The European association of Urology (EAU) suggests a prognostic stratification of Upper Tract Urothelial Cancer (UTUC) based on high and low risk patients, with Radical nephroureterectomy (RNU) and bladder cuff resection being the gold standard for the treatment of non-metastatic High risk UTUC. However, no consensus on post-operative patient management or tools that predict who would benefit the most from a close follow-up rather than adjuvant chemotherapy regimen exist. in Machine Learning (ML) is gaining interest in Urology providing models for prognostic prediction purpose; It’s role in UTUC has not yet been investigated. We aim to develop and validate multiple supervised ML models based on patient- and tumor- related features to predict prognosis in patients with preoperative Histological or Imaging proved UTUC treated with RNU within a multiethnic large cohort. Data from an international multicenter large cohort of histologically proven UTUC patients from Asia and Europe treated with RNU were retrospectively collected. Twenty different ML-supervised predictive models were first trained and then external validate with two separate set. Nomograms were constructed based on 8 independent prognostic factors (age, gender, grading, pT, pN, presence of Carcinoma in Situ (CIS), multifocality and Lymphovascular invasion(LVI)) to predict 6 Outcomes (Overall Survival (OS), Cancer Specific Survival (CSS) and Disease Free Survival (DFS) at 3 and 5 year). Performances were compared using Area-under-curve (AUC) of Receiver-Operating Characteristics (ROC). A total of 3129 patients were enrolled: 637 Asian Patients (training cohort) and 2492 European patients (validation cohort). Upon training assessment, LR models achieved the best results, being the best model for prediction of 4/6 outcomes, with the best result in CSS both at 3 and 5 years (AUC: 0.85, 0.84, 0.81 for CSS-3y, CSS-5y and DFS-3y respectively). Upon external validation, LR(CSL) models achieve the best results, being the number 1 model for prediction of 3/6 outcomes (AUC: 0.84, 0.79, 0.77 for CSS-3y, OS-3y and OS-5y respectively). ML is a promising technology in the field of UTUC. Our model achieve favorable results in terms of prediction of prognosis after RNU, especially in terms of CSS at 3 and 5 years, moreover is the first model of prognosis taking into account the differences in epidemiology existing between European and Asian patients. Further clinical validation and verification of its reliability for the case selection of adjuvant therapy are needed to assess its use in clinical practice linked to clinical decision making. ML is an advancing technology in the field of medicine and urology, which can also be applied to the definition of the prognosis of patients with UTUC undergoing RNU. Our study represents the first experience investigating this potential.

Objective: Bladder cancer remains a significant burden on healthcare systems worldwide. The aim of this review is to evaluate the diagnostic performance of artificial intelligence against conventional first-line methods (cystoscopy and urine cytology) for bladder cancer. Methods: A PROSPERO-registered (CRD420261291622) systematic review and meta-analysis. Studies were included if they assessed artificial intelligence performance in definitive urothelial carcinoma detection via cystoscopy or urine cytology against a non-artificial intelligence human comparator. Bivariate random-effects meta-analysis was performed to assess diagnostic performance with the area under the summary receiver operating characteristic curve calculated from the hierarchical summary receiver operating characteristic curves. Results: Nine studies were included (six cytology, three cystoscopies; 8918 data points). Artificial intelligence demonstrated statistically significant greater sensitivity (0.927 vs 0.754), with a lower negative likelihood ratio (0.087 vs 0.254), suggesting stronger ‘rule-out’ performance. However, this came at the cost of higher false positives compared to conventional methods. Conventional methods (cystoscopy/cytology) demonstrated higher specificity (0.968 vs 0.841) and positive likelihood ratio (23.275 vs 5.849), reflecting stronger rule-in capability. Conclusion: Artificial intelligence algorithms potentially have enhanced screening performance for bladder cancer compared to first-line modalities. The utilisation of a hybrid model may improve outcomes and efficiencies. However, large-scale, prospective trials with standardised reporting and histological reference standards are required before artificial intelligence can safely and equitably be deployed. Level of evidence: 2a

Bladder cancer remains a major global health challenge, characterized by diagnostic uncertainty, substantial treatment costs and high recurrence rates. Current diagnostic and treatment modalities, including cystoscopy, transurethral resection of bladder tumour and standard histopathology, have limitations, including the inability to detect flat lesions, frequent understaging and interobserver variability, highlighting a crucial need for improved approaches. Advances in artificial intelligence (AI), blue-light cystoscopy, narrow-band imaging, cytology and urinary markers show promise in enhancing early detection and diagnosis. Developments in multiparametric MRI, radiomics, genomics and AI-driven algorithms for histopathological analyses have demonstrated considerable improvements in staging and risk stratification of bladder tumours, enabling personalized therapy selection and prognostication. Despite these promising developments, challenges remain regarding standardization, external validation, cost-effectiveness and ethical considerations in clinical implementation. Future research should prioritize addressing these barriers through collaborative, multi-institutional studies and robust validation frameworks. Ultimately, adopting a comprehensive multimodal strategy, such as proposed, novel, multimodal decision-making frameworks in which these advances and technologies are integrated, promises to considerably advance precision oncology in bladder cancer, improving patient outcomes and reducing health care burdens. In this Review, the authors describe and discuss how advances in artificial intelligence, genomics, radiomics and cytology can be integrated into decision-making processes to improve the management of bladder cancer.

To develop and retrospectively validate an artificial intelligence-based decision support system (AI-DSS) for optimising prostate biopsy decisions and improving benefit-to-harm ratios. This retrospective, multicentre, multiscanner study used data from 1022 patients. An AI-DSS integrating PI-RADS scores, automated prostate-specific antigen density (PSAd), and deep-learning imaging risk scores was developed on 770 cases and validated on an independent cohort of 252 men from six UK centres. The AI-DSS performance was benchmarked against the real-world clinical decisions (reference standard) using grade selectivity, biopsy efficiency, and selective biopsy avoidance as outcome measures. Biopsy-proven detection of grade group (GG) ≥ 2 disease was the reference standard. In the validation cohort of 252 patients (mean age, 67.3 years), 137 underwent biopsy and 79 (31

Objective: To evaluate the diagnostic yield of blue-light cystoscopy (BLC) compared with white-light cystoscopy (WLC) in detecting carcinoma in situ (CIS) and muscle-invasive bladder cancer (MIBC), and to assess recurrence-free survival (RFS) following BLC-HAL resection. Patients and Methods: We retrospectively analysed 238 patients undergoing BLC-HAL between July 2017 and July 2024. Seventy-two underwent primary BLC at initial resection, and 166 underwent BLC re-resection following WLC. Endpoints were CIS detection, tumour upstaging, and recurrence-free survival at 12 and 24 months using Kaplan–Meier analysis. Results: Overall, malignancy was confirmed in 113/238 patients (47%). Detection was higher in the secondary arm (55%) compared with the primary arm (29%). In the primary arm, CIS was detected in 19% and MIBC in 24%. In the secondary arm, CIS increased from 18% on WLC to 38% with BLC (p = 0.001), with 26% detected only under blue light; 10% were upstaged to MIBC (p = 0.022). Over one-third of patients were reclassified into a higher EAU NMIBC risk group. Kaplan–Meier analysis showed 12- and 24-month RFS of 71% (95% CI: 36–92%) and 67% (95% CI: 35–88%) in the primary arm, and 62% (95% CI: 49–74%) and 63% (95% CI: 43–79%) in the secondary arm. Median RFS was not reached within 24 months. Conclusions: BLC significantly enhances CIS detection and identifies MIBC and higher-risk disease not seen on WLC, directly influencing patient management. Despite improved detection, recurrence-free survival remains modest, consistent with high-risk NMIBC, supporting guideline recommendations for routine use of BLC at TURBT, particularly in suspected CIS and high-grade disease.

Abstract Objective This study aims to investigate any differences in the levels of intra‐operative (measured by an artificial intelligence device) and post‐operative pain between two different abdominal insufflators (AirSeal vs Stryker) used for a low‐pressure pneumoperitoneum robotic prostatectomy. Methods A prospective randomised controlled clinical study was performed at Lister Hospital, Stevenage. The primary aim was to evaluate the feasibility of recruiting 40 patients with localised prostate cancer who underwent a robotic prostatectomy with either an AirSeal® Insufflation System (n = 20) or Stryker PneumoClear Insufflator (n = 20) for the management of low‐pressure pneumoperitoneum (8 mmHg). The co‐primary aim was to investigate any differences in intra‐operative significant nociceptive stimulus (NOL ≥ 25 for ≥1 min) measured by the Medasense PMD‐200 device, in addition to post‐operative pain scoring and opioid consumption. The secondary aim of the study was to assess any differences in surgical factors (blood loss, console and total procedure time, length of stay, readmission rates, adverse events, differences in creatinine and haemoglobin and unplanned pneumo‐peritoneal pressure changes). Results Forty patients were successfully recruited onto the RALP trial with complete 30‐day follow‐up. AirSeal has fewer significant nociceptive events per recorded hour than Stryker (20.7 vs. 33.5, p = 0.041). Shorter procedure times (p = 0.045), console times (p = 0.045) and blood loss (p < 0.001) were seen in the AirSeal arm of the trial. There were no statistical differences in post‐operative pain scores, analgesia consumption at POD1 (p = 0.599) and at discharge (p = 0.488). There were four (n = 4) adverse effects reported with the Stryker arm of the trial (n = 3 ileus, n = 1 UTI) leading to two (n = 2) formal re‐admissions. Conclusions and relevance In this study, we were able to successfully recruit 40 participants with complete 30‐day follow‐up. There were advantageous surgical factors and lesser intra‐operative nociceptive insult associated with the AirSeal insufflator. Further RCTs are planned with a larger population to investigate the true causality of this relationship.

Background:Previous studies have highlighted the benefits of using artificial intelligence-powered remote patient monitoring (AI RPM) in detecting health changes across various disease cohorts. However, the use of AI RPM for identifying health deteriorations in patients following major surgical procedures remains underexplored. Objective:This exploratory analysis of a prospective trial aims to assess how AI RPM can enhance the predictive performance of 35-month post-radical cystectomy (RC) mortality risk. Our approach highlights the importance of RPM features in improving prediction accuracy and provides interpretable model outputs to enhance clinical understanding and transparency. Methods:We used patient data from a multicenter RC trial conducted in the United Kingdom for model training and validation. Two gradient-boosted machine learning models were developed: one using only clinical-pathological (CP) features and another incorporating both CP and remote patient monitoring (RPM) features (CP+RPM). RPM features are measured by wrist-worn pedometers and surveys. The predictive accuracy of the CP+RPM model was compared with both the CP model and a clinically used nomogram, both of which relied solely on traditional clinical features. We used 200 bootstrap iterations, with 70% of the data used for training and 30% for testing. Shapley Additive Explanations were applied to interpret model results and provide insights into the relative importance of features, improving transparency and understanding of the predictions. Results:A total of 252 patients (33 deaths) from 9 UK centers were included in the analysis. We examined 108 RPM features and 24 CP features for model training. In correlation analysis, only 9 CP features showed coefficients larger than 0.1, compared with 36 RPM features with stronger correlations. The CP+RPM model achieved an area under the receiver operating characteristic curve of 0.77, reflecting a 9% and 10% absolute (13% and 15% relative) improvement over the CP and nomogram models, respectively. Similarly, it outperformed in terms of the area under the precision-recall curve, with a score of 0.44, marking a 6% and 17% absolute (16% and 63% relative) increase compared with the CP and nomogram model. Shapley Additive Explanations analysis revealed that the most significant contributors to mortality prediction were mobility-related RPM features, such as the 30-second chair-to-stand test results and daily step count variance, which reflected the general activity levels of individuals. Conclusions:Our study demonstrates that RPM features significantly enhance long-term survival prediction for post-RC patients, offering a valuable addition to traditional clinical data. The integration of AI with RPM enables more individualized and dynamic tracking of recovery, improving prediction accuracy and fostering a patient-centered care model that has the potential to be applied across a broader range of surgeries and conditions.

Urological surgeons have been shown to suffer with significant musculoskeletal (MSK) discomfort during their careers directly attributed to their work. Robot-assisted surgery (RAS) is believed to offer superior ergonomics to traditional forms of surgery but concerns still exist around their use. This systematic review collates the currently available literature on the ergonomic outcomes of RAS in urology and offers comparison to other surgical modalities. The preferred reporting items for systematic reviews and meta-analysis (PRISMA) guidelines formed the basis of this review, and the study protocol was registered in PROSPERO (CRD420250650617). A thorough database search was conducted in MEDLINE/PubMed and EMBASE, with twenty-two articles eventually included in the review. Data analysis included a narrative synthesis, and sub-group meta-analysis where data homogeneity allowed. Overall, RAS offers a more ergonomic environment for urological procedures than laparoscopic, open, or endoscopic surgery. Questionnaire-based studies demonstrated favourable use among urological surgeons, although numerous issues persist such as neck and back pain. Postural and muscular assessments similarly showed improvements in ergonomy for RAS. However, prolonged poor ergonomic joint positions, and moderate activation of upper body muscles were noted in all forms of surgery. Task load indexes demonstrated lower physical demand among RAS. While RAS offers a superior ergonomic environment to minimally invasive and open surgical techniques in urology, numerous challenges still exist. Continued study is needed, and formal ergonomic assessments should become standard protocol for any emerging robotic systems to ensure that proper ergonomy is maintained across a diverse surgical population.

Robotic technology has revolutionised minimally invasive urological surgery, enhancing precision and minimising surgical complications. Recent evidence suggests that utilising lower pneumoperitoneum pressures improves clinical outcomes but the comparative impact on post-operative pain remains uncertain. This systematic review analyses the literature on low-pressure pneumoperitoneum to investigate its impact on pain and recovery following robotic-assisted urological surgeries, including prostatectomy, partial ephrectomy, and cystectomy. Post-operative opioid consumption, total operating time, estimated intra-operative bleeding, and total inpatient stay were investigated as secondary outcomes. PubMed, NHS Knowledge and Library Hub, Cochrane Central databases, and EMBASE were searched between January 2010 and May 2024. Any identified studies were reviewed against eligibility criteria by two independent authors prior to inclusion. The review was written in compliance with Preferred Reporting Items for Systematic Reviews (PRISMA) guidelines. Nine studies were included: six focused on prostatectomy, two on partial nephrectomy, and one on cystectomy. Low-pressure pneumoperitoneum was found to result in reduced postoperative pain scores, particularly in the immediate recovery period and on postoperative day 1. Despite these improvements, post-operative opioid consumption remained consistent with standard pressures. The surgical workspace was not compromised when pneumoperitoneum pressures were lower. Lowering pneumoperitoneum pressures in robotic-assisted urological surgery appears to reduce immediate postoperative pain scores without increasing overall complications. This has not led to a noticeable reduction in post-operative opioid consumption. The lack of consistent reduction in opioid use and limited high-quality studies highlight the need for further research, particularly for partial nephrectomy and cystectomy.

Objective: To describe the clinical use of URO17®, a noninvasive, urine-based immunocytochemistry assay targeting Keratin 17 (K17), as an adjunct to conventional diagnostic methods for urothelial carcinoma. Materials and Methods: These illustrative cases summarize the real-world use of URO17® in diagnostic workflows for patients presenting with hematuria and those undergoing surveillance for non-muscle invasive bladder cancer (NMIBC). Urine samples were processed via standard immunocytochemistry and interpreted alongside cystoscopic, cytological, and radiographic findings. Discussion: URO17® was used as a complementary diagnostic tool to help guide clinical management. Negative results supported deferral of invasive procedures in selected patients, while positive findings prompted further evaluation when standard tests were inconclusive. Conclusions: In the seven illustrative cases presented, URO17® aided clinical decision-making as part of routine diagnostic and surveillance workflows. The test's integration with existing cytology processes supports its potential role as a noninvasive adjunct for evaluating patients with suspected or recurrent urothelial carcinoma.

Urinary extracellular vesicles (U-EVs) are gaining increasing interest as non-invasive liquid biopsy tools for clinical use. Prostate cancer (PCa) is amongst the highest cancer-related cause of death in men, and therefore, the identification of non-invasive robust biomarkers is of high importance. This study assessed U-EV profiles from individuals affected by PCa at Gleason scores 6–9, compared with healthy controls. U-EVs were characterised and assessed for proteomic cargo content by LC-MS/MS analysis. The U-EV proteomes were compared for enrichment of gene ontology (GO), KEGG, and Reactome pathways, as well as disease–gene associations. U-EVs ranged in size from 50 to 350 nm, with the majority falling within the 100–200 nm size range for all groups. U-EV protein cargoes from the PCa groups differed significantly from healthy controls, with 16 protein hits unique to the GS 6–7 and 88 hits to the GS 8–9 U-EVs. Pathway analysis showed increased enrichment in the PCa U-EVs of biological process GO (5 and 37 unique to GS 6–7 and GS 8–9, respectively), molecular function GO (3 and 6 unique to GS 6–7 and GS 8–9, respectively), and cellular component GO (10 and 22 unique to GS 6–7 and GS 8–9, respectively) pathways. A similar increase was seen for KEGG pathways (11 unique to GS 8–9) and Reactome pathways (102 unique to GS 8–9). Enrichment of disease–gene associations was also increased in the PCa U-EVs, with highest differences for the GS 8–9 U-EVs (26 unique terms). The pathway enrichment in the PCa U-EVs was related to several key inflammatory, cell differentiation, cell adhesion, oestrogen signalling, and infection pathways. Unique GO and KEGG pathways enriched for the GS 8–9 U-EVs were associated with cell–cell communication, immune and stress responses, apoptosis, peptidase activity, antioxidant activity, platelet aggregation, mitosis, proteasome, mRNA stability oxytocin signalling, cardiomyopathy, and several neurodegenerative diseases. Our findings highlight U-EVs as biomarkers to inform disease pathways in prostate cancer patients and offer a non-invasive biomarker tool for clinical use.

Focal therapy (FT) is a promising alternative to radical treatments for localized Prostate Cancer (PCa) in selected patients. However, it is not yet considered a standard treatment option, and there is currently no consensus on managing patients after FT. In this context, Prostate-Specific Membrane Antigen Positron Emission Tomography (PSMA-PET) may support multiparametric MRI (mpMRI) for both pre-operative planning and follow-up. The aim of this systematic review was to provide a comprehensive overview of the current applications of PSMA-PET in the field of FT and to analyze its future perspectives. A literature search was performed using PubMed and Scopus databases, following the Preferred Reporting Items for Systematic Review and Meta-analysis (PRISMA) statement recommendations. All studies reporting data on PSMA-PET performed before and/or after FT for PCa were included. A narrative synthesis was employed to summarize the review findings. No quantitative synthesis was performed due to the heterogeneity and limitations of the studies. Seven studies (2 case reports, 1 retrospective, and 4 prospective single-center studies) were included in this review. A moderate-severe risk of bias was assessed for the included studies. In the field of FT, PSMA-PET showed promising but yet not validated results with several possible applications: (1) pre-operative planning and staging, aiming to improve patient selection trough the identification of intraprostatic suspected lesions and more accurate local and systemic staging; (2) guidance for biopsy and Region of Interest (ROI) definition; (3) follow-up imaging tool, aiming to decrease the number of unnecessary surveillance biopsies. Limited evidence exists regarding the use of PSMA-PET in the field of FT, considering pre-operative setting, treatment guidance and its use as a non-invasive tool to evaluate treatment success or failure and for follow-up. In this scenario, even if the current evidence is still limited and inconclusive, PSMA-PET showed promising results with several possible applications.

Multiparametric magnetic resonance imaging (MRI), with or without prostate biopsy, has become the standard of care for diagnosing clinically significant prostate cancer. Resource capacity limits widespread adoption. Biparametric MRI, which omits the gadolinium contrast sequence, is a shorter and cheaper alternative offering time-saving capacity gains for health systems globally. To assess whether biparametric MRI is noninferior to multiparametric MRI for diagnosis of clinically significant prostate cancer. A prospective, multicenter, within-patient, noninferiority trial of biopsy-naive men from 22 centers (12 countries) with clinical suspicion of prostate cancer (elevated prostate-specific antigen [PSA] level and/or abnormal digital rectal examination findings) from April 2022 to September 2023, with the last follow-up conducted on December 3, 2024. Participants underwent multiparametric MRI, comprising T2-weighted, diffusion-weighted, and dynamic contrast–enhanced (DCE) sequences. Radiologists reported abbreviated biparametric MRI first (T2-weighted and diffusion-weighted), blinded to the DCE sequence. After unblinding, radiologists reported the full multiparametric MRI. Patients underwent a targeted biopsy with or without systematic biopsy if either biparametric MRI or multiparametric MRI was suggestive of clinically significant prostate cancer. The primary outcome was the proportion of men with clinically significant prostate cancer. Secondary outcomes included the proportion of men with clinically insignificant cancer. The noninferiority margin was 5%. Of 555 men recruited, 490 were included for primary outcome analysis. Median age was 65 (IQR, 59-70) years and median PSA level was 5.6 (IQR, 4.4-8.0) ng/mL. The proportion of patients with abnormal digital rectal examination findings was 12.7%. Biparametric MRI was noninferior to multiparametric MRI, detecting clinically significant prostate cancer in 143 of 490 men (29.2%), compared with 145 of 490 men (29.6%) (difference, −0.4 [95% CI, −1.2 to 0.4] percentage points; P = .50). Biparametric MRI detected clinically insignificant cancer in 45 of 490 men (9.2%), compared with 47 of 490 men (9.6%) with the use of multiparametric MRI (difference, −0.4 [95% CI, −1.2 to 0.4] percentage points). Central quality control demonstrated that 99% of scans were of adequate diagnostic quality. In men with suspected prostate cancer, provided image quality is adequate, an abbreviated biparametric MRI scan, with or without targeted biopsy, could become the new standard of care for prostate cancer diagnosis. With approximately 4 million prostate MRIs performed globally annually, adopting biparametric MRI could substantially increase scanner throughput and reduce costs worldwide. ClinicalTrials.gov Identifier: NCT04571840

Multi-centre, multi-vendor validation of artificial intelligence (AI) software to detect clinically significant prostate cancer (PCa) using multiparametric magnetic resonance imaging (MRI) is lacking. We compared a new AI solution, validated on a separate dataset from different UK hospitals, to the original multidisciplinary team (MDT)-supported radiologist’s interpretations. A Conformité Européenne (CE)-marked deep-learning (DL) computer-aided detection (CAD) medical device (Pi) was trained to detect Gleason Grade Group (GG) ≥ 2 cancer using retrospective data from the PROSTATEx dataset and five UK hospitals (793 patients). Our separate validation dataset was on six machines from two manufacturers across six sites (252 patients). Data included in the study were from MRI scans performed between August 2018 to October 2022. Patients with a negative MRI who did not undergo biopsy were assumed to be negative (90.4

BACKGROUND AND OBJECTIVE:High-risk (HR) or intermediate-risk (IR) non-muscle-invasive bladder cancer (NMIBC) carries a high probability of recurrence and/or progression. We present the final analysis results of erdafitinib in HR- or IR-NMIBC with fibroblast growth factor receptor 3/2 alterations (FGFR3/2alt) from the phase 2 THOR-2 study. METHODS:Cohort 1 (HR-NMIBC papillary only) with prior bacillus Calmette-Guérin was randomized 2:1 to erdafitinib or intravesical chemotherapy. Cohorts 2 (carcinoma in situ ± papillary) and 3 (IR-NMIBC) received erdafitinib. The primary endpoint was recurrence-free survival (RFS) for cohort 1. Exploratory endpoints included complete response (CR) rate and duration of response (DoR) for cohorts 2 and 3. KEY FINDINGS AND LIMITATIONS:In cohort 1 (n = 73), median RFS was not reached (NR) for erdafitinib (95% confidence interval [CI] 28.6 mo-not estimable [NE]) and 11.6 mo (95% CI 5.3-NE) for intravesical chemotherapy (hazard ratio 0.28 [95% CI 0.13-0.61; nominal p = 0.0007]; median follow-up, 18.5 and 16.6 mo, respectively). In cohort 2 (n = 16), CR rates were 94% (95% CI 70-100%) and 81% (95% CI 54-96%) at 8 and 32 wk, respectively; the median DoR (mDoR) was 23.3 mo (95% CI 10.0-NE; n = 15). In cohort 3 (n = 18), the CR rate was 89% (95% CI 65-99%) and mDoR was NR (95% CI 13.4 mo-NE). Most common treatment-related adverse event in pooled erdafitinib cohorts (N = 83) was hyperphosphatemia (76%). Limitations include early termination in cohort 1 and small sample size that precluded prespecified hypothesis testing. CONCLUSIONS AND CLINICAL IMPLICATIONS:Oral erdafitinib demonstrated high efficacy in FGFR3/2alt HR-/IR-NMIBC, with a manageable safety profile.