Recent studies have suggested that deep-learning models can satisfactorily assist in fracture diagnosis. We aimed to evaluate the performance of two of such models in wrist fracture detection. We collected image data of patients who visited with wrist trauma at the emergency department. A dataset extracted from January 2018 to May 2020 was split into training (90%) and test (10%) datasets, and two types of convolutional neural networks (i.e., DenseNet-161 and ResNet-152) were trained to detect wrist fractures. Gradient-weighted class activation mapping was used to highlight the regions of radiograph scans that contributed to the decision of the model. Performance of the convolutional neural network models was evaluated using the area under the receiver operating characteristic curve. For model training, we used 4,551 radiographs from 798 patients and 4,443 radiographs from 1,481 patients with and without fractures, respectively. The remaining 10% (300 radiographs from 100 patients with fractures and 690 radiographs from 230 patients without fractures) was used as a test dataset. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of DenseNet-161 and ResNet-152 in the test dataset were 90.3%, 90.3%, 80.3%, 95.6%, and 90.3% and 88.6%, 88.4%, 76.9%, 94.7%, and 88.5%, respectively. The area under the receiver operating characteristic curves of DenseNet-161 and ResNet-152 for wrist fracture detection were 0.962 and 0.947, respectively. We demonstrated that DenseNet-161 and ResNet-152 models could help detect wrist fractures in the emergency room with satisfactory performance.

Ha SO, et al. J Korean Med Sci. 2016 Nov;31(11):1838-1845. https://doi.org/10.3346/jkms.2016.31.11.1838

During the coronavirus disease 2019 (COVID-19) pandemic, prehospital times were delayed for patients who needed to arrive at the hospital in a timely manner to receive treatment. To address this, in March 2020, the Korean government designated emergency medical centers for critical care (EMC-CC). This study retrospectively analyzed whether this intervention effectively reduced ambulance diversion (AD) and shortened prehospital times using emergency medical service records from 219,763 patients from the Gyeonggi Province, collected between 1 January and 31 December 2020. We included non-traumatic patients aged 18 years or older. We used interrupted time series analysis to investigate the intervention effects on the daily AD rate and compared prehospital times before and after the intervention. Following the intervention, the proportion of patients transported 30–35 km and 50 km or more was 13.8% and 5.7%, respectively, indicating an increased distance compared to before the intervention. Although the change in the AD rate was insignificant, the daily AD rate significantly decreased after the intervention. Prehospital times significantly increased after the intervention in all patients (p < 0.001) and by disease group; all prehospital times except for the scene time of cardiac arrest patients increased. In order to achieve optimal treatment times for critically ill patients in a situation that pushes the limits of the medical system, such as the COVID-19 pandemic, even regional distribution of EMC-CC may be necessary, and priority should be given to the allocation of care for patients with mild symptoms.

Early recognition of the signs and symptoms of clinical deterioration could diminish the incidence of cardiopulmonary arrest. The present study investigates outcomes with respect to cardiopulmonary arrest rates in institutions with and without rapid response systems (RRSs) and the current level of cardiopulmonary arrest rate in tertiary hospitals. This was a retrospective study based on data from 14 tertiary hospitals. Cardiopulmonary resuscitation (CPR) rate reports were obtained from each hospital to include the number of cardiopulmonary arrest events in adult patients in the general ward, the annual adult admission statistics, and the structure of the RRS if present. Hospitals with RRSs showed a statistically significant reduction of the CPR rate between 2013 and 2015 (odds ratio [OR], 0.731; 95% confidence interval [CI], 0.577 to 0.927; P = 0.009). Nevertheless, CPR rates of 2013 and 2015 did not change in hospitals without RRS (OR, 0.988; 95% CI, 0.868 to 1.124; P = 0.854). National university-affiliated hospitals showed less cardiopulmonary arrest rate than private university-affiliated in 2015 (1.92 vs. 2.40; OR, 0.800; 95% CI, 0.702 to 0.912; P = 0.001). High-volume hospitals showed lower cardiopulmonary arrest rates compared with medium-volume hospitals in 2013 (1.76 vs. 2.63; OR, 0.667; 95% CI, 0.577 to 0.772; P < 0.001) and in 2015 (1.55 vs. 3.20; OR, 0.485; 95% CI, 0.428 to 0.550; P < 0.001). RRSs may be a feasible option to reduce the CPR rate. The discrepancy in cardiopulmonary arrest rates suggests further research should include a nationwide survey to tease out factors involved in in-hospital cardiopulmonary arrest and differences in outcomes based on hospital characteristics.

The reported survival rates of patients with acute respiratory distress syndrome (ARDS) caused by human adenovirus (HAdV) pneumonia are poor. The results do not differ much in immunocompetent patients supported by extracorporeal membrane oxygenation (ECMO). We report two immunocompetent patients with severe ARDS complicating HAdV pneumonia who were treated successfully and survived to discharge. Compared with previous cases, our cases might have benefited from several factors. First, the time interval between mechanical ventilator support and ECMO implantation was shorter. Second, we implemented conservative fluid management as recommended by the ARDS network using continuous renal replacement therapy (CRRT). Third, we administered an antiviral agent as early as possible. A clinical trial of early ECMO with CRRT and the administration of cidofovir in patients with severe ARDS complicating HAdV pneumonia are needed to confirm our results.

Objective This study aimed to clarify the relative prognostic value of each History, Electrocardiography, Age, Risk Factors, and Troponin (HEART) score component for major adverse cardiac events (MACE) within 3 months and validate the modified HEART (mHEART) score.Methods This study evaluated the HEART score components for patients with chest symptoms visiting the emergency department from November 19, 2018 to November 19, 2019. All components were evaluated using logistic regression analysis and the scores for HEART, mHEART, and Thrombolysis in Myocardial Infarction (TIMI) were determined using the receiver operating characteristics curve.Results The patients were divided into a derivation (809 patients) and a validation group (298 patients). In multivariate analysis, age did not show statistical significance in the detection of MACE within 3 months and the mHEART score was calculated after omitting the age component. The areas under the receiver operating characteristics curves for HEART, mHEART and TIMI scores in the prediction of MACE within 3 months were 0.88, 0.91, and 0.83, respectively, in the derivation group; and 0.88, 0.91, and 0.81, respectively, in the validation group. When the cutoff value for each scoring system was determined for the maintenance of a negative predictive value for a MACE rate >99%, the mHEART score showed the highest sensitivity, specificity, positive predictive value, and negative predictive value (97.4%, 54.2%, 23.7%, and 99.3%, respectively).Conclusion Our study showed that the mHEART score better detects short-term MACE in high-risk patients and ensures the safe disposition of low-risk patients than the HEART and TIMI scores.