Ziyan An

Objective: To evaluate the triage accuracy, response quality, safety, and repeatability of widely used large language models (LLMs) in urologic emergencies and to examine their potential clinical utility and risks. Methods: We developed 50 standardized clinical vignettes covering 10 categories of urologic emergencies, including testicular torsion, acute urinary retention, and Fournier gangrene. The set comprised high-risk vignettes requiring immediate emergency care, borderline vignettes, and atypical vignettes containing misleading cues. Six commercially available LLMs—Kimi 3.0, DeepSeek V4, Qwen 3.8-MAX, GPT-5.6 Sol (ChatGPT), Claude Opus 4.8, and Ant Afu (AQ)—were evaluated in Chinese-language interactions. Each vignette was submitted three times in independent conversations. Two urologists with more than 10 years of clinical experience assessed triage accuracy using a three-level reference standard (immediate emergency department [ED] evaluation, routine outpatient evaluation, or home observation). They also rated response quality across eight dimensions using a 5-point Likert scale and evaluated medical-error severity (0–3), response stability, and Chinese readability. Overall differences were assessed using the Friedman test, followed by pairwise Wilcoxon signed-rank tests with Holm adjustment. Results: A total of 900 responses were generated. Overall three-class accuracy was 89.11%, and the macro-averaged F1 score was 85.73%. Qwen achieved the highest accuracy (94.00%), whereas Claude achieved the lowest (80.67%). However, none of the pairwise comparisons between models reached statistical significance after Holm adjustment. All models generally recognized scenarios requiring immediate ED evaluation, but their ability to distinguish routine outpatient evaluation from home observation varied substantially. Mean content-quality scores ranged from 3.68 to 4.15; AQ achieved the highest overall score (4.15 ± 0.49), whereas DeepSeek achieved the lowest (3.68 ± 0.48). Clinically relevant errors occurred in 12.3% of responses, including major errors in 6.2% and dangerous errors in 3.1%. Three-run exact triage agreement ranged from 78% to 96%. Readability performance varied by metric, with no single model consistently outperforming the others. Conclusions: The six LLMs demonstrated some ability to perform three-level triage of urologic emergencies, supporting further investigation of their potential clinical applications. Nevertheless, important limitations remained in the management of borderline cases, response stability, and safety; some responses included potentially dangerous self-management instructions or could delay care for high-risk patients. Integration with authoritative guidelines, structured risk warnings, and human review will be necessary to improve clinical safety and reliability.

Medical adhesives have been extensively applied for skin wound repair and hemostasis, while the dynamically humid and complex intraperitoneal environment imposes stringent requirements on tissue adhesives. Few studies have reported the application of biological adhesives for bladder defect repair in urological practice. The GSF composite hydrogel adhesive, composed of gelatin methacryloyl (GelMA), silk fibroin methacryloyl (SilMA), and polyether F127 diacrylate (F127DA), was previously fabricated with favorable injectability, appropriate viscosity and superior mechanical toughness. To further confirm the repair efficacy, GSF was characterized in vitro for the adhesive properties and structural stability under dynamically humid conditions. Corresponding in vivo experiments were conducted on rat models with graded bladder rupture and partial bladder defects to further assess the repair performance of GSF. Results showed that GSF hydrogel retained robust interfacial adhesion and intact structural stability for 8 days under dynamically simulated humid intraperitoneal conditions and cyclic urine filling-emptying environments. GSF exhibited rapid bonding capacity and effectively shortened the operation time. Under moderate bladder injury conditions, the wound closure time of the GSF group was only 28.3% of that of the suture group in cystotomy experiment and 34.5% in cystectomy experiment. It achieved satisfactory repair of mild-to-moderate bladder ruptures and partial bladder defects. Postoperative histological and functional evaluations confirmed that GSF hydrogel facilitated bladder structural reconstruction and functional recovery. These findings highlight the significant potential of GSF hydrogel adhesives for repairing and regenerating injured bladders. Future applications of GSF will extend to adhesive repairs of organs within the humidity conditions of the abdominal cavity.

Background: Prostate cancer (PCa) is a leading cause of cancer-related mortality worldwide, highlighting the need for improved prognostic tools. The integration of artificial intelligence (AI) and machine learning (ML) with multi-omics data offers new opportunities for biomarker discovery and risk stratification. Methods: We integrated bulk transcriptomic data from GSE116918 (training, n = 248) and three cross-cohort consistency evaluation cohorts (TCGA-PRAD, GSE70769, GSE46602), focusing on 1087 epithelial–mesenchymal transition (EMT)-associated genes. Using consensus clustering, weighted gene co-expression network analysis (WGCNA), and 91 machine learning algorithm combinations (including Random Forest, Lasso, and CoxBoost), we constructed a prognostic signature. SHAP analysis was used for model interpretability. Single-cell RNA sequencing (scRNA-seq, GSE268307, 10,672 cells) and spatial transcriptomics (10× Genomics Visium FFPE) provided hypothesis-generating evidence; spatial analysis was based on one tissue section. Results: A three-gene signature (INHBA, FAP, ITGBL1) effectively stratified patients into high- and low-risk groups, with the high-risk group showing significantly worse metastasis-free survival (HR = 1.61, 95% CI: 1.39–1.87; 4-year AUC = 0.93 in the training cohort; external AUCs ranged from 0.62 to 0.77). CytoTRACE inferred high differentiation potential of COMP+ fibroblasts, and Monocle3 inferred a transcriptional transition from COMP+ toward NELL2+ fibroblasts. BayesPrism deconvolution suggested that high inferred COMP+ fibroblast abundance was associated with poor prognosis and advanced T stage. NicheNet analysis prioritized BMP7 as a key upstream ligand, with downstream targets enriched in TGF-β signaling and stem cell pluripotency pathways. Conclusions: This study presents a machine learning-based multi-omics framework for prostate cancer risk stratification. The three-gene signature provides a new exploratory prognostic model while inferring a COMP+ to NELL2+ transcriptional transition. These findings may inform future hypothesis-driven studies of treatment sensitivity, pending experimental validation, and demonstrate the value of AI-driven multi-omics integration for precision oncology.

This study aims to evaluate the efficacy of large language models (LLMs) in health management for urological and andrological conditions by comparing two Chinese LLMs: DeepSeek and Kimi. The responses of DeepSeek and Kimi to 30 questions on six urological and andrological diseases were quantitatively assessed using quality assessment tools, expert assessments, and readability metrics. In quality assessments, DeepSeek outperformed Kimi in only two instances: responses to "What are the surgical options for kidney stones?" (PEMAT-AI: P = 0.012; DISCERN-AI: P = 0.024) and "What are the treatment modalities for bladder cancer?" (PEMAT-AI and DISCERN-AI: P < 0.001). Expert assessments revealed that DeepSeek demonstrated superior accuracy and safety compared to Kimi only in addressing "Dietary considerations for kidney stone patients" (accuracy: P < 0.001; safety: P = 0.02). No statistically significant differences were found in quality assessments or expert assessments between the models for disease-specific categories. However, Kimi outperformed DeepSeek in readability evaluations. Both DeepSeek and Kimi exhibit substantial efficacy and clinical applicability in managing urological and andrological diseases. To enhance their practical use, Kimi requires improvements in accuracy and safety, while DeepSeek should focus on improving readability.

The engineered bladder patch with a three‐layer structure was constructed from a bi‐layer silk fibroin scaffold (BSFS) and a methacrylated bladder acellular matrix hydrogel (BAMMAH) that carried induced vascular endothelial cells (VECs) and induced nerve cells (NCs). The patch was developed for bladder augmentation in a rabbit model. The prepared BSFS combined the rigidity of silk fibroin film with the elasticity of silk fibroin sponge, providing a support framework for the construction of engineered bladder. The synthesized BAMMAH exhibited a rapid gelling property, and 2% BAMMAH showed good rheological properties and an internal pore structure. Immunofluorescent staining and RT‐qPCR confirmed that the induction schemes for adipose‐derived mesenchymal stem cells (ADSCs) differentiation into VECs and NCs were feasible and stable. Immunofluorescence analysis demonstrated that incubation with omentum could promote the regeneration of the vascular network inside the engineered patch with a three‐layer structure (BSFS‐BAMMAH‐ADSCs‐VECs‐NCs). Animal experimental data showed that the engineered patch could promote the regeneration of the bladder wall and the recovery of bladder function. These results confirmed that the constructed engineered bladder patch with a three‐layer structure could regenerate the blood vessel network and neural reinnervation, providing a feasible method to solve the difficulties of vascular network and neural innervation in bladder tissue engineering research.

Previous studies of bladder tissue engineering simply seeded cells onto the surface of the material, which makes the cells lack protection and makes it difficult to face the complex in vivo environment. The gelatin methacryloyl (GelMA) hydrogel possesses outstanding biocompatibility and distinctive photo‐crosslinking characteristics and is capable of offering a suitable three‐dimensional growth environment for cells. This study explored the optimal concentration of GelMA for encapsulating adipose‐derived stem cells (ADSCs) and combined it with bladder acellular matrix (BAM) to create a tissue‐engineered bladder patch. Results indicated that 10% GelMA more effectively promoted ADSCs proliferation and spreading compared to 7.5% and 12.5% concentrations, which can offer a better extracellular matrix environment for cells. BAM performed as an excellent substrate with mechanical properties and stitchability similar to natural tissues. Animal experiments demonstrated that the encapsulated ADSCs in GelMA enhanced patch vascularization in vivo and BAM‐GelMA‐ADSCs tissue‐engineered bladder patch can repair large‐scale bladder defects in beagles and promote bladder tissue regeneration and functional recovery. This photocrosslinking hydrogel‐acellular matrix patch provides a protective semi‐controlled environment for ADSCs, supporting the growth and viability of encapsulated cells in vivo, while being easy to suture and preventing leakage, and has significant clinical potential.

The bladder is exposed to constant internal and external mechanical forces due to its deformation and the dynamic environment in which it is placed, which can hamper its repair after an injury. Traditional hydrogel materials have limitations regarding their use in the bladder owing to their poor mechanical and tissue adhesion properties. In this study, a composite hydrogel composed of methacrylate gelatine, methacrylated silk fibroin, and Pluronic F127 diacrylate was developed, which combines the characteristics of natural and synthetic polymers. The mechanical properties of the novel hydrogel, such as stretchability, viscoelasticity, and toughness, were improved by virtue of a particular molecular design strategy whereby covalent and non-covalent bond interactions create a cross-linking effect. In addition, the composite hydrogel has important usability properties; it can be injected in liquid format and rapidly transformed into a gel via photo-initiated crosslinking. This was demonstrated on an isolated porcine bladder where the hydrogel closed arbitrarily-shaped tissue defects within 90 s of its application, verifying its effective bioadhesive and sealing properties. This composite hydrogel has great potential for application in bladder injury repair as a tissue-engineering scaffold.

A scaffold, constructed from a bi-layer silk fibroin skeleton (BSFS) and a bladder acellular matrix hydrogel (BAMH) encapsulated with adipose-derived stem cells (ASCs), was developed for bladder augmentation in a rat model.