​Background: Digital therapeutics show promise for managing urinary incontinence, but long-term effectiveness data are scarce. We assessed whether improvements achieved with app-based multimodal therapy are sustained over 48 weeks and whether timing of intervention initiation affects treatment response. Methods: This prespecified 48-week follow-up of the DINKS randomized-controlled trial followed women (≥18 years) with stress, urge, or mixed urinary incontinence across Germany. Participants received immediate app-based therapy (pelvic floor training, bladder training, cognitive behavioural strategies, and lifestyle guidance) or delayed app-based therapy after a 12-week waitlist. The primary outcome was change from baseline in ICIQ-UI-SF and I-QoL scores. Trial registration: NCT06389838. Findings: Both groups showed clinically meaningful and sustained improvements over 48 weeks. In the intervention group, gains achieved by week 12 were maintained (ICIQ-UI-SF −4·09 to −3·88; I-QoL +18·85 to +16·79). The control group achieved comparable improvements after receiving therapy. Time-aligned analyses showed no significant between-group differences for ICIQ-UI-SF; a modest I-QoL advantage for the intervention group at week 12 was not sustained. Pooled analyses confirmed durable effects exceeding the minimal clinically important difference at all timepoints (ICIQ-UI-SF −3·66 to −4·13; I-QoL +16·75 to +18·70). No adverse events were reported. Interpretation: App-based multimodal therapy produces durable improvements sustained for at least 48 weeks. Timing of intervention initiation does not affect long-term effectiveness, supporting flexible implementation in capacity-constrained health systems. Approximately half of participants transitioned to independent self-management. These findings support digital therapeutics as a first-line treatment option warranting confirmation in larger trials with active comparators.

OBJECTIVES:Squamous cell carcinoma (SCC) of the bladder is an aggressive histologic subtype with distinct clinical behavior and limited treatment options after platinum-based chemotherapy. This study aimed to evaluate potential therapeutic targets in bladder SCC. METHODS:A retrospective cohort of 790 patients who underwent radical cystectomy for bladder cancer between 2011 and 2021 was screened to identify cases with histologically confirmed SCC. All SCC cases in the pathology department from 2003 to 2011 were also reviewed. Clinical and pathological data from 54 patients were analyzed. A tissue microarray (TMA) was constructed, and immunohistochemical (IHC) analyses were performed for programmed death-ligand 1 (PD-L1), nectin cell adhesion molecule 4 (NECTIN4), trophoblast cell-surface antigen 2 (TROP2), human epidermal growth factor receptor 2 (HER2), carcinoembryonic antigen-related cell adhesion molecule 5 (CEACAM5), and CD8+ T cells. Expression levels were assessed for prognostic relevance using the log-rank test and Kaplan-Meier survival analysis. RESULTS:A TMA comprising samples from 42 of 54 patients (22 pure SCC, 20 partial SCC) was successfully constructed. NECTIN4 (positive vs. negative) expression, PD-L1 (combined positive score ≥ 10 vs. <10) expression, and CD8+ density (high vs. low) showed a nearly equal distribution across the cohort. HER2 expression was detected in 14.3% of cases, CEACAM5 in 21.4%, and TROP2 in 83.3% of tumors. High NECTIN4 expression, increased CD8+ density, and administration of adjuvant chemotherapy were associated with improved overall survival. CONCLUSION:Several actionable targets were identified in bladder SCC, supporting further exploration of targeted therapies.

5127 Background: The fibroblast activation protein (FAP) is overexpressed in tumor tissue by cancer associated fibroblasts and radiopharmaceuticals can bind to this target. Recently, the 68 Ga-FAPI PET has emerged as a novel imaging modality for optimized differentiation between benign and malignant lesions. However, data on patients with testicular germ cell tumors (TGCT) are rare. This prospective study aims to investigate the expression, uptake and sensitivity of the 68 Ga-FAPI PET in TGCT patients. Methods: In this prospective observational phase Ib study, patients with TGCT up to clinical stage III and unfavorable TGCT histology in the testis such as teratomas were included. A 68 Ga-FAPI PET was performed in all included patients and analyzed with static (SUVmax/mean). Histology from the testis and whenever available from the metastasis were also stained for FAP and manually categorized into negative, medium and high expression. This study was approved by the local ethics committee (no 2024-17844). Results: We included 12 patients with a mean age of 34.5 (SD 8.81). Clinical stage at time of inclusion were CS II (n = 9), CS1 (n = 1) and CS III (n = 1) as well as one extragonadal TGCT. In eight and four cases the 68 Ga-FAPI PET was performed before and after completion of curative chemotherapy, respectively. Histology was available in six cases (5 = LNs, 1 = mediastinal tumor). FAP expression in the tumor of the testis was high in 50%, and in metastasis 60%. Stratification for high and low FAP lesions was performed according to mean SUVmax of 7.81 (SD 7,9) for all radiographic and histopathologic true positive metastasis. Sensitivity for 68 Ga-FAPI PET was 57% with a specificity 100%. Conclusions: This is the first prospective study that evaluates 68 Ga-FAPI PET in TGCT patients with the largest cohort so far. Stratification for SUVmax lesions above 7.81 showed excellent specificity, and the 68Ga-FAPI PET might potentially serve as a useful novel imaging modality for primary staging in clinical stages IIA and IIB, as well as post-chemotherapy with residual mass.

To better reflect the first two authors’ contributions in the original article [...]

Background and objective:Postprostatectomy incontinence (PPI) reduces quality of life, yet remains undertreated despite effective surgical options. Persistently low intervention rates in Europe for PPI suggest a care gap. This study assessed patients' knowledge of surgical PPI treatments and barriers to treatment uptake. Methods:Cross-sectional baseline analysis of ProKontinenz trial. Men with persistent PPI for ≥12 mo after radical prostatectomy (≥2 pads/d, no prior incontinence surgery) from 34 certified prostate cancer centers were surveyed during January-June 2025, using validated questionnaires and 24-h pad test. The primary outcome was knowledge of incontinence surgery; secondary outcomes included information sources, treatment barriers, and associations with symptom burden/quality of life. Associations with knowledge were assessed using logistic regression. Key findings and limitations:A total of 526 of 692 men participated (90% response rate). Among the participants, common reasons for not considering incontinence surgery were satisfaction with incontinence products (79%), concerns about surgical risks (53%), and doubts about success of surgery (51%). Fifty-nine percent men reported no knowledge of surgical PPI treatment. Independent predictors of lacking knowledge were low urine loss (odds ratio [OR] 2.4, 95% confidence interval [CI] 1.3-4.7), less severe King's Health Questionnaire (KHQ)-score "role limitation" (OR 2.2, 95% CI 1.1-4.3), concerns about treatment success (OR 2.2, 95% CI 1.2-4.1), and missing information from the urologist (OR 4.2, 95% CI 1.1-16.7) or partner (OR 2.0, 95% CI 1.2-3.8). Limitations of the study include self-reported data and a nonvalidated definition of "knowledge." Conclusions and clinical implications:Among patients with PPI for ≥12 mo after radical prostatectomy, more than half did not have any knowledge of potentially effective surgery. Information deficits and symptom severity influence knowledge. Strengthening guideline-based information and clinician-patient communication may help close this gap.

Following implementation of a standardized hydrocelectomy protocol under local anesthesia combined with systemic analgesia at a tertiary referral center, we evaluated its feasibility, safety, and patient acceptance. In this retrospective single-center study, 35 consecutive patients underwent hydrocelectomy between May 2024 and August 2025 via a standardized in situ spermatic cord block. All patients received protocol-based systemic analgesia (1 g metamizole i.v. and 7.5 mg piritramide s.c.). Anticoagulants were paused 48 h preoperatively and resumed postoperatively, while antiplatelet therapy was continued. The primary endpoint was completion without conversion to analgosedation or general anesthesia. Secondary endpoints included procedural pain (VAS), postoperative complications (Clavien–Dindo), and patient satisfaction. Hydrocelectomy was completed under local anesthesia and systemic analgesic support in 33/35 patients (94

BACKGROUND:Therapeutic decisions in clinical oncology are commonly established through interdisciplinary consensus in multidisciplinary cancer conferences (MCC). Artificial intelligence (AI) may support these processes by generating data-driven treatment recommendations (TR). We developed and evaluated an explainable AI system designed to reproduce MCC-based treatment decisions for metastatic and non-metastatic prostate cancer (PC). METHODS:Clinical data from patients with histologically confirmed PC discussed in MCC between 2015 and 2022 were transformed into structured datasets. A hierarchical modeling framework was implemented to first predict overarching treatment categories and subsequently specify therapeutic strategies. Multiple machine learning and deep learning algorithms were trained to replicate MCC recommendations. Model performance was assessed using F1-scores. RESULTS:A total of 5478 MCC cases including 76 clinical input variables and 23 treatment output parameters were analyzed. The AI system generated automated TR with high predictive accuracy across both hierarchical levels. For high-level categories, F1-scores reached 0.89 for surgery and 0.81 for radiation therapy. For detailed recommendations, F1-scores reached 0.99 for prostatectomy and 0.98 for PSMA-ligand therapy. Lower performance in anti-cancer drug categories likely reflects smaller sample sizes. Feature importance analyses ensured model transparency and interpretability. CONCLUSION:To our knowledge, this study presents one of the first large-scale explainable AI system capable of generating MCC-aligned treatment recommendations for metastatic and non-metastatic PC within a multi-target framework. It incorporates the largest reported number of clinical input and treatment output parameters in this setting. Strong predictive performance and interpretability support its potential as a scalable decision-support tool in multidisciplinary oncology. Prospective validation is warranted.

Aggressive metastatic progression often develops in bladder cancer patients with acquired cisplatin or gemcitabine resistance. The potential of the natural isothiocyanates allyl-isothiocyanate (AITC), butyl-isothiocyanate (BITC), and phenylethyl-isothiocyanate (PEITC) to inhibit adhesion and migration of cisplatin- or gemcitabine-resistant and sensitive RT112, T24, and TCCSUP bladder cancer cell lines was investigated. Parameters determined were: cell interaction with collagen or fibronectin, chemotaxis, and membrane receptors involved in adhesion (total and activated integrins β1, β4, β5, CD44s, and CD44v3-v7). CD44s’ location and adhesion- and migration-related signaling proteins were determined. AITC blocked adhesion of almost all sensitive and resistant cancer cells. PEITC and BITC suppressed fibronectin interaction of sensitive and resistant RT112. All three isothiocyanates diminished chemotaxis in all cell lines. Integrin expression was differentially altered but CD44s and CD44v were not altered. BITC and PEITC translocated CD44s from the cell membrane to cytoplasm. The tumor suppressor E-cadherin increased, whereas focal adhesion kinase (FAK), linked to integrin signaling, was deactivated after isothiocyanate treatment. Blocking FAK, β1, β4, or β5 was associated with reduced chemotaxis. Thus, AITC, BITC, and PEITC blocked adhesion and migration in cisplatin- and gemcitabine-resistant bladder cancer cells. This was associated with altered integrin expression and signaling, CD44s translocation, and enhanced E-cadherin.

e17022 Background: Despite ongoing research and evolving therapeutic landscapes, advanced urological malignancies such as prostate cancer (PC), bladder/urothelial cancer (BC), renal cell carcinoma (RCC), and penile cancer (PeC) remain associated with an unfavorable prognosis. While molecularly targeted therapies in PC are already clinically established, their use in other urological entities remains limited. The aim of this study was to analyze the real-world implementation of molecular diagnostics and its therapeutic consequences in a single-center tertiary setting. Methods: In a retrospective database analysis, all patients presenting at our university-based interdisciplinary tumor board (ITB) between 2018 and 2024 were included. Cases with a recommendation for molecular diagnostics were identified and categorized according to tumor entity. Molecular analyses were performed using disease-specific or pan-oncological next-generation sequencing (NGS) panels. Treatment recommendations were evaluated by the Molecular Tumor Board (MTB). Molecular data (including mutations, therapy recommendations, level of evidence, and administered molecular therapies), were analyzed. Results: Out of a total of 11,562 cases discussed in the ITB, molecular diagnostics followed by presentation at the MTB were recommended in 332 (2.9%) cases. Molecular analyses were actually performed in 113 (29.4%, overall cohort: 1.5%) patients, including 64 PC, 24 BC, 22 RCC, and three PeC patients, as well as 66 cases with isolated BRCA testing. The most frequent genetic alterations were PTEN in PC, HER2 and FGFR in BC, VHL in RCC, and EGFR in PeC. BRCA1/2 mutations were detected in 13.6%. Molecularly targeted therapies were initiated in 14 patients including PARP inhibition. Conclusions: Molecular diagnostics is gaining increasing importance in urological oncology; however, in routine clinical practice it rarely translates into therapeutic consequences. BRCA testing and PARP inhibition were the most common treatment. These findings highlight the need for structured molecular testing, prospective data collection, and further development of evidence-based treatment options to better exploit the potential of personalized therapies in uro-oncology.

Background and aimsIncidence of and risk factors for parastomal hernia after robot-assisted (RA) cystectomy with ileum conduit (IC) are not well established. The aims of this systematic review were to summarize the literature (1) on the incidence of parastomal hernia after RA cystectomy and IC reconstruction; (2) on risk or protective factors associated with the development of parastomal hernias after RA cystectomy and IC reconstruction; and (3) on outcomes of minimal invasive parastomal hernia repair in patients with IC.Methodswe conducted literature searches in Medline, EMBASE, and CINHAL up to April 2025 without language restriction. Two independent assessors evaluated eligibility and quality of the included study. Due to high heterogeneity, meta-analysis was not attempted.Resultsout of 368 records, 11 and 2 papers provided information on the incidence of parastomal hernia and on risk factors, respectively. For the outcome of minimal invasive IC hernia repair, 7 studies were included. Most studied presented high risk of bias and the incidence rate varied widely across studies. Similar findings were observed for hernia recurrence after minimal invasive hernia repair.ConclusionA relevant proportion of patients may experience parastomal hernia of IC after RA-cystectomy, however incidence figures varied widely. Information on factors influencing the development of parastomal hernia after RA cystectomy is essentially lacking. Finally, the evidence on the outcome of minimal invasive hernia repair in IC patients is very limited both in terms of quantity and of quality. There is urgent need to address the knowledge gaps detected by this systematic review. Cooperation to achieve prospective multicentre designs with adequate sample size and systematic follow-up methods would be crucial factors to generate the high-quality data required to develop evidence-based strategies to prevent parastomal hernias.

BACKGROUND:The interest in digital information on pelvic floor dysfunction is constantly increasing. Various digital platforms offer an easy and anonymous way for patients to seek information about their condition. However, little is known about the quality of the information on the different platforms or about the how the quality of different sites compares. OBJECTIVE:The aim of this study was to investigate the completeness and quality of information on the search term "stress urinary incontinence" in comparison between different digital platforms. MATERIALS AND METHODS:A systematic analysis of the keyword search "stress urinary incontinence" was performed on Google and the social networks Facebook, YouTube, Instagram, and LinkedIn. The first 30 search results on each platform were evaluated. The results were categorized according to information content and readability. The Health On the Net Foundation (HON) seal was used to assess medical quality. RESULTS:The proportion of informative content was highest on YouTube (97%) and Google (93%). Content was predominantly provided by professional organizations on Google and YouTube. Information on conservative therapies dominated across all platforms. Surgical therapies were only discussed in up to 63% of results on Google and in up to 50% of results on YouTube. In most cases, there was also no comprehensive presentation of all surgical options. The readability of the texts was unsuitable for laypersons on all platforms, and HON certification was only present on Google (37%) and YouTube (3%). CONCLUSION:The results offer practical insights into the quality of digital information on stress urinary incontinence. However, they show deficits in readability and comprehensive presentation of surgical therapies. The physician-patient relationship remains indispensable for taking individual needs into account and avoiding misinformation.

The qualitative heterogeneity of multiparametric MRI (mpMRI) poses significant challenges for the diagnostic pathway of prostate cancer (PCa). The Prostate Imaging Quality Score (PI-QUAL) is a novel tool for the qualitative assessment of mpMRI. Aim of this study was to evaluate the impact of PI-QUAL on consistency of radiological to pathological T-stage. Patients undergoing MRI-TRUS fusion biopsy and radical prostatectomy (RP) from 01/2016 to 03/2024 were retrospectively included. PI-QUAL was determined by two expert radiologists and categorised: inadequate (1–2), sufficient (3) and optimal (4–5). Primary endpoint was upstaging from locally confined disease in mpMRI (mrT ≤ 2) to advanced in RP-specimen (pT ≥ 3a). Variables were compared using analysis of variance and χ2 or Fisher’s exact test. Uni- and multivariate binary regression identified independent predictors. Of 349 patients included, 18 had PI-QUAL 1–2, 44 PI-QUAL 3 and 287 PI-QUAL 4–5. Patient characteristics, PI-RADS scores and biopsy counts were balanced between these groups. Upstaging from mrT ≤ 2 to pT ≥ 3a was significantly more frequent in PI-QUAL 1–2 (22.4

OBJECTIVE:Multiple system atrophy (MSA) is a progressive neurodegenerative disorder categorized as an atypical Parkinsonian syndrome, affecting extrapyramidal, pyramidal, cerebellar, and autonomic systems. Lower urinary tract dysfunction (LUTD), including urgency, frequency, urge incontinence, and incomplete voiding, is a prevalent symptom, often appearing early in the disease. Conservative treatments, such as anticholinergic and alpha-blocker therapies, frequently fail due to poor tolerance and limited efficacy. Many patients also experience bowel symptoms, including constipation and fecal incontinence. This study evaluates sacral neuromodulation (SNM) as a treatment option for LUTD and bowel symptoms in advanced MSA. MATERIALS AND METHODS:In this retrospective case series eight patients (4 females, 4 males; mean age 53 years, range 45-61) with refractory LUTD and bowel symptoms underwent detailed urodynamic evaluations and percutaneous sacral nerve test stimulation. Electrodes were placed bilaterally at the S3 and S4 sacral nerve roots under local anesthesia. During an 8-day test phase, unilateral and bilateral stimulations were applied at frequencies of 3-120 Hz. Success was defined as a ≥ 50% reduction in symptoms, assessed through bladder diaries. RESULTS:Seven patients qualified for permanent SNM implantation (4 unilateral S3, 3 bilateral S3/S4). At 2 months postimplantation, six patients exhibited ≥ 50% LUT symptom reduction. One patient showed improvement after reprogramming at 9 months. During a median 35-month follow-up, LUT relief was maintained in 36 of 44 visits, with reprogramming required in 19. SNM efficacy diminished over time, with five patients eventually requiring suprapubic tubes. Initially, three patients reported bowel symptoms; during follow-up, four additional cases emerged. Despite waning LUT effects, SNM facilitated defecation in some patients. DISCUSSION:This retrospective case series indicate that SNM targeting S3 and S4 nerves offers temporary relief for LUTD and bowel symptoms in advanced MSA. Further research is necessary to optimize patient selection, stimulation parameters, and long-term management strategies.

Primary signet ring cell carcinoma of the urinary bladder (PSRCCB) is an exceedingly rare subtype of urinary bladder carcinoma, comprising 0.12%-0.6% of cases, with a poor prognosis. This case report details a distinctive case of a 32-year-old woman with PSRCCB, presenting without typical risk factors and posing diagnostic and therapeutic challenges. Initial symptoms included urinary tract infection and lower abdominal pain. Imaging and histological assessments identified a mucinous adenocarcinoma with signet ring cell components. The patient underwent curative open partial cystectomy, given her young age and localized tumor, avoiding lymphadenectomy and adjuvant chemotherapy due to complete tumor resection and absence of metastases. Postoperative follow-up showed no pathological findings, underscoring the importance of individualized treatment strategies in rare cancer cases. This case contributes to the limited data on PSRCCB and its management.

OBJECTIVE:To evaluate the impact of previous intravesical treatment with Bacillus Calmette-Guérin (BCG) or mitomycin on postoperative complications and oncologic outcome in non-muscle invasive bladder cancer (NMIBC) patients receiving radical cystectomy (RC). PATIENTS AND METHODS:Between 2016 and 2021, 366 patients who received RC for bladder cancer (BC) were screened. Patients with intravesical treatment with either BCG or mitomycin for NMIBC were compared to patients with BC without prior intravesical treatment. Patients were matched manually for ASA-score, BMI cluster, age, and sex. TNM stages were used as covariates in the analysis model. All complications within 30 days post-surgery and the 90-day mortality rates were analyzed. Patient characteristics were compared between groups using Chi2-tests, and associations were evaluated by logistic regression. Firth logistic regression was applied for comorbidities. Kaplan-Meier curves were generated for overall survival (OS) and progression-free survival (PFS), and Cox regression analysis was performed to further assess survival outcomes. RESULTS:We identified 51 matched patients receiving BCG or mitomycin for NMIBC. Nine women and 42 men were in the interventional group with a mean age of 70 and a BMI of 27.6. In both groups, ASA-score 2, 3, and 4 were present in 18, 29, and four patients. According to the Clavien-Dindo (CD) classification grade ≥ 3b, neither the incidence nor severity of complications differed significantly between groups. Final histopathology and survival outcomes (OS, PFS) were comparable. No associations were found between complications and urinary diversion or surgical approach. As expected, advanced T- and N-stages correlated with worse survival, while coronary artery disease (CAD) was significantly associated with postoperative complications. CONCLUSIONS:To our knowledge, this is the first matched pair analysis that evaluates the impact of intravesical treatment on postoperative complications for patients with NMIBC receiving RC. Intravesical treatment with BCG or mitomycin did not deteriorate postoperative complications in NMIBC patients after RC, irrespective of the final histopathology stage. Oncologic outcomes were similar in both groups.

Although multimodal therapeutic management has significantly improved outcome in prostate cancer (PCa) patients, treatment options for castrate-resistant disease remain challenging. Plant-derived mistletoe extracts have supported cancer patients and are, therefore, widely used as complementary medicine. However, mechanisms behind possible mistletoe benefits to PCa patients remain to be explored. The present study was designed to evaluate the effect of mistletoe extracts from four different host trees (Tiliae, Populi, Salicis, and Crataegi) on the growth and proliferation of PCa cell lines in vitro. PC3, DU145, and LNCaP cells were used to evaluate tumor cell growth (MTT assay) and proliferation (BrdU incorporation assay). Clonogenicity, apoptosis, cell cycle, and cell-cycle-regulating proteins (cyclin-dependent kinases (CDKs) and cyclins) were investigated, as was CD44 standard and splice variant expression and integrin α and β receptors. SiRNA knockdown studies were employed to investigate the functional relevance of integrins. All mistletoe extracts significantly inhibited cell growth in a dose-dependent manner and cell proliferation and clonogenicity were suppressed. Populi and Salicis induced cell-cycle arrest in the G2/M phase and increased apoptosis. Both extracts down-regulated CDK1 and cyclin A and altered CD44 expression. Integrins α5 in all cell lines and α6 in DU145 and LNCaP were particularly diminished. Knocking down α5 and α6 induced cell growth inhibition in DU145. Mistletoe extracts block the growth and proliferation of PCa cells in vitro and therefore qualify for use in future animal studies to evaluate mistletoe as an adjunct to standard PCa treatment.

BACKGROUND:The value of the retroperitoneal (R-RAPN) compared with the conventional transperitoneal (T-RAPN) approach in robot-assisted partial nephrectomy has not been finally clarified. The current work's objective was to prospectively investigate R-RAPN versus T-RAPN. METHODS:The study was designed as a prospective, controlled, non-randomized study with a non-inferiority design. The primary endpoint was Trifecta achievement. The sample size calculation required 141 T-RAPN and 94 R-RAPN. RESULTS:When the recruitment target of 141 was reached in the T-RAPN arm, only 34 R-RAPN had been performed, so the study was terminated early. Trifecta as the main outcome parameter was achieved in 82% of the R-RAPN and 76% of the T-RAPN groups, so no sign for inferiority could be detected (p = 0.6). CONCLUSIONS:In this prospective study, there was no evidence of inferiority of R-RAPN compared to T-RAPN for the Trifecta endpoint. R-RAPN may be an individually advantageous alternative to T-RAPN for selected patients. TRIAL REGISTRATION:The study was registered in the German Clinical Trials Register (DRKS00028619).

BACKGROUND:Decisions on the best available treatment in clinical oncology are based on expert opinions in multidisciplinary cancer conferences (MCC). Artificial intelligence (AI) could increase evidence-based treatment by generating additional treatment recommendations (TR). We aimed to develop such an AI system for urothelial carcinoma (UC) and renal cell carcinoma (RCC). METHODS:Comprehensive data of patients with histologically confirmed UC and RCC who received MCC recommendations in the years 2015 - 2022 were transformed into machine readable representations. Development of a two-step process to train a classifier to mimic TR was followed by identification of superordinate and detailed categories of TR. Machine learning (CatBoost, XGBoost, Random Forest) and deep learning (TabPFN, TabNet, SoftOrdering CNN, FCN) techniques were trained. Results were measured by F1-scores for accuracy weights. RESULTS:AI training was performed with 1617 (UC) and 880 (RCC) MCC recommendations (77 and 76 patient input parameters). The AI system generated fully automated TR with excellent F1-scores for UC (e.g. 'Surgery' 0.81, 'Anti-cancer drug' 0.83, 'Gemcitabine/Cisplatin' 0.88) and RCC (e.g. 'Anti-cancer drug' 0.92 'Nivolumab' 0.78, 'Pembrolizumab/Axitinib' 0.89). Explainability is provided by clinical features and their importance score. Finally, TR and explainability were visualized on a dashboard. CONCLUSION:This study demonstrates for the first time AI-generated, explainable TR in UC and RCC with excellent performance results as a potential support tool for high-quality, evidence-based TR in MCC. The comprehensive technical and clinical development sets global reference standards for future AI developments in MCC recommendations in clinical oncology. Next, prospective validation of the results is mandatory.