 1 year. METHODS: A prospective, longitudinal study measuring the temperature exposure and concentration of drugs stored on 2 rescue helicopters in Switzerland over 1 year. The study drugs included epinephrine, norepinephrine, amiodarone, midazolam, fentanyl, naloxone, rocuronium, etomidate, and ketamine. Temperatures were measured inside the medication storage bags and the crew cabins at 10-minute intervals. Drug stability was measured on a monthly basis over the course of 12 months using high-performance liquid chromatography. The medications were considered stable at a minimum remaining drug concentration of 90% of the label claim. RESULTS: Temperatures ranged from -1.2 °C to 38.1 °C (29.84 °F to 100.58 °F) inside the drug storage bags. Of all the temperature measurements inside the drug storage bags, 37% lay outside the recommended storage conditions. All drugs maintained a concentration above 90% of the label claim. The observation periods for rocuronium and etomidate were shortened to 7 months because of a supply shortage of reference samples. CONCLUSION: Drugs stored under the real-life conditions of Swiss HEMS are subjected to temperatures outside the manufacturer's approved storage requirements. Despite this, all drugs stored under these conditions remained stable throughout our study. Real-life stability testing could be a way to extend drug exchange intervals.