Purpose: To compare the perioperative outcomes and oncological results of open, laparoscopic, and robotic radical nephroureterectomy (RNU) in patients with upper tract urothelial carcinoma (UTUC) and to analyze trends in the utilization of RNU. Methods: From 2017 to 2020, the records of 61, 185, and 119 patients who underwent open, laparoscopic, and robotic RNU, respectively, were reviewed. Results: Baseline characteristics were not significantly different among the three groups. Robotic RNU has recently started to increase from 9% in 2017 to 67% in 2021. Operation time, blood loss, length of hospital stay, and 90-day complications were not different between the three groups. The three-year overall survival (OS) rates for open, laparoscopic, and robotic RNU were 91.8%, 90.4%, and 92.1%, respectively (p > 0.05). No differences in the progression-free survival (PFS), cancer-specific survival (CSS), and OS were observed according to the surgical approach in the Kaplan–Meier survival analysis. Multivariate analysis showed that surgical approach was not an independent predictor of PFS, CSS, and OS. Conclusion: The use of robotic RNU in patients with UTUC has been starting to increase and replace open and laparoscopic RNU. Perioperative outcomes, 90-day complications, and oncological outcomes of robotic RNU were not inferior to those of open and laparoscopic RNU.

Background: Differentiating histologic subtypes of fat-poor small renal masses using conventional imaging remains difficult due to their overlapping radiologic characteristics. We aimed to develop a machine learning-based diagnostic model using CT-derived radiomic features to classify the five most common renal tumor subtypes: clear cell RCC (ccRCC), papillary RCC (pRCC), chromophobe RCC (chRCC), angiomyolipoma (AML), and oncocytoma. Methods: A total of 499 patients with pathologically confirmed renal tumors who underwent preoperative contrast-enhanced CT and nephrectomy were retrospectively analyzed. Results: We extracted and analyzed radiomic features from 1548 multi-phase CT scans from 499 patients, focusing on fat-poor tumors. Five machine learning classifiers including Linear SVM, Rbf SVM, Random Forest, and XGBoost were involved. Among the models, XGBoost showed the best classification performance, with an average AU-PRC: mean = 0.757, standard error = 0.033 and a renal angiomyolipoma-specific AU-ROC: mean = 0.824, standard error = 0.023. These results outperformed other single-phase CT radiomic feature-based machine learning models trained with 20% of principal components. Conclusions: This study demonstrates the effectiveness of radiomics-based machine learning in classifying renal tumor subtypes and highlights the potential of AI in medical imaging. The findings, particularly the utility of single-phase CT and feature optimization, offer valuable insights for future precision medicine approaches. Such methods may support more personalized diagnosis and treatment planning in renal oncology.

Background: Lower urinary tract symptoms (LUTS) are commonly quantified using validated instruments such as the International Prostate Symptom Score (IPSS) and the Overactive Bladder Symptom Score (OABSS). However, structured questionnaires are not consistently administered in routine outpatient practice, where clinicians frequently rely on narrative documentation. While generative large language models (LLMs) have demonstrated potential in clinical natural language processing, their performance stability across successive model generations for automated symptom scoring remains unclear. We conducted a head-to-head comparison of ChatGPT-4o and ChatGPT-5.1 to evaluate generational performance differences in automated LUTS scoring. Materials and methods: This retrospective secondary analysis of a previously reported outpatient cohort evaluated the performance of ChatGPT-4o and ChatGPT-5.1 in estimating LUTS-related scores from clinician-documented narratives. Free-text symptom narratives documented from electronic medical records were entered directly into each model using identical prompts. Ground-truth IPSS and OABSS total scores were obtained from completed questionnaires. Predictive performance was assessed using mean absolute error (MAE), root mean squared error (RMSE), intraclass correlation coefficients (ICC), and Spearman’s correlation coefficients. Classification of clinically significant LUTS (IPSS ≥ 8) and overactive bladder (OAB; OABSS ≥ 3 with urgency score ≥ 2) was evaluated using accuracy, Cohen’s kappa (κ), and area under the receiver operating characteristic curve (AUC). The analysis included 91 patients from the original cohort. Results: Among 91 patients (mean age 71.9 ± 10.3 years; 58.2% male), 49 completed IPSS and 78 completed OABSS. For IPSS prediction, MAE/RMSE were 4.88/6.34 for ChatGPT-4o and 4.92/7.01 for ChatGPT-5.1, with no significant differences between models. For OABSS prediction, MAE/RMSE were 1.88/2.76 and 2.03/2.93, respectively, again without significant differences. Agreement was moderate for IPSS (ICC 0.561–0.509) and higher for OABSS (ICC 0.704–0.658). Classification accuracy exceeded 0.85 for both outcomes, and ROC analysis demonstrated comparable discriminative performance across model versions. Conclusions: ChatGPT-4o and ChatGPT-5.1 demonstrated comparable and moderate performance in approximating LUTS-related symptom scores from unstructured clinical narratives. These findings suggest that generative AI models may serve as supportive tools for automated symptom quantification and indicate relative performance stability across model generations within real-world urological practice.

This study aims to determine the problems involved in using a mathematical calculation to analyze the pathophysiology of nocturia using a frequency volume chart (FVC). In this retrospective study, we reviewed 253 patients who completed the FVC during ≥ 3 days for nocturia from January 2017 to February 2019. The etiology of nocturia was defined as a combination of 4 pathophysiologies, including nocturnal polyuria (NP), decreased bladder capacity (dBC), decreased nocturnal bladder capacity, and global polyuria. To analyze the differences according to diagnostic criteria for NP and dBC, 2 definitions were classified. Definition 1: NP is NP index (NPi) > 0.35 and dBC as maximal voided volume (MVV) < 325 mL. Definition 2: NP is NPi = 0.20 to 0.33 depending on age and dBC as MVV < 200 mL. The MVV in the FVC for ≥3 days was significantly higher than that for 1 day (330 mL vs 400 mL, P < .001). During the entire FVC period, all pathophysiology remained unchanged in only 16.6% of cases (inter-day variation). Of 323 days in which nocturia occurred ≥ 2 per night, 118 days (36.5%) full bladder voiding of nocturia was not the same for each day (inter-nocturia variation). According to definitions 1 and 2, the serial changes of NP and dBC showed different patterns. The mathematical calculation used in analyzing the pathophysiology of nocturia using an FVC has problems such as differences according to the duration of FVC and inability to express inter-day and inter-nocturia variations. Therefore, this mathematical calculation is not helpful when determining the treatment modality for nocturia.