Emergency medicine residents' learning curve in diagnosing deep vein thrombosis with 3-point venous point-of-care ultrasound.

BACKGROUND: Many cases of deep vein thrombosis (DVT) are diagnosed in the emergency department, and abbreviated lower extremity venous point-of-care ultrasound (POCUS) has already shown an accuracy comparable to that of specialists. This study aimed to identify the learning curve necessary for emergency medicine (EM) residents to achieve expertise-level accuracy in diagnosing DVT through a 3-point lower extremity venous POCUS. METHODS: This prospective study was conducted at an emergency department between May 2021 and October 2022. Four EM residents underwent a one-hour POCUS training session and performed DVT assessments in participants with DVT symptoms or confirmed pulmonary embolism. POCUS was performed at three proximal lower extremity sites to evaluate the thrombi presence and vein compressibility, with results validated by specialized radiology ultrasound. Cumulative sum (CUSUM) and the Bush and Mosteller models were used to analyze the learning curve, while generalized estimating equations were used to identify factors affecting diagnostic accuracy. RESULTS: 91 POCUS scans were conducted in 49 patients, resulting in 22% DVT confirmed by specialized venous ultrasound. In the CUSUM analysis, all four EM residents attained a 90% success rate at the common femoral vein, whereas only half achieved this rate when all three sites were considered. According to Bush and Mosteller models, 13-18 cases are required to attain 90-95% diagnostic accuracy. After 10-16 cases, the examination time for each resident decreased, and a 20% increase in examiner confidence was linked to a 2.506-fold increase in the DVT diagnosis accuracy. CONCLUSION: EM residents generally required 13-18 cases for 90-95% DVT diagnostic accuracy, but proficiency varied among individuals, particularly requiring more cases for regions outside the common femoral vein.

Adoption of Augmented Reality in Educational Programs for Nurses in Intensive Care Units of Tertiary Academic Hospitals: Mixed Methods Study.

BACKGROUND: In the wake of challenges brought by the COVID-19 pandemic to conventional medical education, the demand for innovative teaching methods has surged. Nurse training, with its focus on hands-on practice and self-directed learning, encountered significant hurdles with conventional approaches. Augmented reality (AR) offers a potential solution to addressing this issue. OBJECTIVE: The aim of this study was to develop, introduce, and evaluate an AR-based educational program designed for nurses, focusing on its potential to facilitate hands-on practice and self-directed learning. METHODS: An AR-based educational program for nursing was developed anchored by the Kern six-step framework. First, we identified challenges in conventional teaching methods through interviews and literature reviews. Interviews highlighted the need for hands-on practice and on-site self-directed learning with feedback from a remote site. The training goals of the platform were established by expert trainers and researchers, focusing on the utilization of a ventilator and extracorporeal membrane oxygenation system. Intensive care nurses were enrolled to evaluate AR education. We then assessed usability and acceptability of the AR training using the System Usability Scale and Technology Acceptance Model with intensive care nurses who agreed to test the new platform. Additionally, selected participants provided deeper insights through semistructured interviews. RESULTS: This study highlights feasibility and key considerations for implementing an AR-based educational program for intensive care unit nurses, focusing on training objectives of the platform. Implemented over 2 months using Microsoft Dynamics 365 Guides and HoloLens 2, 28 participants were trained. Feedback gathered through interviews with the trainers and trainees indicated a positive reception. In particular, the trainees mentioned finding AR particularly useful for hands-on learning, appreciating its realism and the ability for repetitive practice. However, some challenges such as difficulty in adapting to the new technology were expressed. Overall, AR exhibits potential as a supplementary tool in nurse education. CONCLUSIONS: To our knowledge, this is the first study to substitute conventional methods with AR in this specific area of critical care nursing. These results indicate the multiple principal factors to take into consideration when adopting AR education in hospitals. AR is effective in promoting self-directed learning and hands-on practice, with participants displaying active engagement and enhanced skill acquisition. TRIAL REGISTRATION: ClinicalTrials.gov NCT05629663; https://clinicaltrials.gov/study/NCT05629663.

Inter hospital external validation of interpretable machine learning based triage score for the emergency department using common data model.

Emergency departments (ED) are complex, triage is a main task in the ED to prioritize patient with limited medical resources who need them most. Machine learning (ML) based ED triage tool, Score for Emergency Risk Prediction (SERP), was previously developed using an interpretable ML framework with single center. We aimed to develop SERP with 3 Korean multicenter cohorts based on common data model (CDM) without data sharing and compare performance with inter-hospital validation design. This retrospective cohort study included all adult emergency visit patients of 3 hospitals in Korea from 2016 to 2017. We adopted CDM for the standardized multicenter research. The outcome of interest was 2-day mortality after the patients' ED visit. We developed each hospital SERP using interpretable ML framework and validated inter-hospital wisely. We accessed the performance of each hospital's score based on some metrics considering data imbalance strategy. The study population for each hospital included 87,670, 83,363 and 54,423 ED visits from 2016 to 2017. The 2-day mortality rate were 0.51%, 0.56% and 0.65%. Validation results showed accurate for inter hospital validation which has at least AUROC of 0.899 (0.858-0.940). We developed multicenter based Interpretable ML model using CDM for 2-day mortality prediction and executed Inter-hospital external validation which showed enough high accuracy.

Corrigendum to "Development and Asian-wide validation of the Grade for Interpretable Field Triage (GIFT) for predicting mortality in pre-hospital patients using the Pan-Asian Trauma Outcomes Study (PATOS)" [The Lancet Regional Health - Western Pacific 34 (2023) 100733].

[This corrects the article DOI: 10.1016/j.lanwpc.2023.100733.].

Real-Time Tracheal Ultrasound vs. Capnography for Intubation Confirmation during CPR Wearing a Powered Air-Purifying Respirator in COVID-19 Era.

This study aimed to compare the accuracy of real-time trans-tracheal ultrasound (TTUS) with capnography to confirm intubation in cardiopulmonary resuscitation (CPR) while wearing a powered air-purifying respirator (PAPR). This setting reflects increased caution due to contagious diseases. This single-center, prospective, comparative study enrolled patients requiring CPR while wearing a PAPR who visited the emergency department of a tertiary medical center from December 2020 to August 2022. A physician performed the TTUS in real time and recorded the tube placement assessment. Another healthcare provider attached waveform capnography to the tube and recorded end-tidal carbon dioxide (EtCO2) after five ventilations. The accuracy and agreement of both methods compared with direct laryngoscopic visualization of tube placement, and the time taken by both methods was evaluated. Thirty-three patients with cardiac arrest were analyzed. TTUS confirmed tube placement with 100% accuracy, sensitivity, and specificity, whereas capnography demonstrated 97% accuracy, 96.8% sensitivity, and 100% specificity. The Kappa values for TTUS and capnography compared to direct visualization were 1.0 and 0.7843, respectively. EtCO2 was measured in 45 (37-59) seconds (median (interquartile range)), whereas TTUS required only 12 (8-23) seconds, indicating that TTUS was significantly faster (p < 0.001). No significant correlation was found between the physician's TTUS proficiency and image acquisition time. This study demonstrated that TTUS is more accurate and faster than EtCO2 measurement for confirming endotracheal tube placement during CPR, particularly in the context of PAPR usage in pandemic conditions.

Effect of Blade Size on the First-Pass Success Rate of Endotracheal Intubation Using the C-MAC Video Laryngoscope.

We sought to determine whether blade size influences the first-pass success (FPS) rate when performing endotracheal intubation (ETI) with a C-MAC video laryngoscope (VL) in emergency department (ED) patients. This single-center, retrospective, observational study was conducted between August 2016 and July 2022. A total of 1467 patients was divided into two categories based on the blade size used during the first ETI attempt: blade-3 (n = 365) and blade-4 groups (n = 1102). The primary outcome was the FPS rate. The secondary outcomes included the glottic view, multiple attempt rate, and ETI-related complications. We used propensity score matching to reduce the potential confounders between the two groups. Among these, 363 pairs of matched propensity scores were generated. The FPS rate did not differ between the blade-3 (84.8%) and blade-4 groups (87.3%) in the matched cohort (p = 0.335). The multiple attempt rate did not differ significantly between groups (p = 0.289) and was 3.9% and 2.5% in the blade-3 and blade-4 groups, respectively. The difficult glottic view (11.3 vs. 6.9%, p = 0.039) and complication rates (15.4% vs. 10.5%, p = 0.047) were significantly higher in the blade-3 group than in the blade-4 group. The FPS rates of ETI with the blade-3 and blade-4 groups in adult patients in the ED did not differ significantly.

Machine learning pre-hospital real-time cardiac arrest outcome prediction (PReCAP) using time-adaptive cohort model based on the Pan-Asian Resuscitation Outcome Study.

To save time during transport, where resuscitation quality can degrade in a moving ambulance, it would be prudent to continue the resuscitation on scene if there is a high likelihood of ROSC occurring at the scene. We developed the pre-hospital real-time cardiac arrest outcome prediction (PReCAP) model to predict ROSC at the scene using prehospital input variables with time-adaptive cohort. The patient survival at discharge from the emergency department (ED), the 30-day survival rate, and the final Cerebral Performance Category (CPC) were secondary prediction outcomes in this study. The Pan-Asian Resuscitation Outcome Study (PAROS) database, which includes out-of-hospital cardiac arrest (OHCA) patients transferred by emergency medical service in Asia between 2009 and 2018, was utilized for this study. From the variables available in the PAROS database, we selected relevant variables to predict OHCA outcomes. Light gradient-boosting machine (LightGBM) was used to build the PReCAP model. Between 2009 and 2018, 157,654 patients in the PAROS database were enrolled in our study. In terms of prediction of ROSC on scene, the PReCAP had an AUROC score between 0.85 and 0.87. The PReCAP had an AUROC score between 0.91 and 0.93 for predicting survived to discharge from ED, and an AUROC score between 0.80 and 0.86 for predicting the 30-day survival. The PReCAP predicted CPC with an AUROC score ranging from 0.84 to 0.91. The feature importance differed with time in the PReCAP model prediction of ROSC on scene. Using the PAROS database, PReCAP predicted ROSC on scene, survival to discharge from ED, 30-day survival, and CPC for each minute with an AUROC score ranging from 0.8 to 0.93. As this model used a multi-national database, it might be applicable for a variety of environments and populations.

Clinical support system for triage based on federated learning for the Korea triage and acuity scale.

Background and aims: This study developed a clinical support system based on federated learning to predict the need for a revised Korea Triage Acuity Scale (KTAS) to facilitate triage. Methods: This was a retrospective study that used data from 11,952,887 patients in the Korean National Emergency Department Information System (NEDIS) from 2016 to 2018 for model development. Separate cohorts were created based on the emergency medical center level in the NEDIS: regional emergency medical center (REMC), local emergency medical center (LEMC), and local emergency medical institution (LEMI). External and temporal validation used data from emergency department (ED) of the study site from 2019 to 2021. Patient features obtained during the triage process and the initial KTAS scores were used to develop the prediction model. Federated learning was used to rectify the disparity in data quality between EDs. The patient's demographic information, vital signs in triage, mental status, arrival information, and initial KTAS were included in the input feature. Results: 3,626,154 patients' visits were included in the regional emergency medical center cohort; 8,278,081 patients' visits were included in the local emergency medical center cohort; and 48,652 patients' visits were included in the local emergency medical institution cohort. The study site cohort, which is used for external and temporal validation, included 135,780 patients visits. Among the patients in the REMC and study site cohorts, KTAS level 3 patients accounted for the highest proportion at 42.4% and 45.1%, respectively, whereas in the LEMC and LEMI cohorts, KTAS level 4 patients accounted for the highest proportion. The area under the receiver operating characteristic curve for the prediction model was 0.786, 0.750, and 0.770 in the external and temporal validation. Patients with revised KTAS scores had a higher admission rate and ED mortality rate than those with unaltered KTAS scores. Conclusions: This novel system might accurately predict the likelihood of KTAS acuity revision and support clinician-based triage.

A Pilot Study Evaluating LV Diastolic Function with M-Mode Measurement of Mitral Valve Movement in the Parasternal Long Axis View.

This pilot study aimed to develop a new, reliable, and easy-to-use method for the evaluation of diastolic function through the M-mode measurement of mitral valve (MV) movement in the parasternal long axis (PSLA), similar to E-point septal separation (EPSS) used for systolic function estimation. Thirty healthy volunteers from a tertiary emergency department (ED) underwent M-mode measurements of the MV anterior leaflet in the PSLA view. EPSS, A-point septal separation (APSS), A-point opening length (APOL), and E-point opening length (EPOL) were measured in the PSLA view, along with the E and A velocities and e' velocity in the apical four-chamber view. Correlation analyses were performed to assess the relationship between M-mode and Doppler measurements, and the measurement time was evaluated. No significant correlations were found between M-mode and Doppler measurements in the study. However, M-mode measurements exhibited high reproducibility and faster acquisition, and the EPOL value consistently exceeded the APOL value, resembling the E and A pattern. These findings suggest that visually assessing the M-mode pattern on the MV anterior leaflet in the PSLA view may be a practical approach to estimating diastolic function in the ED. Further investigations with a larger and more diverse patient population are needed to validate these findings.

EARLY PREDICTION OF UNEXPECTED LATENT SHOCK IN THE EMERGENCY DEPARTMENT USING VITAL SIGNS.

ABSTRACT: Objective/Introduction : Sequential vital-sign information and trends in vital signs are useful for predicting changes in patient state. This study aims to predict latent shock by observing sequential changes in patient vital signs. Methods : The dataset for this retrospective study contained a total of 93,194 emergency department (ED) visits from January 1, 2016, and December 31, 2020, and Medical Information Mart for Intensive Care (MIMIC)-IV-ED data. We further divided the data into training and validation datasets by random sampling without replacement at a 7:3 ratio. We carried out external validation with MIMIC-IV-ED. Our prediction model included logistic regression (LR), random forest (RF) classifier, a multilayer perceptron (MLP), and a recurrent neural network (RNN). To analyze the model performance, we used area under the receiver operating characteristic curve (AUROC). Results : Data of 89,250 visits of patients who met prespecified criteria were used to develop a latent-shock prediction model. Data of 142,250 patient visits from MIMIC-IV-ED satisfying the same inclusion criteria were used for external validation of the prediction model. The AUROC values of prediction for latent shock were 0.822, 0.841, 0.852, and 0.830 with RNN, MLP, RF, and LR methods, respectively, at 3 h before latent shock. This is higher than the shock index or adjusted shock index. Conclusion : We developed a latent shock prediction model based on 24 h of vital-sign sequence that changed with time and predicted the results by individual.

Development and Asian-wide validation of the Grade for Interpretable Field Triage (GIFT) for predicting mortality in pre-hospital patients using the Pan-Asian Trauma Outcomes Study (PATOS).

Background: Field triage is critical in injury patients as the appropriate transport of patients to trauma centers is directly associated with clinical outcomes. Several prehospital triage scores have been developed in Western and European cohorts; however, their validity and applicability in Asia remains unclear. Therefore, we aimed to develop and validate an interpretable field triage scoring systems based on a multinational trauma registry in Asia. Methods: This retrospective and multinational cohort study included all adult transferred injury patients from Korea, Malaysia, Vietnam, and Taiwan between 2016 and 2018. The outcome of interest was a death in the emergency department (ED) after the patients' ED visit. Using these results, we developed the interpretable field triage score with the Korea registry using an interpretable machine learning framework and validated the score externally. The performance of each country's score was assessed using the area under the receiver operating characteristic curve (AUROC). Furthermore, a website for real-world application was developed using R Shiny. Findings: The study population included 26,294, 9404, 673 and 826 transferred injury patients between 2016 and 2018 from Korea, Malaysia, Vietnam, and Taiwan, respectively. The corresponding rates of a death in the ED were 0.30%, 0.60%, 4.0%, and 4.6% respectively. Age and vital sign were found to be the significant variables for predicting mortality. External validation showed the accuracy of the model with an AUROC of 0.756-0.850. Interpretation: The Grade for Interpretable Field Triage (GIFT) score is an interpretable and practical tool to predict mortality in field triage for trauma. Funding: This research was supported by a grant of the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea (Grant Number: HI19C1328).

Feasibility of patch-type wireless 12-lead electrocardiogram in laypersons.

Various efforts have been made to diagnose acute cardiovascular diseases (CVDs) early in patients. However, the sole option currently is symptom education. It may be possible for the patient to obtain an early 12-lead electrocardiogram (ECG) before the first medical contact (FMC), which could decrease the physical contact between patients and medical staff. Thus, we aimed to verify whether laypersons can obtain a 12-lead ECG in an off-site setting for clinical treatment and diagnosis using a patch-type wireless 12-lead ECG (PWECG). Participants who were ≥ 19 years old and under outpatient cardiology treatment were enrolled in this simulation-based one-arm interventional study. We confirmed that participants, regardless of age and education level, can use the PWECG on their own. The median age of the participants was 59 years (interquartile range [IQR] = 56-62 years), and the median duration to obtain a 12-lead ECG result was 179 s (IQR = 148-221 s). With appropriate education and guidance, it is possible for a layperson to obtain a 12-lead ECG, minimizing the contact with a healthcare provider. These results can be used subsequently for treatment.

Clinical factors predicting return emergency department visits in chemotherapy-induced febrile neutropenia patients.

BACKGROUND: Although chemotherapy-induced febrile neutropenia (FN) is the most common and life-threatening oncologic emergency, the characteristics and outcomes associated with return visits to the emergency department (ED) in these patients are uncertain. Hence, we aimed to investigate the predictive factors and clinical outcomes of chemotherapy-induced FN patients returning to the ED. METHOD: This single-center, retrospective observational study spanning 14 years included chemotherapy-induced FN patients who visited the ED and were discharged. The primary outcome was a return visit to the ED within five days. We conducted logistic regression analyses to evaluate the factors influencing ED return visit. RESULTS: This study included 1318 FN patients, 154 (12.1%) of whom revisited the ED within five days. Patients (53.3%) revisited the ED owing to persistent fever (56.5%), with no intensive care unit admission and only one mortality case who was discharged hopelessly. Multivariable analysis revealed that shock index >0.9 (odds ratio [OR]: 1.45, 95% confidence interval [CI], 1.01-2.10), thrombocytopenia (<100 × 103/uL) (OR: 1.64, 95% CI, 1.11-2.42), and lactic acid level > 2 mmol/L (OR: 1.51, 95% CI, 0.99-2.25) were associated with an increased risk of a return visit to the ED, whereas being transferred into the ED from other hospitals (OR: 0.08; 95% CI, 0.005-0.38) was associated with a decreased risk of a return visit to the ED. CONCLUSION: High shock index, lactic acid, thrombocytopenia, and ED arrival type can predict return visits to the ED in chemotherapy-induced FN patients.

A Simple Bacteremia Score for Predicting Bacteremia in Patients with Suspected Infection in the Emergency Department: A Cohort Study.

Bacteremia is a life-threatening condition that has increased in prevalence over the past two decades. Prompt recognition of bacteremia is important; however, identification of bacteremia requires 1 to 2 days. This retrospective cohort study, conducted from 10 November 2014 to November 2019, among patients with suspected infection who visited the emergency department (ED), aimed to develop and validate a simple tool for predicting bacteremia. The study population was randomly divided into derivation and development cohorts. Predictors of bacteremia based on the literature and logistic regression were assessed. A weighted value was assigned to predictors to develop a prediction model for bacteremia using the derivation cohort; discrimination was then assessed using the area under the receiver operating characteristic curve (AUC). Among the 22,519 patients enrolled, 18,015 were assigned to the derivation group and 4504 to the validation group. Sixteen candidate variables were selected, and all sixteen were used as significant predictors of bacteremia (model 1). Among the sixteen variables, the top five with higher odds ratio, including procalcitonin, neutrophil-lymphocyte ratio (NLR), lactate level, platelet count, and body temperature, were used for the simple bacteremia score (model 2). The proportion of bacteremia increased according to the simple bacteremia score in both cohorts. The AUC for model 1 was 0.805 (95% confidence interval [CI] 0.785-0.824) and model 2 was 0.791 (95% CI 0.772-0.810). The simple bacteremia prediction score using only five variables demonstrated a comparable performance with the model including sixteen variables using all laboratory results and vital signs. This simple score is useful for predicting bacteremia-assisted clinical decisions.

National Surveillance of Pediatric Out-of-Hospital Cardiac Arrest in Korea: The 10-Year Trend From 2009 to 2018.

BACKGROUND: This study reports trends in pediatric out-of-hospital cardiac arrest (OHCA) and factors affecting clinical outcomes by age group. METHODS: We identified 4,561 OHCA patients younger than 18 years between January 2009 and December 2018 in the Korean OHCA Registry. The patients were divided into four groups: group 1 (1 year or younger), group 2 (1 to 5 years), group 3 (6 to 12 years), and group 4 (13 to 17 years). The primary outcome was survival to hospital discharge, and the secondary outcomes were return of spontaneous circulation (ROSC) at the emergency department (ED) and good neurological status at discharge. Multivariate logistic analyses were performed. RESULTS: The incidence rate of pediatric OHCA in group 1 increased from 45.57 to 60.89 per 100,000 person-years, while that of the overall population decreased over the 10 years. The rates of ROSC at the ED, survival to hospital discharge, and good neurologic outcome were highest in group 4 (37.9%, 9.7%, 4.9%, respectively) and lowest in group 1 (28.3%, 7.1%, 3.2%). The positive factors for survival to discharge were event location of a public/commercial building or place of recreation, type of first responder, prehospital delivery of automated external defibrillator shock, initial shockable rhythm at the ED. The factors affecting survival outcomes differed by age group. CONCLUSION: This study reports comprehensive trends in pediatric OHCA in the Republic of Korea. Our findings imply that preventive methods for the targeted population should be customized by age group.

Development and validation of interpretable machine learning models for inpatient fall events and electronic medical record integration.

OBJECTIVE: Falls are one of the most frequently occurring adverse events among hospitalized patients. The Morse Fall Scale, which has been widely used for fall risk assessment, has the two limitations of low specificity and difficulty in practical implementation. The aim of this study was to develop and validate an interpretable machine learning model for prediction of falls to be integrated in an electronic medical record (EMR) system. METHODS: This was a retrospective study involving a tertiary teaching hospital in Seoul, Korea. Based on the literature, 83 known predictors were grouped into seven categories. Interpretable fall event prediction models were developed using multiple machine learning models including gradient boosting and Shapley values. RESULTS: Overall, 191,778 cases with 272 fall events (0.1%) were included in the analysis. With the validation cohort of 2020, the area under the receiver operating curve (AUROC) of the gradient boosting model was 0.817 (95% confidence interval [CI], 0.720-0.904), better performance than random forest (AUROC, 0.801; 95% CI, 0.708-0.890), logistic regression (AUROC, 0.802; 95% CI, 0.721-0.878), artificial neural net (AUROC, 0.736; 95% CI, 0.650-0.821), and conventional Morse fall score (AUROC, 0.652; 95% CI, 0.570-0.715). The model's interpretability was enhanced at both the population and patient levels. The algorithm was later integrated into the current EMR system. CONCLUSION: We developed an interpretable machine learning prediction model for inpatient fall events using EMR integration formats.

An Augmented Reality-Based Guide for Mechanical Ventilator Setup: Prospective Randomized Pilot Trial.

BACKGROUND: Recently, the demand for mechanical ventilation (MV) has increased with the COVID-19 pandemic; however, the conventional approaches to MV training are resource intensive and require on-site training. Consequently, the need for independent learning platforms with remote assistance in institutions without resources has surged. OBJECTIVE: This study aimed to determine the feasibility and effectiveness of an augmented reality (AR)-based self-learning platform for novices to set up a ventilator without on-site assistance. METHODS: This prospective randomized controlled pilot study was conducted at Samsung Medical Center, Korea, from January to February 2022. Nurses with no prior experience of MV or AR were enrolled. We randomized the participants into 2 groups: manual and AR groups. Participants in the manual group used a printed manual and made a phone call for assistance, whereas participants in the AR group were guided by AR-based instructions and requested assistance with the head-mounted display. We compared the overall score of the procedure, required level of assistance, and user experience between the groups. RESULTS: In total, 30 participants completed the entire procedure with or without remote assistance. Fewer participants requested assistance in the AR group compared to the manual group (7/15, 47.7% vs 14/15, 93.3%; P=.02). The number of steps that required assistance was also lower in the AR group compared to the manual group (n=13 vs n=33; P=.004). The AR group had a higher rating in predeveloped questions for confidence (median 3, IQR 2.50-4.00 vs median 2, IQR 2.00-3.00; P=.01), suitability of method (median 4, IQR 4.00-5.00 vs median 3, IQR 3.00-3.50; P=.01), and whether they intended to recommend AR systems to others (median 4, IQR 3.00-5.00 vs median 3, IQR 2.00-3.00; P=.002). CONCLUSIONS: AR-based instructions to set up a mechanical ventilator were feasible for novices who had no prior experience with MV or AR. Additionally, participants in the AR group required less assistance compared with those in the manual group, resulting in higher confidence after training. TRIAL REGISTRATION: ClinicalTrials.gov NCT05446896; https://beta.clinicaltrials.gov/study/NCT05446896.

Decision effect of a deep-learning model to assist a head computed tomography order for pediatric traumatic brain injury.

The study aims to measure the effectiveness of an AI-based traumatic intracranial hemorrhage prediction model in the decisions of emergency physicians regarding ordering head computed tomography (CT) scans. We developed a deep-learning model for predicting traumatic intracranial hemorrhages (DEEPTICH) using a national trauma registry with 1.8 million cases. For simulation, 24 cases were selected from previous emergency department cases. For each case, physicians made decisions on ordering a head CT twice: initially without the DEEPTICH assistance, and subsequently with the DEEPTICH assistance. Of the 528 responses from 22 participants, 201 initial decisions were different from the DEEPTICH recommendations. Of these 201 initial decisions, 94 were changed after DEEPTICH assistance (46.8%). For the cases in which CT was initially not ordered, 71.4% of the decisions were changed (p < 0.001), and for the cases in which CT was initially ordered, 37.2% (p < 0.001) of the decisions were changed after DEEPTICH assistance. When using DEEPTICH, 46 (11.6%) unnecessary CTs were avoided (p < 0.001) and 10 (11.4%) traumatic intracranial hemorrhages (ICHs) that would have been otherwise missed were found (p = 0.039). We found that emergency physicians were likely to accept AI based on how they perceived its safety.

Effectiveness of a Real-Time Ventilation Feedback Device for Guiding Adequate Minute Ventilation: A Manikin Simulation Study.

Background and objectives: It is often challenging even for skilled rescuers to provide adequate positive pressure ventilation consistently. This study aimed to investigate the effectiveness of a newly developed real-time ventilation feedback device (RTVFD) that estimates tidal volume (TV) and ventilation interval (VI) in real time. Materials and methods: We conducted a randomised, crossover, manikin simulation study. A total of 26 medical providers were randomly assigned to the RTVFD-assisted ventilation (RAV) first group (n = 13) and the non-assisted ventilation (NV) first group (n = 13). Participants provided ventilation using adult and paediatric bag valves (BVs) for 2 min each. After a washout period, the simulation was repeated by exchanging the participants' groups. Results: The primary outcome was optimal TV in the RAV and NV groups using adult and paediatric BVs. A secondary outcome was optimal VI in the RAV and NV groups using adult and paediatric BVs. The proportions of optimal TV values were higher for the RAVs when using both adult and paediatric BVs (adult BV: 47.29% vs. 18.46%, p < 0.001; paediatric BV: 89.51% vs. 72.66%, p < 0.001) than for the NVs. The proportions of optimal VI were significantly higher in RAVs when using both adult and paediatric BVs than that in NVs (adult BV: 95.64% vs. 50.20%, p < 0.001; paediatric BV: 95.83% vs. 57.14%, p < 0.001). Additionally, we found that with paediatric BVs, the simulation had a higher OR for both optimal TV (13.26; 95% CI, 9.96-17.65; p < 0.001) and VI (1.32; 1.08-1.62, p = 0.007), regardless of RTVFD use. Conclusion: Real-time feedback using RTVFD significantly improves the TV and VI in both adult and paediatric BVs in a manikin simulation study.