Purpose: Semantic segmentation is a fundamental part of the surgical application of deep learning. Traditionally, segmentation in vision tasks has been performed using convolutional neural networks (CNNs), but the transformer architecture has recently been introduced and widely investigated. We aimed to investigate the performance of deep learning models in segmentation in robot-assisted radical prostatectomy (RARP) and identify which of the architectures is superior for segmentation in robotic surgery. Materials and Methods: Intraoperative images during RARP were obtained. The dataset was randomly split into training and validation data. Segmentation of the surgical instruments, bladder, prostate, vas and seminal vesicle was performed using three CNN models (DeepLabv3, MANet, and U-Net++) and three transformers (SegFormer, BEiT, and DPT), and their performances were analyzed. Results: The overall segmentation performance during RARP varied across different model architectures. For the CNN models, DeepLabV3 achieved a mean Dice score of 0.938, MANet scored 0.944, and U-Net++ reached 0.930. For the transformer architectures, SegFormer attained a mean Dice score of 0.919, BEiT scored 0.916, and DPT achieved 0.940. The performance of CNN models was superior to that of transformer models in segmenting the prostate, vas, and seminal vesicle. Conclusions Deep learning models provided accurate segmentation of the surgical instruments and anatomical structures observed during RARP. Both CNN and transformer models showed reliable predictions in the segmentation task; however, CNN models may be more suitable than transformer models for organ segmentation and may be more applicable in unusual cases. Further research with large datasets is needed.

Purpose: With the recent rising interest in artificial intelligence (AI) in medicine, many studies have explored the potential and usefulness of AI in urological diseases. This study aimed to comprehensively review recent applications of AI in urologic oncology. Materials and Methods: We searched the PubMed-MEDLINE databases for articles in English on machine learning (ML) and deep learning (DL) models related to general surgery and prostate, bladder, and kidney cancer. The search terms were a combination of keywords, including both “urology” and “artificial intelligence” with one of the following: “machine learning,” “deep learning,” “neural network,” “renal cell carcinoma,” “kidney cancer,” “urothelial carcinoma,” “bladder cancer,” “prostate cancer,” and “robotic surgery.” Results: A total of 58 articles were included. The studies on prostate cancer were related to grade prediction, improved diagnosis, and predicting outcomes and recurrence. The studies on bladder cancer mainly used radiomics to identify aggressive tumors and predict treatment outcomes, recurrence, and survival rates. Most studies on the application of ML and DL in kidney cancer were focused on the differentiation of benign and malignant tumors as well as prediction of their grade and subtype. Most studies suggested that methods using AI may be better than or similar to existing traditional methods. Conclusions AI technology is actively being investigated in the field of urological cancers as a tool for diagnosis, prediction of prognosis, and decision-making and is expected to be applied in additional clinical areas soon. Despite technological, legal, and ethical concerns, AI will change the landscape of urological cancer management.

Purpose: The purpose of this study was to explore the association between benign prostatic hyperplasia (BPH) and the incidence of falls from the perspective of geriatric morbid conditions. Methods: Data were sourced from the triennial National Survey of Older Koreans conducted by the Ministry of Health and Welfare (2017–2020). In total, 8,135 male participants aged 65 and older were included, and information was gathered through questionnaires and physical measurements. Logistic regression analysis was utilized to determine the impact of BPH on the risk of falls, and subgroup analyses were conducted to examine the influence of BPH on specific types of falls. Results: Of the participants, 15.2% (1,238 of 8,135) reported that their BPH treatment exceeded 3 months, and 8.0% (648 of 8,135) reported experiencing falls, with 61.4% (398/648) of these falls resulting in injuries. A significant association was identified between BPH and both falls (odds ratio [OR], 1.798; 95% confidence interval [CI], 1.479–2.185) and falls with injuries (OR, 2.133; 95% CI, 1.689–2.694). A subgroup analysis indicated a correlation between BPH and falls in groups having one (OR, 1.912; 95% CI, 1.356–2.694) and 2 or more conditions (OR, 1.856; 95% CI, 1.455–2.367) involving visual and auditory impairments, cognitive decline, depression, lower motor weakness, and limitations in daily activities. Conclusions The findings indicate that BPH contributes to the incidence of falls among older men, particularly those with comorbid conditions. Considering the heightened fall risk among elderly individuals suffering from multiple morbidities, particularly those with BPH, targeted interventions are essential for mitigating the risk of falls in this vulnerable group.

Objectives: Lack of physical activity has a critical effect on the physical and mental health of adolescents. This study examined the influence of family adversities on the longitudinal changes in physical inactivity among adolescents during the coronavirus disease 2019 (COVID-19) pandemic. Methods: The study used multi-wave data from the Korean Children and Youth Panel Survey, including 2590 Korean adolescents aged 12-14 years. The longitudinal trajectory of physical inactivity among adolescents and the effects of related factors were estimated using a latent growth modeling method. Results: Our results revealed a significant increase in physical inactivity among adolescents over time. At the onset of the pandemic, approximately one-seventh of Korean middle schoolers reported a lack of physical activity. However, 3 years later, during the quarantine, nearly one-fifth of these adolescents reported a significant increase in their physical inactivity. Initially, low level parental education was predictive of adolescents’ physical inactivity, but this effect diminished over time, becoming statistically insignificant by the end of the 3-year period. Moreover, the increase in physical inactivity over the 3 years was significantly influenced by parental rejection. Conclusions These findings suggest that adolescents who experience parental rejection are more likely to report an increase in sedentary behaviors in contexts such as the COVID-19 pandemic.

Purpose: Heart failure (HF) and atrial fibrillation (AF) frequently coexist, with over 50% patients with HF having AF, while onethird of those with AF develop HF. Differences in obesity-mediated association between HF and HF-related AF among Asians and Europeans were evaluated. Materials and Methods: Using the Korean National Health Insurance Service-Health Screening (K-NHIS-HealS) cohort and the UK Biobank, we included 394801 Korean and 476883 UK adults, respectively aged 40–70 years. The incidence and risk of HF were evaluated based on body mass index (BMI). Results: The proportion of obese individuals was significantly higher in the UK Biobank cohort than in the K-NHIS-HealS cohort (24.2% vs. 2.7%, p<0.001). The incidence of HF and HF-related AF was higher among the obese in the UK than in Korea. The risk of HF was higher among the British than in Koreans, with adjusted hazard ratios of 1.82 [95% confidence interval (CI), 1.30–2.55] in KNHIS-HealS and 2.00 (95% CI, 1.69–2.37) in UK Biobank in obese participants (p for interaction <0.001). A 5-unit increase in BMI was associated with a 44% greater risk of HF-related AF in the UK Biobank cohort (p<0.001) but not in the K-NHIS-HealS cohort (p=0.277). Conclusion Obesity was associated with an increased risk of HF and HF-related AF in both Korean and UK populations. The higher incidence in the UK population was likely due to the higher proportion of obese individuals.

Background: This study aimed to examine the association of serum uric acid levels with incident cardiovascular disease and mortality in Korean adults without gout. Methods: This large longitudinal cohort study included adults aged > 19 years who had serum uric acid levels measured at least once at the National Health Insurance Service Ilsan Hospital from January 1, 2006 to December 31, 2015. Longitudinal data on person-level cardiovascular disease and cardiovascular mortality were linked to the National Health Insurance Service claims database and National Death Index. Results: Among a total of 92,454 study participants with a median follow-up of 4.7 years, 7,670 (8.3%) composite events of cardiovascular disease or cardiovascular mortality were observed. Multivariable Cox proportional-hazards models revealed that each 1 mg/dL increment in uric acid level was associated with a 6% higher risk of composite outcomes.Compared with that for the uric acid level category of 4.0 to < 5.0 mg/dL, adjusted hazard ratios (95% confidence interval) for uric acid level categories of 5.0 to < 6.0, 6.0 to < 7.0, and ≥ 7.0 mg/dL were 1.10 (1.04–1.18), 1.20 (1.11–1.30), and 1.36 (1.25–1.47), respectively. In the secondary analyses for cardiovascular disease or cardiovascular mortality examined separately, a higher uric acid level was similarly associated with a higher risk of each adverse outcome. These associations were generally consistent across clinically relevant subgroups. Conclusion A graded association was noted between serum uric acid levels and cardiovascular risk, suggesting that higher uric acid levels may adversely affect cardiovascular health and survival in individuals without gout.

Background and Objectives: We investigated whether extra-pulmonary vein (PV) ablation targeting a high maximal slope of the action potential duration restitution curve (Smax) improves the rhythm outcome of persistent atrial fibrillation (PeAF) ablation. Methods: In this open-label, multi-center, randomized, and controlled trial, 178 PeAF patients were randomized with 1:1 ratio to computational modeling-guided virtual Smax ablation (V-Smax) or empirical ablation (E-ABL) groups. Smax maps were generated by computational modeling based on atrial substrate maps acquired during clinical procedures in sinus rhythm. Smax maps were generated during the clinical PV isolation (PVI). The V-Smax group underwent an additional extra-PV ablation after PVI targeting the virtual high Smax sites. Results: After a mean follow-up period of 12.3±5.2 months, the clinical recurrence rates (25.6% vs. 23.9% in the V-Smax and the E-ABL group, p=0.880) or recurrence appearing as atrial tachycardia (11.1% vs. 5.7%, p=0.169) did not differ between the 2 groups. The postablation cardioversion rate was higher in the V-Smax group than E-ABL group (14.4% vs. 5.7%, p=0.027). Among antiarrhythmic drug-free patients (n=129), the AF freedom rate was 78.7% in the V-Smax group and 80.9% in the E-ABL group (p=0.776). The total procedure time was longer in the V-Smax group (p=0.008), but no significant difference was found in the major complication rates (p=0.497) between the groups. Conclusions Unlike a dominant frequency ablation, the computational modeling-guided V-Smax ablation did not improve the rhythm outcome of the PeAF ablation and had a longer procedure time.

Purpose: We investigated the relationship between nocturia and mortality risk in the United States. Methods: Data were obtained from the National Health and Nutrition Examination Survey 2005–2010. Mortality data were obtained by linking the primary database to death certificate data found in the National Death Index with mortality follow-up up to December 31, 2015. Nocturia was defined based on symptoms reported in the symptom questionnaire. We categorized patients into 2 groups: mild nocturia (2–3 voidsight) and moderate-to severe nocturia (≥4 voidsight). Multiple Cox regression analyses were performed with adjustment for confounding variables at the baseline survey. Results: This study included 9,892 adults (4,758 men, 5,134 women). Nocturia occurred in 3,314 individuals (33.5%). Nocturia was significantly associated with all-cause mortality (hazard ratio [HR], 1.23; 95% confidence interval [CI], 1.10–1.39) and cardiovascular disease (CVD) mortality (HR, 1.55; 95% CI, 1.19–2.01). Moreover, the mortality risk increased with increasing nocturia severity. Further analysis with propensity score matching showed that nocturia was still significantly associated with all-cause mortality and CVD mortality. In subgroup analysis according to sex, nocturia was significantly associated with allcause mortality and CVD mortality in men. In women, moderate-to-severe nocturia was significantly associated with allcause mortality and CVD mortality. In subgroup analysis according to cardio-metabolic diseases, nocturia was associated with CVD mortality in patients with diabetes mellitus, hypertension, dyslipidemia, or CVD at baseline. In subgroup analysis of patients without diabetes mellitus, hypertension or CVD, nocturia was significantly associated with all-cause mortality. Conclusions Nocturia was significantly associated with mortality in men and women after adjusting for major confounding factors.

Purpose: This study aimed to construct a database of the effective doses (ED) from F-18 fluorodeoxyglucose (FDG) torso positron emission tomography/computed tomography (PET/CT) in Korea to provide data that supports the reduction of the CT dose of PET/CT and optimization of PET/CT protocols in Korea. Methods: We investigated data of ED and CT parameters of FDG PET/CT. The data were analyzed by body weight groups. Results: A total of 31 hospitals participated in the survey (99 adults). The mean total EDs (± SD) were 8.77 ± 2.76, 10.93 ± 3.14, and 12.57 ± 3.79 mSv for the 55-, 70-, and 85-kg groups, respectively. The FDG EDs were 4.80 ± 0.98, 6.05 ± 1.15, and 6.89 ± 1.52 mSv, and the CT EDs were 4.00 ± 2.12, 4.88 ± 2.51, and 5.68 ± 2.89 mSv, respectively. Of the enrolled hospitals, 54.5% used ultra-low-dose CT protocols, and their CT ED was significantly lower than low-dose CT group in all groups (2.9 ± 1.0, 3.2 ± 1.1, and 3.3 ± 1.0 mSv vs. 6.6 ± 1.6, 7.2 ± 2.1, and 7.9 ± 2.2 mSv, all p < 0.001, respectively). In the ultra-low-dose CT group, the CT ED with the iterative reconstruction was significantly lower than that of CT without iterative reconstruction in the 55-kg group (2.4 ± 0.9 vs. 3.3 ± 0.9, p = 0.04). Conclusions These results and current recommendations can be helpful for optimizing PET/CT diagnostic reference level (DRL) and reducing unnecessary PET/CT radiation exposure.

Background: There is limited information on the clinical characteristics of patients with coronavirus disease 2019 (COVID-19) who are asymptomatic or have mild symptoms. Methods: We performed a retrospective case series of patients with COVID-19 enrolled from February 22 to March 26, 2020. Forty cases of COVID-19 were confirmed using real-time reverse-transcription polymerase chain reaction among patients who underwent screening tests and were consecutively hospitalized at Ulsan University Hospital, Ulsan, Korea.The final follow-up date was May 19, 2020. All COVID-19 cases in Ulsan were included.Demographic and epidemiological information, comorbidities, clinical signs and symptoms, laboratory and radiologic findings, medications, treatments, outcomes, and main durations of patients with COVID-19 were compared according to supplemental oxygen requirement. Results: Forty patients were included (median age, 30 years; interquartile range [IQR], 25–57 years; 58% female). Six (15%) patients required supplemental oxygen. The prevalence of asymptomatic severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) infection was 5% and that of presymptomatic infection was 13%. Cough, fever, myalgia, rhinorrhea or nasal congestion, and diarrhea were the screening criteria for diagnosing symptomatic and presymptomatic SARS-CoV-2 infections. Sputum production, chest discomfort, a large number of symptoms, abnormal procalcitonin and C-reactive protein levels, and abnormal chest X-ray or chest computed tomography findings were more common in patients requiring supplemental oxygen than in those not requiring supplemental oxygen. Overall mortality rate was 3% (1/40). Four patients (10%) were readmitted after testing positive by reversetranscription polymerase chain reaction again. Incubation period was 5 days (IQR, 4–6 days), and the duration of viral shedding was 21 days (IQR, 14–28 days; maximum, 51 days). Conclusion The prevalence of asymptomatic SARS-CoV-2 infection was 5%, which is much lower than that previously reported. This finding suggests that careful interviews and follow-ups should be performed to identify SARS-CoV-2 infections. Cough, fever, myalgia, rhinorrhea or nasal congestion, and diarrhea are adequate screening criteria for covering all symptoms of SARS-CoV-2 infection. Further evaluation is required to create representative screening criteria for COVID-19.