Purpose: This study aimed to develop and evaluate machine learning models, specifically CatBoost and extreme gradient boosting (XGBoost), for diagnosing lower urinary tract symptoms (LUTS) in male patients. The objective is to differentiate between bladder outlet obstruction (BOO) and detrusor underactivity (DUA) using a comprehensive dataset that includes patient-reported outcomes, uroflowmetry measurements, and ultrasound-derived features. Methods: The dataset used in this study was collected from male patients aged 40 and older who presented with LUTS and sought treatment at the urology department of Samsung Medical Center. We developed and trained CatBoost and XGBoost models using this dataset. These models incorporated features like prostate size, voiding parameters, and responses from questionnaires. Their performance was assessed using standard metrics such as accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUROC). Results: The results indicated that the CatBoost models displayed greater sensitivity, rendering them effective for initial screenings by accurately identifying true positive cases. Conversely, the XGBoost models showed higher specificity and precision, making them more suitable for confirming diagnoses and reducing false positives. In terms of overall performance for both BOO and DUA, XGBoost surpassed CatBoost, achieving an AUROC of 0.826 and 0.819, respectively. Conclusions Integrating these machine learning models into the diagnostic workflow for LUTS can significantly enhance clinical decision-making by offering noninvasive, cost-effective, and patient-friendly diagnostic alternatives. The combined application of CatBoost and XGBoost models has the potential to improve diagnostic accuracy and provide customized treatment plans for patients, ultimately leading to better clinical outcomes.

Purpose: This study aimed to develop and evaluate machine learning models, specifically CatBoost and extreme gradient boosting (XGBoost), for diagnosing lower urinary tract symptoms (LUTS) in male patients. The objective is to differentiate between bladder outlet obstruction (BOO) and detrusor underactivity (DUA) using a comprehensive dataset that includes patient-reported outcomes, uroflowmetry measurements, and ultrasound-derived features. Methods: The dataset used in this study was collected from male patients aged 40 and older who presented with LUTS and sought treatment at the urology department of Samsung Medical Center. We developed and trained CatBoost and XGBoost models using this dataset. These models incorporated features like prostate size, voiding parameters, and responses from questionnaires. Their performance was assessed using standard metrics such as accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUROC). Results: The results indicated that the CatBoost models displayed greater sensitivity, rendering them effective for initial screenings by accurately identifying true positive cases. Conversely, the XGBoost models showed higher specificity and precision, making them more suitable for confirming diagnoses and reducing false positives. In terms of overall performance for both BOO and DUA, XGBoost surpassed CatBoost, achieving an AUROC of 0.826 and 0.819, respectively. Conclusions Integrating these machine learning models into the diagnostic workflow for LUTS can significantly enhance clinical decision-making by offering noninvasive, cost-effective, and patient-friendly diagnostic alternatives. The combined application of CatBoost and XGBoost models has the potential to improve diagnostic accuracy and provide customized treatment plans for patients, ultimately leading to better clinical outcomes.

Purpose: This study aimed to develop and evaluate machine learning models, specifically CatBoost and extreme gradient boosting (XGBoost), for diagnosing lower urinary tract symptoms (LUTS) in male patients. The objective is to differentiate between bladder outlet obstruction (BOO) and detrusor underactivity (DUA) using a comprehensive dataset that includes patient-reported outcomes, uroflowmetry measurements, and ultrasound-derived features. Methods: The dataset used in this study was collected from male patients aged 40 and older who presented with LUTS and sought treatment at the urology department of Samsung Medical Center. We developed and trained CatBoost and XGBoost models using this dataset. These models incorporated features like prostate size, voiding parameters, and responses from questionnaires. Their performance was assessed using standard metrics such as accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUROC). Results: The results indicated that the CatBoost models displayed greater sensitivity, rendering them effective for initial screenings by accurately identifying true positive cases. Conversely, the XGBoost models showed higher specificity and precision, making them more suitable for confirming diagnoses and reducing false positives. In terms of overall performance for both BOO and DUA, XGBoost surpassed CatBoost, achieving an AUROC of 0.826 and 0.819, respectively. Conclusions Integrating these machine learning models into the diagnostic workflow for LUTS can significantly enhance clinical decision-making by offering noninvasive, cost-effective, and patient-friendly diagnostic alternatives. The combined application of CatBoost and XGBoost models has the potential to improve diagnostic accuracy and provide customized treatment plans for patients, ultimately leading to better clinical outcomes.

Adult-onset Still’s disease (AOSD) is a rare systemic inflammatory disease characterized by spiking fever, arthralgia, skin rashes, and hyperferritinemia. The rash is usually salmon-colored, non-itchy, accompanied by fever, and disappears with an improvement of fever. However, in some cases, the rash persisted regardless of fever. Here, we present a case of AOSD with an atypical persistent rash that showed histological findings resembling those of neutrophilic urticarial dermatosis. The patient was a 60-year-old woman with high fever, arthralgia, and a persistent flagellated skin rash. Despite systemic steroid treatment, the patient developed a serious complication: macrophage activation syndrome. Since this case presented with an atypical persistent rash with histological resemblance to neutrophilic urticarial dermatosis, we report its contribution to the further study of AOSD.

Background/Aims: Global distribution of dominant liver cancer aetiologies has significantly changed over the past decades. This study analyzed the updated temporal trends of liver cancer aetiologies and sociodemographic status in 204 countries and territories from 1990 to 2019. Methods: The Global Burden of Disease 2019 report was used for statistical analysis. In addition, we performed stratification analysis to five quintiles using sociodemographic index and 21 geographic regions. Results: The crude numbers of liver cancer disease-adjusted life years (DALYs) and deaths significantly increased during the study period (DALYs; 11,278,630 in 1990 and 12,528,422 in 2019, deaths; 365,215 in 1990 and 484,577 in 2019). However, the Age-standardized DALY and mortality rates decreased. Hepatitis B virus (HBV) remains the leading cause of liver cancer DALYs and mortality, followed by hepatitis C virus (HCV), alcohol consumption, and non-alcoholic steatohepatitison-alcoholic fatty liver disease (NASH/NAFLD). Although Age-standardized DALY and mortality rates of liver cancer due to HBV and HCV have decreased, the rates due to alcohol consumption and NASH/NAFLD have increased. In 2019, the population of the East Asia region had the highest Age-standardized DALY and mortality rates, followed by high-income Asia-Pacific and Central Asia populations. Although East Asia and high-income Asia-Pacific regions showed a decrease during the study period, Age-standardized DALY rates increased in Central Asia. High-income North American and Australasian populations also showed a significant increase in Age-standardized DALY. Conclusions Liver cancer remains an ongoing global threat. The burden of liver cancer associated with alcohol consumption and NASH/NAFLD is markedly increasing and projected to continuously increase.

Humans ; Adolescent ; Pandemics ; Substance-Related Disorders/epidemiology* ; Smoking ; Ethanol ; Republic of Korea/epidemiology* ; Alcohol Drinking/epidemiology*

Background: Dapsone has been used for a long time to treat skin diseases. Although various drug-related side effects and adverse reactions to dapsone have been reported, most studies have addressed only one or two specific reactions to dapsone. Objective: This study aimed to investigate the overall adverse reactions to dapsone in Koreans and their relationship with patient demographics. Methods: A retrospective analysis was conducted by reviewing the electronic medical records from 2005 to 2020. The association between adverse drug reactions and dapsone use was assessed using the Naranjo scale. Correlations between variables and adverse reactions were analyzed using univariate and logistic regression analyses. Results: The overall incidence of adverse drug reactions to dapsone was 7.7% (41 of 533 patients). The incidence was significantly higher in female than in male, and predictable adverse reactions were significantly higher (6.8%, 36 of 533 patients) than in unpredictable cases (0.9%, 5 of 533 patients). The most common adverse event was methemoglobinemia/anemia (3.0%, 16 of 533 patients), and the least common was hypersensitivity syndrome, which occurred in only one case (0.2%, 1 of 533 patients). With the exception of hypersensitivity syndrome, which is a severe drug-related side effects and adverse reactions, most patients recovered after drug discontinuation. Conclusion Dapsone can be used relatively safely for various chronic diseases if medical personnel are aware of its adverse reactions.