Background and Objectives: Voice disorders can significantly impact quality of life. This study evaluates the feasibility of using deep learning models to detect voice disorders using an opensource dataset.Materials and Method We utilized the Saarbrücken Voice Database, which contains 1231 voice recordings of various pathologies. Datasets were used for training (n=1036) and validation (n=195). Key vocal parameters, including fundamental frequency (F0), formants (F1, F2), harmonics-to-noise ratio, jitter, and shimmer, were analyzed. A convolutional neural network (CNN) was designed to classify voice recordings into normal, vox senilis, and laryngocele. Performance was assessed using precision, recall, F1-score, and accuracy. Results: The CNN model demonstrated high classification performance, with precision, recall, and F1-scores of 1.00 for normal and 0.99 for vox senilis and laryngocele. Accuracy reached 1.00 after 50 epochs and remained stable through 100 epochs. Time-frequency analysis supported the model’s ability to differentiate between classes. Conclusion This study highlights the potential of deep learning for voice disorder detection, achieving high accuracy and precision. Future research should address dataset diversity and realworld integration for broader clinical adoption.

Background and Objectives: Voice disorders can significantly impact quality of life. This study evaluates the feasibility of using deep learning models to detect voice disorders using an opensource dataset.Materials and Method We utilized the Saarbrücken Voice Database, which contains 1231 voice recordings of various pathologies. Datasets were used for training (n=1036) and validation (n=195). Key vocal parameters, including fundamental frequency (F0), formants (F1, F2), harmonics-to-noise ratio, jitter, and shimmer, were analyzed. A convolutional neural network (CNN) was designed to classify voice recordings into normal, vox senilis, and laryngocele. Performance was assessed using precision, recall, F1-score, and accuracy. Results: The CNN model demonstrated high classification performance, with precision, recall, and F1-scores of 1.00 for normal and 0.99 for vox senilis and laryngocele. Accuracy reached 1.00 after 50 epochs and remained stable through 100 epochs. Time-frequency analysis supported the model’s ability to differentiate between classes. Conclusion This study highlights the potential of deep learning for voice disorder detection, achieving high accuracy and precision. Future research should address dataset diversity and realworld integration for broader clinical adoption.

Background and Objectives: Voice disorders can significantly impact quality of life. This study evaluates the feasibility of using deep learning models to detect voice disorders using an opensource dataset.Materials and Method We utilized the Saarbrücken Voice Database, which contains 1231 voice recordings of various pathologies. Datasets were used for training (n=1036) and validation (n=195). Key vocal parameters, including fundamental frequency (F0), formants (F1, F2), harmonics-to-noise ratio, jitter, and shimmer, were analyzed. A convolutional neural network (CNN) was designed to classify voice recordings into normal, vox senilis, and laryngocele. Performance was assessed using precision, recall, F1-score, and accuracy. Results: The CNN model demonstrated high classification performance, with precision, recall, and F1-scores of 1.00 for normal and 0.99 for vox senilis and laryngocele. Accuracy reached 1.00 after 50 epochs and remained stable through 100 epochs. Time-frequency analysis supported the model’s ability to differentiate between classes. Conclusion This study highlights the potential of deep learning for voice disorder detection, achieving high accuracy and precision. Future research should address dataset diversity and realworld integration for broader clinical adoption.

Purpose: This study aimed to develop and assess the feasibility and effectiveness of digital therapeutics for supportive care after gastrectomy.Materials and Method: The study included 39 patients with gastric cancer who underwent minimally invasive gastrectomy and were able to use a mobile application (app) on their smartphones. The developed research app automatically calculates and provides daily targets for calorie and protein intake based on the patient’s body mass index (BMI). Patients recorded their daily diets, weights, and symptoms in the app and completed special questionnaires to assess the feasibility of the app in real-world clinical practice. Results: At the 10-week follow-up, the mean questionnaire scores for ease of learning, usability, and effectiveness of the app (primary endpoint) were 2.32±0.41, 2.35±0.43, and 2.4±0.39 (range: 0–3), respectively. Patients were classified as underweight (<18.5, n=4), normal (18.5–24.9, n=24), or overweight (≥25.0, n=11) according to predischarge BMI.Underweight patients showed higher compliance with app usage and a higher rate of achieving the target calorie and protein intake than normal weight and overweight patients (98% vs. 77% vs. 81%, p=0.0313; 102% vs. 75% vs. 61%, P=0.0111; 106% vs. 79% vs. 64%, P=0.0429). Two patients transitioned from underweight to normal weight (50.0%), one patient (4.3%) transitioned from normal weight to underweight, and two patients (22.2%) transitioned from overweight to normal weight. Conclusions The mobile app is feasible and useful for postoperative supportive care in terms of ease of learning, usability, and effectiveness. Digital therapeutics may be an effective way to provide supportive care for postgastrectomy patients, particularly in terms of nutrition.

Background: The benefits of transradial access (TRA) over transfemoral access (TFA) for bifurcation percutaneous coronary intervention (PCI) are uncertain because of the limited availability of device selection. This study aimed to compare the procedural differences and the in-hospital and long-term outcomes of TRA and TFA for bifurcation PCI using secondgeneration drug-eluting stents (DESs). Methods: Based on data from the Coronary Bifurcation Stenting Registry III, a retrospective registry of 2,648 patients undergoing bifurcation PCI with second-generation DES from 21 centers in South Korea, patients were categorized into the TRA group (n = 1,507) or the TFA group (n = 1,141). After propensity score matching (PSM), procedural differences, in-hospital outcomes, and device-oriented composite outcomes (DOCOs; a composite of cardiac death, target vessel-related myocardial infarction, and target lesion revascularization) were compared between the two groups (772 matched patients each group). Results: Despite well-balanced baseline clinical and lesion characteristics after PSM, the use of the two-stent strategy (14.2% vs. 23.7%, P = 0.001) and the incidence of in-hospital adverse outcomes, primarily driven by access site complications (2.2% vs. 4.4%, P = 0.015), were significantly lower in the TRA group than in the TFA group. At the 5-year follow-up, the incidence of DOCOs was similar between the groups (6.3% vs. 7.1%, P = 0.639). Conclusion The findings suggested that TRA may be safer than TFA for bifurcation PCI using second-generation DESs. Despite differences in treatment strategy, TRA was associated with similar long-term clinical outcomes as those of TFA. Therefore, TRA might be the preferred access for bifurcation PCI using second-generation DES.

Purpose: De novo malignancy is common after liver transplantation (LT); however, there are limited reports on the clinical outcomes of gastric cancer surgery after LT. Our study aimed to investigate the feasibility and safety of gastric cancer surgery after LT. Methods: Seventeen patients underwent gastric cancer surgery after LT at a single institution between January 2013 and June 2021. We retrospectively collected data on surgical complications, survival, and recurrence status of these cases. Results: Fifteen patients (88.2%) underwent curative gastrectomy, with 10 open distal (66.7%) and 5 laparoscopic distal (33.3%) gastrectomies. Surgical and severe complication rates were 3 of 15 (20.0%) and 1 of 15 (6.7%), respectively. There were no significant differences between laparoscopic (33.3%) and open surgery (66.7%) in terms of operation time and complication rate. No surgery-related mortalities occurred. Immunosuppressants could be maintained without difficulty, and no suspicious acute rejection was identified during the perioperative period. There was 1 recurrence after curative surgery (recurrence rate, 6.7%), and the 5-year cancer-specific survival rate after curative surgery was 93.3%. Conclusion Laparoscopic gastrectomy can be safely done even after LT in terms of postoperative complications and graft safety.

Background/Aims: This study aimed to evaluate the prevalence and natural progression of subepithelial lesions (SELs) in the upper gastrointestinal (UGI) tract. Methods: The medical records of patients with UGI SELs who underwent endoscopic screening at eight university hospitals between January and December 2010 were retrospectively investigated. The follow-up evaluations were performed until December 2016. Results: UGI SELs were found in 1,044 of the 65,233 participants screened (endoscopic prevalence, 1.60%; the total number of lesions, 1,062; mean age, 55.1±11.2 years; men, 53.6%). The median follow-up period was 48 (range, 8–74) months. SELs were most frequently found in the stomach (63.8%) and had a mean size of 9.9±6.1 mm. Endoscopic ultrasonography (EUS) was performed in 293 patients (28.1%). The most common lesions were leiomyomas, followed by gastrointestinal stromal tumors (GISTs), and ectopic pancreas. The proportions of SELs with malignant potential according to size were 3% (<1 cm), 22% (1–2 cm), 27% (2–3 cm), and 38% (≥3 cm). In gastric SELs larger than 1 cm, resections were performed in 20 patients because of an increase in size, of which 12 were found to be GISTs. Conclusions The prevalence of UGI SELs was 1.60%. Further, 23% of gastric SELs ≥1 cm were precancerous lesions, most followed by EUS and clinical decisions without initial pathological confirmation.

Background and Objectives: This study aimed to investigate the association between cardiovascular events and 2 different levels of elevated on-treatment diastolic blood pressures (DBP) in the presence of achieved systolic blood pressure targets (SBP). Methods: A nation-wide population-based cohort study comprised 237,592 patients with hypertension treated. The primary endpoint was a composite of cardiovascular death, myocardial infarction, and stroke. Elevated DBP was defined according to the Seventh Report of Joint National Committee (JNC7; SBP <140 mmHg, DBP ≥90 mmHg) or to the 2017 American College of Cardiology/American Heart Association (ACC/AHA) definitions (SBP <130 mmHg, DBP ≥80 mmHg). Results: During a median follow-up of 9 years, elevated on-treatment DBP by the JNC7 definition was associated with an increased risk of the occurrence of primary endpoint compared with achieved both SBP and DBP (adjusted hazard ratio [aHR], 1.14; 95% confidence interval [CI], 1.05–1.24) but not in those by the 2017 ACC/AHA definition. Elevated ontreatment DBP by the JNC7 definition was associated with a higher risk of cardiovascular mortality (aHR, 1.42; 95% CI, 1.18–1.70) and stroke (aHR, 1.19; 95% CI, 1.08–1.30). Elevated on-treatment DBP by the 2017 ACC/AHA definition was only associated with stroke (aHR, 1.10;95% CI, 1.04–1.16). Similar results were seen in the propensity-score-matched cohort. Conclusion Elevated on-treatment DBP by the JNC7 definition was associated a high risk of major cardiovascular events, while elevated DBP by the 2017 ACC/AHA definition was only associated with a higher risk of stroke. The result of study can provide evidence of DBP targets in subjects who achieved SBP targets.

Background/Aims: While switching strategies of P2Y12 receptor inhibitors (RIs) have sometimes been used in acute myocardial infarction (AMI) patients, the current status of in-hospital P2Y12RI switching remains unknown. Methods: Overall, 8,476 AMI patients who underwent successful revascularization from Korea Acute Myocardial Infarction Registry-National Institute of Health (KAMIR-NIH) were divided according to in-hospital P2Y12RI strategies, and net adverse cardiovascular events (NACEs), defined as a composite of cardiac death, non-fatal myocardial infarction (MI), stroke, or thrombolysis in myocardial infarction (TIMI) major bleeding during hospitalization were compared. Results: Patients with in-hospital P2Y12RI switching accounted for 16.5%, of which 867 patients were switched from clopidogrel to potent P2Y12RI (C-P) and 532 patients from potent P2Y12RI to clopidogrel (P-C). There were no differences in NACEs among the unchanged clopidogrel, the unchanged potent P2Y12RIs, and the P2Y12RI switching groups. However, compared to the unchanged clopidogrel group, the C-P group had a higher incidence of non-fatal MI, and the P-C group had a higher incidence of TIMI major bleeding. In clinical events of in-hospital P2Y12RI switching, 90.9% of non-fatal MI occurred during pre-switching clopidogrel administration, 60.7% of TIMI major bleeding was related to pre-switching P2Y12RIs, and 71.4% of TIMI major bleeding was related to potent P2Y12RIs. Only 21.6% of the P2Y12RI switching group switched to P2Y12RIs after a loading dose (LD); however, there were no differences in clinical events between patients with and without LD. Conclusions In-hospital P2Y12RI switching occurred occasionally, but had relatively similar clinical outcomes compared to unchanged P2Y12RIs in Korean AMI patients. Non-fatal MI and bleeding appeared to be mainly related to pre-switching P2Y12RIs.

BACKGROUND AND OBJECTIVES: There is a paucity of data regarding the benefit of clopidogrel monotherapy after dual antiplatelet therapy (DAPT) in patients treated with drug-eluting stents (DES). This study compared outcome between clopidogrel versus aspirin as monotherapy after DES for acute myocardial infarction (MI). METHODS: From Korea Acute Myocardial Infarction Registry-National Institute of Health database, 1,819 patients treated with DES who were switched to monotherapy with clopidogrel (n=534) or aspirin (n=1,285) after uneventful 12-month DAPT were analyzed. The primary endpoint was net adverse clinical events (NACE), defined as a composite of death from any cause, MI, repeat percutaneous coronary intervention (PCI), stent thrombosis, ischemic stroke, or major bleeding during the period from 12 to 24 months. RESULTS: After adjustment using inverse probability of treatment weighting, patients who received clopidogrel, compared with those treated with aspirin, had a similar incidence of NACE (0.7% and 0.7%; hazard ratio, 1.06; 95% confidence interval, 0.31–3.60; p=0.923). The 2 groups had similar rates of death from any cause (0.1% in each group, p=0.789), MI (0.3% and 0.1%, respectively; p=0.226), repeat PCI (0.1% and 0.3%, respectively; p=0.548), stent thrombosis (0.1% and 0%, respectively; p=0.121), major bleeding (0.2% in each group, p=0.974), and major adverse cardiovascular and cerebrovascular events (0.5% in each group, p=0.924). CONCLUSIONS Monotherapy with clopidogrel, compared to aspirin, after DAPT showed similar clinical outcomes in patients with acute MI treated with DES.