Background: The diagnosis of major depressive disorder (MDD) relies primarily on clinical interviews, which can be subjective and time consuming. Thus, there is a need for more objective diagnostic tools. The aim of this study was to develop an artificial intelligence (AI) application that predicts the antidepressant drug response of individual patients with MDD based on longitudinal data. Methods: Longitudinal data from patient records, including sex, age, outpatient or inpatient status, medication type and dosage, and the Hamilton Depression Rating Scale (HAMD) scores, were used to train the Transformer model and the 1-dimensional convolutional neural network model. Individual patient records were allocated to training (80%), validation (10%), and testing (10%) datasets. Results: The AI model demonstrated 88% sensitivity and 92% specificity for predicting the treatment response. Significant factors independently associated with the antidepressant response included age, sex, history of depression, and baseline HAMD scores. Conclusion This AI-driven software application provides a clinically valuable tool for predicting treatment response.While promising, further research is needed to incorporate voice data into the AI model using the voice recording feature to further improve diagnostic accuracy.

Background: The diagnosis of major depressive disorder (MDD) relies primarily on clinical interviews, which can be subjective and time consuming. Thus, there is a need for more objective diagnostic tools. The aim of this study was to develop an artificial intelligence (AI) application that predicts the antidepressant drug response of individual patients with MDD based on longitudinal data. Methods: Longitudinal data from patient records, including sex, age, outpatient or inpatient status, medication type and dosage, and the Hamilton Depression Rating Scale (HAMD) scores, were used to train the Transformer model and the 1-dimensional convolutional neural network model. Individual patient records were allocated to training (80%), validation (10%), and testing (10%) datasets. Results: The AI model demonstrated 88% sensitivity and 92% specificity for predicting the treatment response. Significant factors independently associated with the antidepressant response included age, sex, history of depression, and baseline HAMD scores. Conclusion This AI-driven software application provides a clinically valuable tool for predicting treatment response.While promising, further research is needed to incorporate voice data into the AI model using the voice recording feature to further improve diagnostic accuracy.

Background: The diagnosis of major depressive disorder (MDD) relies primarily on clinical interviews, which can be subjective and time consuming. Thus, there is a need for more objective diagnostic tools. The aim of this study was to develop an artificial intelligence (AI) application that predicts the antidepressant drug response of individual patients with MDD based on longitudinal data. Methods: Longitudinal data from patient records, including sex, age, outpatient or inpatient status, medication type and dosage, and the Hamilton Depression Rating Scale (HAMD) scores, were used to train the Transformer model and the 1-dimensional convolutional neural network model. Individual patient records were allocated to training (80%), validation (10%), and testing (10%) datasets. Results: The AI model demonstrated 88% sensitivity and 92% specificity for predicting the treatment response. Significant factors independently associated with the antidepressant response included age, sex, history of depression, and baseline HAMD scores. Conclusion This AI-driven software application provides a clinically valuable tool for predicting treatment response.While promising, further research is needed to incorporate voice data into the AI model using the voice recording feature to further improve diagnostic accuracy.

Background: The diagnosis of major depressive disorder (MDD) relies primarily on clinical interviews, which can be subjective and time consuming. Thus, there is a need for more objective diagnostic tools. The aim of this study was to develop an artificial intelligence (AI) application that predicts the antidepressant drug response of individual patients with MDD based on longitudinal data. Methods: Longitudinal data from patient records, including sex, age, outpatient or inpatient status, medication type and dosage, and the Hamilton Depression Rating Scale (HAMD) scores, were used to train the Transformer model and the 1-dimensional convolutional neural network model. Individual patient records were allocated to training (80%), validation (10%), and testing (10%) datasets. Results: The AI model demonstrated 88% sensitivity and 92% specificity for predicting the treatment response. Significant factors independently associated with the antidepressant response included age, sex, history of depression, and baseline HAMD scores. Conclusion This AI-driven software application provides a clinically valuable tool for predicting treatment response.While promising, further research is needed to incorporate voice data into the AI model using the voice recording feature to further improve diagnostic accuracy.

Background: The diagnosis of major depressive disorder (MDD) relies primarily on clinical interviews, which can be subjective and time consuming. Thus, there is a need for more objective diagnostic tools. The aim of this study was to develop an artificial intelligence (AI) application that predicts the antidepressant drug response of individual patients with MDD based on longitudinal data. Methods: Longitudinal data from patient records, including sex, age, outpatient or inpatient status, medication type and dosage, and the Hamilton Depression Rating Scale (HAMD) scores, were used to train the Transformer model and the 1-dimensional convolutional neural network model. Individual patient records were allocated to training (80%), validation (10%), and testing (10%) datasets. Results: The AI model demonstrated 88% sensitivity and 92% specificity for predicting the treatment response. Significant factors independently associated with the antidepressant response included age, sex, history of depression, and baseline HAMD scores. Conclusion This AI-driven software application provides a clinically valuable tool for predicting treatment response.While promising, further research is needed to incorporate voice data into the AI model using the voice recording feature to further improve diagnostic accuracy.

There are limited data on outcomes after implantation of everolimus-eluting stents (EES) in East Asian patients with small vessel coronary lesions. A total of 1,600 patients treated with XIENCE EES (Abbott Vascular, CA, USA) were divided into the small vessel group treated with one ≤2.5 mm stent (n=119) and the non-small vessel group treated with one ≥2.75 mm stent (n=933). The primary end point was a patient-oriented composite outcome (POCO), a composite of all-cause death, myocardial infarction (MI), and any repeat revascularization at 12 months. The key secondary end point was a device-oriented composite outcome (DOCO), a composite of cardiovascular death, target-vessel MI, and target lesion revascularization at 12 months. The small vessel group was more often female, hypertensive, less likely to present with ST-elevation MI, and more often treated for the left circumflex artery, whereas the non-small vessel group more often had type B2/C lesions, underwent intravascular ultrasound, and received unfractionated heparin. In the propensity matched cohort, the mean stent diameter was 2.5±0.0 mm and 3.1±0.4 mm in the small and non-small vessel groups, respectively. Propensity-adjusted POCO at 12 months was 6.0% in the small vessel group and 4.3% in the non-small vessel group (p=0.558). There was no significant difference in DOCO at 12 months (small vessel group: 4.3% and non-small vessel group: 1.7%, p=0.270).Outcomes of XIENCE EES for small vessel disease were comparable to those for non-small vessel disease at 12-month clinical follow-up in real-world Korean patients.

Purpose: We sought to assess mortality trends in chest-abdominal trauma patients, before and after the implementation of the Project Supporting Establishment of Trauma Centers (PSETC) in the Republic of Korea. Methods: Data from the National Health Insurance Service claims database between 2009 to 2017 were analyzed. Patients with chest-abdominal trauma were defined as those with relevant main diagnosis codes and claims for emergency medical management fees. Mortality and cumulative data were analyzed for each year to compare mortality before and after the establishment of regional trauma centers across Korea (2014). Results: In total, 29,127 patients were included in the analysis. While the annual incidence of trauma-related chest-abdominal injuries increased, mortalities decreased. In particular, the trauma incidence rate among patients over 50 years increased during the study period. Mortalities at trauma centers did not change year by year after the PSETC. Before and after 2014, when trauma centers operated under the PSETC, mortalities decreased [trauma cases before the PSETC; n = 14,321 (mortality 5.61), after the PSETC; n = 14,806 (mortality 4.96)]. Conclusion The number of patients treated for chest-abdominal injuries increased from 2009 to 2017 in Korea, whereas mortalities decreased over the same period.

Background: Blood pressure readings taken before anesthesia often influence the decision to delay or cancel elective surgeries. However, the implications of these specific blood pressure values, especially how they compare to baseline, on postoperative in-hospital 30-day mortality remain underexplored. This research aimed to examine the effect of discrepancies between the baseline blood pressure evaluated in the ward a day before surgery, and the blood pressure observed just before the administration of anesthesia, on the postoperative mortality risks. Methods: The study encompassed 60,534 adults scheduled for non-cardiac surgeries at a tertiary care center in Seoul, Korea. Baseline blood pressure was calculated as the mean of the blood pressure readings taken within 24 hours prior to surgery. The preanesthetic blood pressure was the blood pressure measured right before the administration of anesthesia. We focused on in-hospital 30-day mortality as the primary outcome. Results: Our research revealed that a lower preanesthetic systolic or mean blood pressure that deviates by 20 mmHg or more from baseline significantly increased the risk of 30-day mortality. This association was particularly pronounced in individuals with a history of hypertension and those aged 65 and above. Higher preanesthetic blood pressure was not significantly associated with an increased risk of 30-day mortality. Conclusion We found that a lower preanesthetic blood pressure compared to baseline significantly increased the 30-day postoperative mortality risk, whereas a higher preanesthetic blood pressure did not. Our study emphasizes the critical importance of accounting for variations in both baseline and preanesthetic blood pressure when assessing surgical risks and outcomes.

Background: Aortic arch (AA) branching patterns vary among different mammalian species.Most previous studies have focused on dogs, whereas those on raccoon dogs remain unexplored. Objectives: The objective of this study was to describe the AA branching pattern in raccoon dogs and compare their morphological features with those of other carnivores. Methods: We prepared silicone cast specimens from a total of 36 raccoon dog carcasses via retrograde injection through the abdominal aorta. The brachiocephalic trunk (BCT) branching patterns were classified based on the relationship between the left and right common carotid arteries. The subclavian artery (SB) branching pattern was examined based on the order of the four major branches: the vertebral artery (VT), costocervical trunk (CCT), superficial cervical artery (SC), and internal thoracic artery (IT). Results: In most cases (88.6%), the BCT branched off from the left common carotid artery and terminated in the right common carotid and right subclavian arteries. In the remaining cases (11.4%), the BCT formed a bicarotid trunk. The SB exhibited various branching patterns, with 26 observed types. Based on the branching order of the four major branches, we identified the main branching pattern, in which the VT branched first (98.6%), the CCT branched second (81.9%), the SC branched third (62.5%), and the IT branched fourth (52.8%). Conclusions The AA branching pattern in raccoon dogs exhibited various branching patterns with both similarities and differences compared to other carnivores.

Purpose: Cysteinyl leukotrienes (CysLTs) have been recognized as key mediators associated with type 2 inflammation in the airways of asthmatic patients. CysLTs are associated with airway constriction, eosinophil recruitment/activation, and airway remodeling. The study aimed to understand the role of CysLTs in adult asthmatics in a real-world clinical setting. Methods: One hundred five adult asthmatics who had maintained antiasthmatic medications were enrolled. Asthmatic subjects were classified into 2 groups according to urinary leukotriene E4 (uLTE4) levels, and their clinical parameters and inflammatory mediators, including forced expiratory volume in 1 second (FEV1) %, fractional exhaled nitric oxide (FeNO), blood eosinophil count, serum periostin (sPON), and urinary eosinophil derived neurotoxin (uEDN) were compared between the high-uLTE4 and low-uLTE4 groups. Results: The prevalence of chronic rhinosinusitis (CRS), severe asthma, and aspirin-exacerbated respiratory disease (AERD) were significantly higher in the high-uLTE4 group than in the low-uLTE4 group. The high-uLTE4 group had lower FEV1% and maximal midexpiratory flow %, but higher FeNO levels than the low-uLTE4 group. In addition, blood eosinophil count, sPON, and uEDN levels were significantly higher in the high-uLTE4 group than in the low-uLTE4 group. The presence of AERD and levels of FeNO, sPON, and uEDN were significantly associated with higher uLTE4 levels in asthmatics. Conclusion CysLTs are associated with type 2 inflammation in the airways of asthmatic patients, contributing to the development of AERD, CRS, and asthma severity. The stratification of clinical phenotypes according to the uLTE4 level could support optimizing anti-inflammatory therapy for better control of asthma.