Objective: : Deep learning is a machine learning approach based on artificial neural network training, and object detection algorithm using deep learning is used as the most powerful tool in image analysis. We analyzed and evaluated the diagnostic performance of a deep learning algorithm to identify skull fractures in plain radiographic images and investigated its clinical applicability. Methods: : A total of 2026 plain radiographic images of the skull (fracture, 991; normal, 1035) were obtained from 741 patients. The RetinaNet architecture was used as a deep learning model. Precision, recall, and average precision were measured to evaluate the deep learning algorithm’s diagnostic performance. Results: : In ResNet-152, the average precision for intersection over union (IOU) 0.1, 0.3, and 0.5, were 0.7240, 0.6698, and 0.3687, respectively. When the intersection over union (IOU) and confidence threshold were 0.1, the precision was 0.7292, and the recall was 0.7650. When the IOU threshold was 0.1, and the confidence threshold was 0.6, the true and false rates were 82.9% and 17.1%, respectively. There were significant differences in the true/false and false-positive/false-negative ratios between the anteriorposterior, towne, and both lateral views (p=0.032 and p=0.003). Objects detected in false positives had vascular grooves and suture lines. In false negatives, the detection performance of the diastatic fractures, fractures crossing the suture line, and fractures around the vascular grooves and orbit was poor. Conclusion : The object detection algorithm applied with deep learning is expected to be a valuable tool in diagnosing skull fractures.

Pulmonary vein isolation is an well-established treatment strategy for atrial fibrillation (AF), and it is especially effective for patients with paroxysmal AF. However, the success rate is limited for patients with persistent AF, because non-pul‑ monary vein triggers which increase AF recurrence are frequently found in these patients. The major non-pulmonary vein triggers are from the left atrial posterior wall, left atrial appendage, ligament of Marshall, coronary sinus, superior vena cava, and crista terminalis, but other atrial sites can also generate AF triggers. All these sites have been known to contain atrial myocytes with potential arrhythmogenic electrical activity. The prevalence and clinical characteristics of these non-pulmonary vein triggers are well studied; however, the clinical outcome of catheter ablation for persistent AF is still unclear. Here, we reviewed the current ablation strategies for persistent AF and the clinical implications of major non-pulmonary vein triggers.

Background: In a substantial proportion of patients with syncope, the exact cause is not identified because of the difficulty to document electrocardiograms correlated with the events during a syncope episode. Thus, an implant‑ able loop recorder (ILR) was introduced for diagnosing hidden arrhythmia; however, its clinical use remains limited.Therefore, we conducted a retrospective analysis to assess the diagnostic value of the ILR in patients with unexplained syncope or palpitations. Methods: All patients who had undergone ILR implantation from May 2016 to January 2020, were studied retrospec‑ tively. We analyzed their electrocardiogram stored in the device. Results: Among the 70 patients (mean age ± SD; 50.2 ± 20.3 years, 27 men) with unknown causes of syncope or pal‑ pitation, during two years follow-up, arrhythmia was detected in 26 patients (37.1%). Nineteen (73.1%) patients under‑ went permanent pacemaker implantation due to symptomatic bradycardia or atrioventricular block. All arrhythmias were detected within 6 days to 39 months after loop recorder implantation. Thirteen patients (50%) showed sick sinus syndrome (eight long pauses and five tachycardia-bradycardia syndromes). Eleven patients (42.3%) had paroxysmal atrioventricular block. Two patients who underwent permanent pacemaker implantation showed a positive tilt-table test. Three patients underwent radiofrequency catheter ablation for paroxysmal supraventricular tachycardia and atrial fibrillation. The mean duration for the detection of first sign (arrhythmia or palpitations) was 7.5 months, and the time from the detection of arrhythmia to ablation or device implantation was 3.4 months. Conclusion ILR monitoring detected a substantial number of significant bradycardias in patients with unexplained syncope and palpitations, suggesting that it is an effective diagnostic method that can shorten the time required to identify the cause of arrhythmias.

Background/Aims: Atrial fibrillation (AF)-related stroke accounts for 20% of ischemic strokes. Rivaroxaban use in AF patients for preventing stroke and systemic embolism was approved in 2013 in Korea. This study was to investigate the safety and effectiveness of rivaroxaban use in Korean patients with non-valvular AF in a real-world setting. Methods: This was an analysis of the Korean patients in Xarelto for Prevention of Stroke in Patients with Atrial Fibrillation in Asia-Pacific (XANAP), which was a prospective, observational cohort study including patients with non-valvular AF starting rivaroxaban treatment to prevent stroke or non-central nervous system systemic embolism (non-CNS SE), conducted in 10 Asian countries. Results: A total of 844 patients were enrolled in the Korean portion of the XANAP study. In XANAP Korea, the mean age was 70.1 years and 62.6% were males. The mean CHADS2 score was 2.5 and the mean CHA2DS2-VASc score was 3.8. 47% of the patients had experienced prior stroke or non-CNS SE or transient ischemic attack. 73.6% of the patients had CHADS2 score ≥ 2. Incidence proportions of 0.8% of the patients (1.1 per 100 patient-years) developed adjudicated treatment-emergent major bleeding. Death was observed in 1.2% of the patients. The incidence of non-major bleeding as well as thromboembolic event were 8.4% (11.6 per 100 patient-years) and 1.5% (2.0 per 100 patient-years), respectively. Conclusions This study reaffirmed the consistent safety profile of rivaroxaban. We found consistent results with overall XANAP population for rivaroxaban in terms of safety in non-valvular AF patients for the prevention of stroke and non-CNS SE.

Background: This study aims to investigate the current status of AF (atrial fibrillation) catheter ablation in Korea. Methods: The patients who underwent AF catheter ablation from September 2017 to December 2019 were pro‑ spectively enrolled from 37 arrhythmia centers. Demographic data, procedural characteristics, the extent of catheter ablation, acute success of the ablation lesion set, rate and independent risk factor for recurrence of AF were analyzed. Results: A total of 2402 AF patients [paroxysmal AF (PAF) 45.7%, persistent AF (PeAF) 43.1% and redo AF 11.2%] were included. Pulmonary vein isolation (PVI) was performed in 2378 patients (99%) and acute success rate was 97.9%.Additional non-PV ablation (NPVA) were performed in 1648 patients (68.6%). Post-procedural complication rate was 2.2%. One-year AF-free survival rate was 78.6% and the PeAF patients showed poorer survival rate than the ones with other types (PeAF 72.4%, PAF 84.2%, redo AF 80.0%). Additional NPVA did not influence the recurrence of AF in the PAF patients (PVI 17.0% vs. NPVA 14.6%, P value 0.302). However, it showed lower AF recurrence rate in the PeAF patients (PVI 34.9% vs. NPVA 24.4%, P value 0.001). Valvular heart disease, left atrial diameter, PeAF, PVI alone, need of NPVA for terminating AF, and failed ablation were independent predictors of AF recurrence. Conclusions Additional NPVA was associated better rhythm outcome in the patients with PeAF, not in the ones with PAF. The independent risk factors for AF recurrence in Korean population were similar to previous studies. Further research is needed to discover optimal AF ablation strategy.

Purpose: Nutritional status and support in critically ill patients are important factors in determining patient recovery and prognosis.The aim of this study was to analyze the early nutritional status and the methods of nutritional support in critically ill patients with acute poisoning and to evaluate the effect of nutritional status on prognosis. Methods: A retrospective study was conducted in tertiary care teaching hospital from January 2018 to December 2020. in an emergency department of university hospital, 220 patients who were stayed more than 2 days of poisoning in intensive care unit were enrolled. Results: 155 (70.5%) of patients with acute poisoning had low-risk in nutritional risk screening (NRS). Patients with malignancy had higher NRS (low risk 5.2%, moderate risk 18.5%, high risk 13.2%, p=0.024). Patients of 91.4% supplied nutrition via oral route or enteral route. Parenteral route for starting method of nutritional support were higher in patients with acute poisoning of herbicide or pesticide (medicine 3.2%, herbicide 13.8%, pesticide 22.2%, p=0.000). In multivariate logistic regression analysis, herbicide or pesticide intoxication, higher risk in NRS and sequential organ failure assessment over 4.5 were affecting factor on poor recovery at discharge. Conclusion NRS in patients intoxicated with herbicide or pesticide were higher than that in patients intoxicated with medicine intoxication. Enteral nutrition in patients intoxicated with herbicide or pesticide was less common. Initial NRS was correlated with recovery at discharge in patient with intoxication. It is expected to be helpful in finding patients with high-risk nutritional status in acute poisoning patients and establishing a treatment plan that can actively implement nutritional support.

Background/Aims: Atrial fibrillation (AF)-related stroke accounts for 20% of ischemic strokes. Rivaroxaban use in AF patients for preventing stroke and systemic embolism was approved in 2013 in Korea. This study was to investigate the safety and effectiveness of rivaroxaban use in Korean patients with non-valvular AF in a real-world setting. Methods: This was an analysis of the Korean patients in Xarelto for Prevention of Stroke in Patients with Atrial Fibrillation in Asia-Pacific (XANAP), which was a prospective, observational cohort study including patients with non-valvular AF starting rivaroxaban treatment to prevent stroke or non-central nervous system systemic embolism (non-CNS SE), conducted in 10 Asian countries. Results: A total of 844 patients were enrolled in the Korean portion of the XANAP study. In XANAP Korea, the mean age was 70.1 years and 62.6% were males. The mean CHADS2 score was 2.5 and the mean CHA2DS2-VASc score was 3.8. 47% of the patients had experienced prior stroke or non-CNS SE or transient ischemic attack. 73.6% of the patients had CHADS2 score ≥ 2. Incidence proportions of 0.8% of the patients (1.1 per 100 patient-years) developed adjudicated treatment-emergent major bleeding. Death was observed in 1.2% of the patients. The incidence of non-major bleeding as well as thromboembolic event were 8.4% (11.6 per 100 patient-years) and 1.5% (2.0 per 100 patient-years), respectively. Conclusions This study reaffirmed the consistent safety profile of rivaroxaban. We found consistent results with overall XANAP population for rivaroxaban in terms of safety in non-valvular AF patients for the prevention of stroke and non-CNS SE.

Since a novel beta-coronavirus, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) was first reported in December 2019, there has been a rapid global spread of the virus. Genomic surveillance was conducted on samples isolated from infected individuals to monitor the spread of genetic variants of SARS-CoV-2 in Korea. The Korea Disease Control and Prevention Agency performed whole genome sequencing of SARS-CoV-2 in Korea for 1 year (January 2020 to January 2021). A total of 2,488 SARSCoV-2 cases were sequenced (including 648 cases from abroad). Initially, the prevalent clades of SARSCoV-2 were the S and V clades, however, by March 2020, GH clade was the most dominant. Only international travelers were identified as having G or GR clades, and since the first variant 501Y.V1 was identified (from a traveler from the United Kingdom on December 22 nd , 2020), a total of 27 variants of 501Y.V1, 501Y.V2, and 484K.V2 have been classified (as of January 25 th , 2021). The results in this study indicated that quarantining of travelers entering Korea successfully prevented dissemination of the SARS-CoV-2 variants in Korea.

Background: Radiofrequency catheter ablation (RFCA) has been accepted as an efficient therapy for tachycardia, and substantial improvement in the outcomes of RFCA in pediatric patients has been seen. However, there is not enough data on the clinical outcomes of RFCA for ventricular tachycardia (VT) in pediatric patients. The objective of this study was to elucidate the efficacy and safety of RFCA for VT in pediatric patients. Methods: We performed a retrospective study involving 35 consecutive pediatric VT ablation procedures in 28 patients at a single institution. Results: The median age at ablation was 14.0 years (range 6.9–19.2 years). There were 24 patients with a structurally normal heart and four patients with congenital heart disease (CHD). The left ventricular posteroseptal area was the most common site of VT origin (22/28, 78.6%). However, there was an unusual case of VT which involved a papillary muscle as its origin. Acute success was achieved in 30 (85.7%) of 35 procedures. The recurrence rate after successful RFCA was 14.2% (5/35) at a median follow-up of 6.7 years (range 1.0–16.7 years). There were five procedural failures due to the inability to induce VT for complete mapping. Ultimately, long-term success was achieved in 27 patients (96.4%) after repeated procedures and no major complications occurred. Long-term success was associated with VT inducibility (p = < 0.001). Conclusions Difficulty in inducing VT for precise mapping was a significant obstacle to successful RFCA. RFCA was identified as safe and effective therapy to eliminate VT in the selected pediatric VT patients.

PURPOSE: Although quantification of amyloid positron emission tomography (PET) is important for evaluating patients with cognitive impairment, its routine clinical use is hampered by complicated preprocessing steps and required MRI. Here, we suggested a one-step quantification based on deep learning using native-space amyloid PET images of different radiotracers acquired from multiple centers. METHODS: Amyloid PET data of the Alzheimer Disease Neuroimaging Initiative (ADNI) were used for this study. A training/validation consists of 850 florbetapir PET images. Three hundred sixty-six florbetapir and 89 florbetaben PET images were used as test sets to evaluate the model. Native-space amyloid PET images were used as inputs, and the outputs were standardized uptake value ratios (SUVRs) calculated by the conventional MR-based method. RESULTS: The mean absolute errors (MAEs) of the composite SUVR were 0.040, 0.060, and 0.050 of training/validation and test sets for florbetapir PETand a test set for florbetaben PET, respectively. The agreement of amyloid positivity measured by Cohen's kappa for test sets of florbetapir and florbetaben PET were 0.87 and 0.89, respectively. CONCLUSION We suggest a one-step quantification method for amyloid PET via a deep learning model. The model is highly reliable to quantify the amyloid PET regardless of multicenter images and various radiotracers.