Background: and Purpose Previous research on patients with acute ischemic stroke (AIS) has shown a 0.5% incidence of major gastrointestinal bleeding (GIB) requiring blood transfusion during hospitalization. The existing literature has insufficiently explored the long-term incidence in this population despite the decremental impact of GIB on stroke outcomes. Methods: We analyzed the data from a cohort of patients with AIS admitted to 14 hospitals as part of a nationwide multicenter prospective stroke registry between 2011 and 2013. These patients were followed up for up to 6 years. The occurrence of major GIB events, defined as GIB necessitating at least two units of blood transfusion, was tracked using the National Health Insurance Service claims data. Results: Among 10,818 patients with AIS (male, 59%; mean age, 68±13 years), 947 (8.8%) experienced 1,224 episodes of major GIB over a median follow-up duration of 3.1 years. Remarkably, 20% of 947 patients experienced multiple episodes of major GIB. The incidence peaked in the first month after AIS, reaching 19.2 per 100 person-years, and gradually decreased to approximately one-sixth of this rate by the 2nd year with subsequent stabilization. Multivariable analysis identified the following predictors of major GIB: anemia, estimated glomerular filtration rate <60 mL/min/1.73 m2 , and a 3-month modified Rankin Scale score of ≥4. Conclusion Patients with AIS are susceptible to major GIB, particularly in the first month after the onset of AIS, with the risk decreasing thereafter. Implementing preventive strategies may be important, especially for patients with anemia and impaired renal function at stroke onset and those with a disabling stroke.

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 Purpose Previous research on patients with acute ischemic stroke (AIS) has shown a 0.5% incidence of major gastrointestinal bleeding (GIB) requiring blood transfusion during hospitalization. The existing literature has insufficiently explored the long-term incidence in this population despite the decremental impact of GIB on stroke outcomes. Methods: We analyzed the data from a cohort of patients with AIS admitted to 14 hospitals as part of a nationwide multicenter prospective stroke registry between 2011 and 2013. These patients were followed up for up to 6 years. The occurrence of major GIB events, defined as GIB necessitating at least two units of blood transfusion, was tracked using the National Health Insurance Service claims data. Results: Among 10,818 patients with AIS (male, 59%; mean age, 68±13 years), 947 (8.8%) experienced 1,224 episodes of major GIB over a median follow-up duration of 3.1 years. Remarkably, 20% of 947 patients experienced multiple episodes of major GIB. The incidence peaked in the first month after AIS, reaching 19.2 per 100 person-years, and gradually decreased to approximately one-sixth of this rate by the 2nd year with subsequent stabilization. Multivariable analysis identified the following predictors of major GIB: anemia, estimated glomerular filtration rate <60 mL/min/1.73 m2 , and a 3-month modified Rankin Scale score of ≥4. Conclusion Patients with AIS are susceptible to major GIB, particularly in the first month after the onset of AIS, with the risk decreasing thereafter. Implementing preventive strategies may be important, especially for patients with anemia and impaired renal function at stroke onset and those with a disabling stroke.

Background: High-resolution chest computed tomography (CT) is a crucial assessment tool for diagnosing Birt-Hogg-Dubé (BHD) syndrome. This study aimed to analyze differences of lung cysts between BHD and other cystic lung diseases. Methods: From January 2020 to December 2022, patients with multiple lung cysts who underwent chest CT at Gangnam Severance Hospital were included. Results: Over a 3-year period (from January 2020 to December 2022), out of 52,823 patients who underwent a chest CT scan, 301 (0.6%) patients with multiple lung cysts were enrolled in this study. Of enrolled patients, 24 (8.0%) were diagnosed with BHD. In patients with BHD, 95.8% exhibited bilateral cysts, and 83.3% showed basal predominance. The cysts’ maximal diameter averaged 32.1 mm (interquartile range, 26.5 to 43.5). Additionally, 95.8% of patients with BHD had diverse cyst sizes and morphologies. Multivariate logistic regression analysis revealed that bilateral cysts (odds ratio [OR], 12.393; 95% confidence interval [CI], 1.613 to 274.682; p=0.038), basal predominance (OR, 8.511; 95% CI, 2.252 to 39.392; p=0.002), maximum diameter (OR, 1.053; 95% CI, 1.009 to 1.108; p=0.032), and diversity of morphology (OR, 19.513; 95% CI, 2.833 to 398.119; p=0.010) were significant factors associated with BHD diagnosis. A multivariate prediction model for BHD diagnosis demonstrated a sensitivity of 95.83%, a specificity of 81.22%, and an area under the receiver operating characteristic curve of 0.951 (95% CI, 0.914 to 0.987). Conclusion Distinguishing features of lung cysts from other cystic lung diseases include bilateral cysts, basal dominance, large size, and irregular shape.

Background: and Purpose Previous research on patients with acute ischemic stroke (AIS) has shown a 0.5% incidence of major gastrointestinal bleeding (GIB) requiring blood transfusion during hospitalization. The existing literature has insufficiently explored the long-term incidence in this population despite the decremental impact of GIB on stroke outcomes. Methods: We analyzed the data from a cohort of patients with AIS admitted to 14 hospitals as part of a nationwide multicenter prospective stroke registry between 2011 and 2013. These patients were followed up for up to 6 years. The occurrence of major GIB events, defined as GIB necessitating at least two units of blood transfusion, was tracked using the National Health Insurance Service claims data. Results: Among 10,818 patients with AIS (male, 59%; mean age, 68±13 years), 947 (8.8%) experienced 1,224 episodes of major GIB over a median follow-up duration of 3.1 years. Remarkably, 20% of 947 patients experienced multiple episodes of major GIB. The incidence peaked in the first month after AIS, reaching 19.2 per 100 person-years, and gradually decreased to approximately one-sixth of this rate by the 2nd year with subsequent stabilization. Multivariable analysis identified the following predictors of major GIB: anemia, estimated glomerular filtration rate <60 mL/min/1.73 m2 , and a 3-month modified Rankin Scale score of ≥4. Conclusion Patients with AIS are susceptible to major GIB, particularly in the first month after the onset of AIS, with the risk decreasing thereafter. Implementing preventive strategies may be important, especially for patients with anemia and impaired renal function at stroke onset and those with a disabling stroke.

Background: High-resolution chest computed tomography (CT) is a crucial assessment tool for diagnosing Birt-Hogg-Dubé (BHD) syndrome. This study aimed to analyze differences of lung cysts between BHD and other cystic lung diseases. Methods: From January 2020 to December 2022, patients with multiple lung cysts who underwent chest CT at Gangnam Severance Hospital were included. Results: Over a 3-year period (from January 2020 to December 2022), out of 52,823 patients who underwent a chest CT scan, 301 (0.6%) patients with multiple lung cysts were enrolled in this study. Of enrolled patients, 24 (8.0%) were diagnosed with BHD. In patients with BHD, 95.8% exhibited bilateral cysts, and 83.3% showed basal predominance. The cysts’ maximal diameter averaged 32.1 mm (interquartile range, 26.5 to 43.5). Additionally, 95.8% of patients with BHD had diverse cyst sizes and morphologies. Multivariate logistic regression analysis revealed that bilateral cysts (odds ratio [OR], 12.393; 95% confidence interval [CI], 1.613 to 274.682; p=0.038), basal predominance (OR, 8.511; 95% CI, 2.252 to 39.392; p=0.002), maximum diameter (OR, 1.053; 95% CI, 1.009 to 1.108; p=0.032), and diversity of morphology (OR, 19.513; 95% CI, 2.833 to 398.119; p=0.010) were significant factors associated with BHD diagnosis. A multivariate prediction model for BHD diagnosis demonstrated a sensitivity of 95.83%, a specificity of 81.22%, and an area under the receiver operating characteristic curve of 0.951 (95% CI, 0.914 to 0.987). Conclusion Distinguishing features of lung cysts from other cystic lung diseases include bilateral cysts, basal dominance, large size, and irregular shape.

Background: High-resolution chest computed tomography (CT) is a crucial assessment tool for diagnosing Birt-Hogg-Dubé (BHD) syndrome. This study aimed to analyze differences of lung cysts between BHD and other cystic lung diseases. Methods: From January 2020 to December 2022, patients with multiple lung cysts who underwent chest CT at Gangnam Severance Hospital were included. Results: Over a 3-year period (from January 2020 to December 2022), out of 52,823 patients who underwent a chest CT scan, 301 (0.6%) patients with multiple lung cysts were enrolled in this study. Of enrolled patients, 24 (8.0%) were diagnosed with BHD. In patients with BHD, 95.8% exhibited bilateral cysts, and 83.3% showed basal predominance. The cysts’ maximal diameter averaged 32.1 mm (interquartile range, 26.5 to 43.5). Additionally, 95.8% of patients with BHD had diverse cyst sizes and morphologies. Multivariate logistic regression analysis revealed that bilateral cysts (odds ratio [OR], 12.393; 95% confidence interval [CI], 1.613 to 274.682; p=0.038), basal predominance (OR, 8.511; 95% CI, 2.252 to 39.392; p=0.002), maximum diameter (OR, 1.053; 95% CI, 1.009 to 1.108; p=0.032), and diversity of morphology (OR, 19.513; 95% CI, 2.833 to 398.119; p=0.010) were significant factors associated with BHD diagnosis. A multivariate prediction model for BHD diagnosis demonstrated a sensitivity of 95.83%, a specificity of 81.22%, and an area under the receiver operating characteristic curve of 0.951 (95% CI, 0.914 to 0.987). Conclusion Distinguishing features of lung cysts from other cystic lung diseases include bilateral cysts, basal dominance, large size, and irregular shape.

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: High-resolution chest computed tomography (CT) is a crucial assessment tool for diagnosing Birt-Hogg-Dubé (BHD) syndrome. This study aimed to analyze differences of lung cysts between BHD and other cystic lung diseases. Methods: From January 2020 to December 2022, patients with multiple lung cysts who underwent chest CT at Gangnam Severance Hospital were included. Results: Over a 3-year period (from January 2020 to December 2022), out of 52,823 patients who underwent a chest CT scan, 301 (0.6%) patients with multiple lung cysts were enrolled in this study. Of enrolled patients, 24 (8.0%) were diagnosed with BHD. In patients with BHD, 95.8% exhibited bilateral cysts, and 83.3% showed basal predominance. The cysts’ maximal diameter averaged 32.1 mm (interquartile range, 26.5 to 43.5). Additionally, 95.8% of patients with BHD had diverse cyst sizes and morphologies. Multivariate logistic regression analysis revealed that bilateral cysts (odds ratio [OR], 12.393; 95% confidence interval [CI], 1.613 to 274.682; p=0.038), basal predominance (OR, 8.511; 95% CI, 2.252 to 39.392; p=0.002), maximum diameter (OR, 1.053; 95% CI, 1.009 to 1.108; p=0.032), and diversity of morphology (OR, 19.513; 95% CI, 2.833 to 398.119; p=0.010) were significant factors associated with BHD diagnosis. A multivariate prediction model for BHD diagnosis demonstrated a sensitivity of 95.83%, a specificity of 81.22%, and an area under the receiver operating characteristic curve of 0.951 (95% CI, 0.914 to 0.987). Conclusion Distinguishing features of lung cysts from other cystic lung diseases include bilateral cysts, basal dominance, large size, and irregular shape.

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.