Machine Learning and External Validation of the IDENTIFY Risk Calculator for Patients with Haematuria Referred to Secondary Care for Suspected Urinary Tract Cancer.

BACKGROUND: The IDENTIFY study developed a model to predict urinary tract cancer using patient characteristics from a large multicentre, international cohort of patients referred with haematuria. In addition to calculating an individual's cancer risk, it proposes thresholds to stratify them into very-low-risk (<1%), low-risk (1-<5%), intermediate-risk (5-<20%), and high-risk (≥20%) groups. OBJECTIVE: To externally validate the IDENTIFY haematuria risk calculator and compare traditional regression with machine learning algorithms. DESIGN, SETTING, AND PARTICIPANTS: Prospective data were collected on patients referred to secondary care with new haematuria. Data were collected for patient variables included in the IDENTIFY risk calculator, cancer outcome, and TNM staging. Machine learning methods were used to evaluate whether better models than those developed with traditional regression methods existed. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: The area under the receiver operating characteristic curve (AUC) for the detection of urinary tract cancer, calibration coefficient, calibration in the large (CITL), and Brier score were determined. RESULTS AND LIMITATIONS: There were 3582 patients in the validation cohort. The development and validation cohorts were well matched. The AUC of the IDENTIFY risk calculator on the validation cohort was 0.78. This improved to 0.80 on a subanalysis of urothelial cancer prevalent countries alone, with a calibration slope of 1.04, CITL of 0.24, and Brier score of 0.14. The best machine learning model was Random Forest, which achieved an AUC of 0.76 on the validation cohort. There were no cancers stratified to the very-low-risk group in the validation cohort. Most cancers were stratified to the intermediate- and high-risk groups, with more aggressive cancers in higher-risk groups. CONCLUSIONS: The IDENTIFY risk calculator performed well at predicting cancer in patients referred with haematuria on external validation. This tool can be used by urologists to better counsel patients on their cancer risks, to prioritise diagnostic resources on appropriate patients, and to avoid unnecessary invasive procedures in those with a very low risk of cancer. PATIENT SUMMARY: We previously developed a calculator that predicts patients' risk of cancer when they have blood in their urine, based on their personal characteristics. We have validated this risk calculator, by testing it on a separate group of patients to ensure that it works as expected. Most patients found to have cancer tended to be in the higher-risk groups and had more aggressive types of cancer with a higher risk. This tool can be used by clinicians to fast-track high-risk patients based on the calculator and investigate them more thoroughly.

The Transatlantic Recommendations for Prostate Gland Evaluation with Magnetic Resonance Imaging After Focal Therapy (TARGET): A Systematic Review and International Consensus Recommendations.

BACKGROUND AND OBJECTIVE: Magnetic resonance imaging (MRI) can detect recurrences after focal therapy for prostate cancer but there is no robust guidance regarding its use. Our objective was to produce consensus recommendations on MRI acquisition, interpretation, and reporting after focal therapy. METHODS: A systematic review was performed in July 2022 to develop consensus statements. A two-round consensus exercise was then performed, with a consensus meeting in January 2023, during which 329 statements were scored by 23 panellists from Europe and North America spanning urology, radiology, and pathology with experience across eight focal therapy modalities. Using RAND Corporation/University of California-Los Angeles methodology, the Transatlantic Recommendations for Prostate Gland Evaluation with MRI after Focal Therapy (TARGET) were based on consensus for statements scored with agreement or disagreement. KEY FINDINGS AND LIMITATIONS: In total, 73 studies were included in the review. All 20 studies (100%) reporting suspicious imaging features cited focal contrast enhancement as suspicious for cancer recurrence. Of 31 studies reporting MRI assessment criteria, the Prostate Imaging-Reporting and Data System (PI-RADS) score was the scheme used most often (20 studies; 65%), followed by a 5-point Likert score (six studies; 19%). For the consensus exercise, consensus for statements scored with agreement or disagreement increased from 227 of 295 statements (76.9%) in round one to 270 of 329 statements (82.1%) in round two. Key recommendations include performing routine MRI at 12 mo using a multiparametric protocol compliant with PI-RADS version 2.1 standards. PI-RADS category scores for assessing recurrence within the ablation zone should be avoided. An alternative 5-point scoring system is presented that includes a major dynamic contrast enhancement (DCE) sequence and joint minor diffusion-weighted imaging and T2-weighted sequences. For the DCE sequence, focal nodular strong early enhancement was the most suspicious imaging finding. A structured minimum reporting data set and minimum reporting standards for studies detailing MRI data after focal therapy are presented. CONCLUSIONS AND CLINICAL IMPLICATIONS: The TARGET consensus recommendations may improve MRI acquisition, interpretation, and reporting after focal therapy for prostate cancer and provide minimum standards for study reporting. PATIENT SUMMARY: Magnetic resonance imaging (MRI) scans can detect recurrent of prostate cancer after focal treatments, but there is a lack of guidance on MRI use for this purpose. We report new expert recommendations that may improve practice.

Diagnostic Performance of 68Ga-PSMA-11 PET/CT Versus Multiparametric MRI for Detection of Intraprostatic Radiorecurrent Prostate Cancer.

For men with prostate cancer who develop biochemical failure after radiotherapy, European guidelines recommend reimaging with 68Ga-PSMA-11 PET/CT and multiparametric MRI (mpMRI). However, the accuracy of 68Ga-PSMA-11 PET/CT for detecting intraprostatic recurrences is unclear, both with and without mpMRI. Methods: A single-center retrospective study of a series of patients investigated for radiorecurrence between 2016 and 2022 is described. All patients underwent 68Ga-PSMA-11 PET/CT, mpMRI, and prostate biopsy. PET/CT images were interpreted independently by 2 expert readers masked to other imaging and clinical data. The primary outcome was the diagnostic accuracy of PET/CT versus mpMRI and of PET/CT with mpMRI together versus mpMRI alone. The secondary outcome was the proportion of cancers missed by mpMRI but detected by PET/CT. Diagnostic accuracy analysis was performed at the prostate hemigland level using cluster bootstrapping. Results: Thirty-five men (70 hemiglands) were included. Cancer was confirmed by biopsy in 43 of 70 hemiglands (61%). PET/CT sensitivity and negative predictive values (NPVs) were 0.89 (95% CI, 0.78-0.98) and 0.79 (95% CI, 0.62-0.95), respectively, which were not significantly different from results by MRI (sensitivity of 0.72; 95% CI, 0.61-0.83; P = 0.1) (NPV of 0.59; 95% CI, 0.41-0.75; P = 0.07). Specificity and positive predictive values were not significantly different. When PET/CT and MRI were used together, the sensitivity was 0.98 (95% CI, 0.92-1.00) and NPV was 0.93 (95% CI, 0.75-1.00), both significantly higher than MRI alone (P = 0.003 and P < 0.001, respectively). Specificity and positive predictive values remained not significantly different. MRI missed 12 of 43 cancers (28%; 95% CI, 17%-43%), of which 11 of 12 (92%; 95% CI, 62%-100%) were detected by PET/CT. Conclusion: For detecting intraprostatic radiorecurrence, 68Ga-PSMA-11 PET/CT has high sensitivity that is not significantly different from mpMRI. When 68Ga-PSMA-11 PET/CT and mpMRI were used together, the results conferred a significantly greater sensitivity and NPV than with mpMRI alone. 68Ga-PSMA-11 PET/CT may therefore be a useful tool in the diagnosis of localized radiorecurrence.

The Role of Multiparametric MRI and MRI-targeted Biopsy in the Diagnosis of Radiorecurrent Prostate Cancer: An Analysis from the FORECAST Trial.

BACKGROUND: The role of multiparametric magnetic resonance imaging (MRI) for detecting recurrent prostate cancer after radiotherapy is unclear. OBJECTIVE: To evaluate MRI and MRI-targeted biopsies for detecting intraprostatic cancer recurrence and planning for salvage focal ablation. DESIGN, SETTING, AND PARTICIPANTS: FOcal RECurrent Assessment and Salvage Treatment (FORECAST; NCT01883128) was a prospective cohort diagnostic study that recruited 181 patients with suspected radiorecurrence at six UK centres (2014 to 2018); 144 were included here. INTERVENTION: All patients underwent MRI with 5 mm transperineal template mapping biopsies; 84 had additional MRI-targeted biopsies. MRI scans with Likert scores of 3 to 5 were deemed suspicious. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: First, the diagnostic accuracy of MRI was calculated. Second, the pathological characteristics of MRI-detected and MRI-undetected tumours were compared using the Wilcoxon rank sum test and chi-square test for trend. Third, four biopsy strategies involving an MRI-targeted biopsy alone and with systematic biopsies of one to two other quadrants were studied. Fisher's exact test was used to compare MRI-targeted biopsy alone with the best other strategy for the number of patients with missed cancer and the number of patients with cancer harbouring additional tumours in unsampled quadrants. Analyses focused primarily on detecting cancer of any grade or length. Last, eligibility for focal therapy was evaluated for men with localised (≤T3bN0M0) radiorecurrent disease. RESULTS AND LIMITATIONS: Of 144 patients, 111 (77%) had cancer detected on biopsy. MRI sensitivity and specificity at the patient level were 0.95 (95% confidence interval [CI] 0.92 to 0.99) and 0.21 (95% CI 0.07 to 0.35), respectively. At the prostate quadrant level, 258/576 (45%) quadrants had cancer detected on biopsy. Sensitivity and specificity were 0.66 (95% CI 0.59 to 0.73) and 0.54 (95% CI 0.46 to 0.62), respectively. At the quadrant level, compared with MRI-undetected tumours, MRI-detected tumours had longer maximum cancer core length (median difference 3 mm [7 vs 4 mm]; 95% CI 1 to 4 mm, p < 0.001) and a higher grade group (p = 0.002). Of the 84 men who also underwent an MRI-targeted biopsy, 73 (87%) had recurrent cancer diagnosed. Performing an MRI-targeted biopsy alone missed cancer in 5/73 patients (7%; 95% CI 3 to 15%); with additional systematic sampling of the other ipsilateral and contralateral posterior quadrants (strategy 4), 2/73 patients (3%; 95% CI 0 to 10%) would have had cancer missed (difference 4%; 95% CI -3 to 11%, p = 0.4). If an MRI-targeted biopsy alone was performed, 43/73 (59%; 95% CI 47 to 69%) patients with cancer would have harboured undetected additional tumours in unsampled quadrants. This reduced but only to 7/73 patients (10%; 95% CI 4 to 19%) with strategy 4 (difference 49%; 95% CI 36 to 62%, p < 0.0001). Of 73 patients, 43 (59%; 95% CI 47 to 69%) had localised radiorecurrent cancer suitable for a form of focal ablation. CONCLUSIONS: For patients with recurrent prostate cancer after radiotherapy, MRI and MRI-targeted biopsy, with or without perilesional sampling, will diagnose cancer in the majority where present. MRI-undetected cancers, defined as Likert scores of 1 to 2, were found to be smaller and of lower grade. However, if salvage focal ablation is planned, an MRI-targeted biopsy alone is insufficient for prostate mapping; approximately three of five patients with recurrent cancer found on an MRI-targeted biopsy alone harboured further tumours in unsampled quadrants. Systematic sampling of the whole gland should be considered in addition to an MRI-targeted biopsy to capture both MRI-detected and MRI-undetected disease. PATIENT SUMMARY: After radiotherapy, magnetic resonance imaging (MRI) is accurate for detecting recurrent prostate cancer, with missed cancer being smaller and of lower grade. Targeting a biopsy to suspicious areas on MRI results in a diagnosis of cancer in most patients. However, for every five men who have recurrent cancer, this targeted approach would miss cancers elsewhere in the prostate in three of these men. If further focal treatment of the prostate is planned, random biopsies covering the whole prostate in addition to targeted biopsies should be considered so that tumours are not missed.

Re-evaluating the diagnostic efficacy of PSA as a referral test to detect clinically significant prostate cancer in contemporary MRI-based image-guided biopsy pathways.

Introduction: Modern image-guided biopsy pathways at diagnostic centres have greatly refined the investigations of men referred with suspected prostate cancer. However, the referral criteria from primary care are still based on historical prostate-specific antigen (PSA) cut-offs and age-referenced thresholds. Here, we tested whether better contemporary pathways and biopsy methods had improved the predictive utility value of PSA referral thresholds. Methods: PSA referral thresholds, age-referenced ranges and PSA density (PSAd) were assessed for positive predictive value (PPV) in detection of clinically significant prostate cancer (csPCa - histological ⩾ Grade Group 2). Data were analysed from men referred to three diagnostics centres who used multi-parametric magnetic resonance imaging (mpMRI)-guided prostate biopsies for disease characterisation. Findings were validated in a separate multicentre cohort. Results: Data from 2767 men were included in this study. The median age, PSA and PSAd were 66.4 years, 7.3 ng/mL and 0.1 ng/mL2, respectively. Biopsy detected csPCa was found in 38.7%. The overall area under the curve (AUC) for PSA was 0.68 which is similar to historical performance. A PSA threshold of ⩾ 3 ng/mL had a PPV of 40.3%, but this was age dependent (PPV: 24.8%, 32.7% and 56.8% in men 50-59 years, 60-69 years and ⩾ 70 years, respectively). Different PSA cut-offs and age-reference ranges failed to demonstrate better performance. PSAd demonstrated improved AUC (0.78 vs 0.68, p < 0.0001) and improved PPV compared to PSA. A PSAd of ⩾ 0.10 had a PPV of 48.2% and similar negative predictive value (NPV) to PSA ⩾ 3 ng/mL and out-performed PSA age-reference ranges. This improved performance was recapitulated in a separate multi-centre cohort (n = 541). Conclusion: The introduction of MRI-based image-guided biopsy pathways does not appear to have altered PSA diagnostic test characteristics to positively detect csPCa. We find no added value to PSA age-referenced ranges, while PSAd offers better PPV and the potential for a single clinically useful threshold (⩾0.10) for all age groups. Level of evidence: IV.

External validation of a risk model predicting failure of salvage focal ablation for prostate cancer.

OBJECTIVES: To externally validate a published model predicting failure within 2 years after salvage focal ablation in men with localised radiorecurrent prostate cancer using a prospective, UK multicentre dataset. PATIENTS AND METHODS: Patients with biopsy-confirmed ≤T3bN0M0 cancer after previous external beam radiotherapy or brachytherapy were included from the FOcal RECurrent Assessment and Salvage Treatment (FORECAST) trial (NCT01883128; 2014-2018; six centres), and from the high-intensity focussed ultrasound (HIFU) Evaluation and Assessment of Treatment (HEAT) and International Cryotherapy Evaluation (ICE) UK-based registries (2006-2022; nine centres). Eligible patients underwent either salvage focal HIFU or cryotherapy, with the choice based predominantly on anatomical factors. Per the original multivariable Cox regression model, the predicted outcome was a composite failure outcome. Model performance was assessed at 2 years post-salvage with discrimination (concordance index [C-index]), calibration (calibration curve and slope), and decision curve analysis. For the latter, two clinically-reasonable risk threshold ranges of 0.14-0.52 and 0.26-0.36 were considered, corresponding to previously published pooled 2-year recurrence-free survival rates for salvage local treatments. RESULTS: A total of 168 patients were included, of whom 84/168 (50%) experienced the primary outcome in all follow-ups, and 72/168 (43%) within 2 years. The C-index was 0.65 (95% confidence interval 0.58-0.71). On graphical inspection, there was close agreement between predicted and observed failure. The calibration slope was 1.01. In decision curve analysis, there was incremental net benefit vs a 'treat all' strategy at risk thresholds of ≥0.23. The net benefit was therefore higher across the majority of the 0.14-0.52 risk threshold range, and all of the 0.26-0.36 range. CONCLUSION: In external validation using prospective, multicentre data, this model demonstrated modest discrimination but good calibration and clinical utility for predicting failure of salvage focal ablation within 2 years. This model could be reasonably used to improve selection of appropriate treatment candidates for salvage focal ablation, and its use should be considered when discussing salvage options with patients. Further validation in larger, international cohorts with longer follow-up is recommended.

Audit, Feedback, and Education to Improve Quality and Outcomes in Transurethral Resection and Single-Instillation Intravesical Chemotherapy for Nonmuscle Invasive Bladder Cancer Treatment: Protocol for a Multicenter International Observational Study With an Embedded Cluster Randomized Trial.

BACKGROUND: Nonmuscle invasive bladder cancer (NMIBC) accounts for 75% of bladder cancers. It is common and costly. Cost and detriment to patient outcomes and quality of life are driven by high recurrence rates and the need for regular invasive surveillance and repeat treatments. There is evidence that the quality of the initial surgical procedure (transurethral resection of bladder tumor [TURBT]) and administration of postoperative bladder chemotherapy significantly reduce cancer recurrence rates and improve outcomes (cancer progression and mortality). There is surgeon-reported evidence that TURBT practice varies significantly across surgeons and sites. There is limited evidence from clinical trials of intravesical chemotherapy that NMIBC recurrence rate varies significantly between sites and that this cannot be accounted for by differences in patient, tumor, or adjuvant treatment factors, suggesting that how the surgery is performed may be a reason for the variation. OBJECTIVE: This study primarily aims to determine if feedback on and education about surgical quality indicators can improve performance and secondarily if this can reduce cancer recurrence rates. Planned secondary analyses aim to determine what surgeon, operative, perioperative, institutional, and patient factors are associated with better achievement of TURBT quality indicators and NMIBC recurrence rates. METHODS: This is an observational, international, multicenter study with an embedded cluster randomized trial of audit, feedback, and education. Sites will be included if they perform TURBT for NMIBC. The study has four phases: (1) site registration and usual practice survey; (2) retrospective audit; (3) randomization to audit, feedback, and education intervention or to no intervention; and (4) prospective audit. Local and national ethical and institutional approvals or exemptions will be obtained at each participating site. RESULTS: The study has 4 coprimary outcomes, which are 4 evidence-based TURBT quality indicators: a surgical performance factor (detrusor muscle resection); an adjuvant treatment factor (intravesical chemotherapy administration); and 2 documentation factors (resection completeness and tumor features). A key secondary outcome is the early cancer recurrence rate. The intervention is a web-based surgical performance feedback dashboard with educational and practical resources for TURBT quality improvement. It will include anonymous site and surgeon-level peer comparison, a performance summary, and targets. The coprimary outcomes will be analyzed at the site level while recurrence rate will be analyzed at the patient level. The study was funded in October 2020 and began data collection in April 2021. As of January 2023, there were 220 hospitals participating and over 15,000 patient records. Projected data collection end date is June 30, 2023. CONCLUSIONS: This study aims to use a distributed collaborative model to deliver a site-level web-based performance feedback intervention to improve the quality of endoscopic bladder cancer surgery. The study is funded and projects to complete data collection in June 2023. TRIAL REGISTRATION: ClinicalTrials.org NCT05154084; https://clinicaltrials.gov/ct2/show/NCT05154084. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/42254.

Oncological and functional outcomes of organ-preserving cystectomy versus standard radical cystectomy: A systematic review and meta-analysis.

Introduction: Radical cystectomy (RC) is historically considered the gold standard treatment for muscle invasive and high-risk non-muscle invasive bladder cancer. However, this technique leaves the majority of patients of both sexes with poor sexual and urinary function. Organ-sparing cystectomy (OSC) techniques are emerging as an alternative to the standard procedure to preserve these functions, without compromising the oncological outcomes. We present a systematic review and meta-analysis of the published literature. Methods: MEDLINE, Embase and Web of Science were systematically searched for eligible studies on 6 April 2021. Primary outcomes studied were both oncological outcomes, specifically overall recurrence, and functional outcomes, specifically sexual function, and daytime and nighttime continence. Odds ratios (OR) with 95% confidence intervals (95% CI) were calculated. The PROSPERO registration reference number was CRD42018118897. Results: From 13 894 identified abstracts, 19 studies (1886 male and 305 female patients) were eligible for inclusion in this review. These studies included patients who underwent either whole prostate, prostate capsule, seminal vesicle, nerve, uterus, ovary, vagina and fallopian tube sparing techniques. Four studies included only female patients.Thirteen studies reported oncological outcomes, and overall recurrence rate was similar between the two groups (five studies; OR 0.73; 95% CI 0.38-1.40, p = 0.34). Thirteen studies reported on male sexual function. In men, OSC had significantly greater odds of retaining potency (five studies; OR 9.05; 95% CI 5.07-16.16, p < 0.00001). Fourteen studies (13 on males and 1 female) reported urinary outcomes. In men, OSC demonstrated greater odds of daytime (seven studies; OR 2.61; 95% CI 1.74 to 3.92, p < 0.00001) and nighttime continence (seven studies; OR 2.62; 95% CI 1.76 to 3.89, p < 0.00001). Conclusion: In carefully selected patients, OSC allows the potential to provide better sexual and urinary function without compromising oncological outcomes. There remains, however, a paucity of OSC studies in females. Further studies are required to make recommendations based on robust clinical evidence.

Impact of COVID-19 on the management and outcomes of ureteric stones in the UK: a multicentre retrospective study.

OBJECTIVES: To determine if management of ureteric stones in the UK changed during the coronavirus disease 2019 (COVID-19) pandemic and whether this affected patient outcomes. PATIENTS AND METHODS: We conducted a multicentre retrospective study of adults with computed tomography-confirmed ureteric stone disease at 39 UK hospitals during a pre-pandemic period (23/3/2019-22/6/2019) and a period during the pandemic (the 3-month period after the first severe acute respiratory syndrome coronavirus-2 case at individual sites). The primary outcome was success of primary treatment modality, defined as no further treatment required for the index ureteric stone. Our study protocol was published prior to data collection. RESULTS: A total of 3735 patients were included (pre-pandemic 1956 patients; pandemic 1779 patients). Stone size was similar between groups (P > 0.05). During the pandemic, patients had lower hospital admission rates (pre-pandemic 54.0% vs pandemic 46.5%, P < 0.001), shorter mean length of stay (4.1 vs 3.3 days, P = 0.02), and higher rates of use of medical expulsive therapy (17.4% vs 25.4%, P < 0.001). In patients who received interventional management (pre-pandemic 787 vs pandemic 685), rates of extracorporeal shockwave lithotripsy (22.7% vs 34.1%, P < 0.001) and nephrostomy were higher (7.1% vs 10.5%, P = 0.03); and rates of ureteroscopy (57.2% vs 47.5%, P < 0.001), stent insertion (68.4% vs 54.6%, P < 0.001), and general anaesthetic (92.2% vs 76.2%, P < 0.001) were lower. There was no difference in success of primary treatment modality between patient cohorts (pre-pandemic 73.8% vs pandemic 76.1%, P = 0.11), nor when patients were stratified by treatment modality or stone size. Rates of operative complications, 30-day mortality, and re-admission and renal function at 6 months did not differ between the data collection periods. CONCLUSIONS: During the COVID-19 pandemic, there were lower admission rates and fewer invasive procedures performed. Despite this, there were no differences in treatment success or outcomes. Our findings indicate that clinicians can safely adopt management strategies developed during the pandemic to treat more patients conservatively and in the community.

Virtual classroom proficiency-based progression for robotic surgery training (VROBOT): a randomised, prospective, cross-over, effectiveness study.

Robotic surgery training has lacked evidence-based standardisation. We aimed to determine the effectiveness of adjunctive interactive virtual classroom training (VCT) in concordance with the self-directed Fundamentals of Robotic Surgery (FRS) curriculum. The virtual classroom is comprised of a studio with multiple audio-visual inputs to which participants can connect remotely via the BARCO weConnect platform. Eleven novice surgical trainees were randomly allocated to two training groups (A and B). In week 1, both groups completed a robotic skills induction. In week 2, Group A received training with the FRS curriculum and adjunctive VCT; Group B only received access to the FRS curriculum. In week 3, the groups received the alternate intervention. The primary outcome was measured using the validated robotic-objective structured assessment of technical skills (R-OSAT) at the end of week 2 (time-point 1) and 3 (time-point 2). All participants completed the training curriculum and were included in the final analyses. At time-point 1, Group A achieved a statistically significant greater mean proficiency score compared to Group B (44.80 vs 35.33 points, p = 0.006). At time-point 2, there was no significant difference in mean proficiency score in Group A from time-point 1. In contrast, Group B, who received further adjunctive VCT showed significant improvement in mean proficiency by 9.67 points from time-point 1 (95% CI 5.18-14.15, p = 0.003). VCT is an effective, accessible training adjunct to self-directed robotic skills training. With the steep learning curve in robotic surgery training, VCT offers interactive, expert-led learning and can increase training effectiveness and accessibility.

Developing machine learning algorithms for dynamic estimation of progression during active surveillance for prostate cancer.

Active Surveillance (AS) for prostate cancer is a management option that continually monitors early disease and considers intervention if progression occurs. A robust method to incorporate "live" updates of progression risk during follow-up has hitherto been lacking. To address this, we developed a deep learning-based individualised longitudinal survival model using Dynamic-DeepHit-Lite (DDHL) that learns data-driven distribution of time-to-event outcomes. Further refining outputs, we used a reinforcement learning approach (Actor-Critic) for temporal predictive clustering (AC-TPC) to discover groups with similar time-to-event outcomes to support clinical utility. We applied these methods to data from 585 men on AS with longitudinal and comprehensive follow-up (median 4.4 years). Time-dependent C-indices and Brier scores were calculated and compared to Cox regression and landmarking methods. Both Cox and DDHL models including only baseline variables showed comparable C-indices but the DDHL model performance improved with additional follow-up data. With 3 years of data collection and 3 years follow-up the DDHL model had a C-index of 0.79 (±0.11) compared to 0.70 (±0.15) for landmarking Cox and 0.67 (±0.09) for baseline Cox only. Model calibration was good across all models tested. The AC-TPC method further discovered 4 distinct outcome-related temporal clusters with distinct progression trajectories. Those in the lowest risk cluster had negligible progression risk while those in the highest cluster had a 50% risk of progression by 5 years. In summary, we report a novel machine learning approach to inform personalised follow-up during active surveillance which improves predictive power with increasing data input over time.

A BURST-BAUS consensus document for best practice in the conduct of scrotal exploration for suspected testicular torsion: the Finding consensus for orchIdopeXy In Torsion (FIX-IT) study.

OBJECTIVES: To produce a best practice consensus guideline for the conduct of scrotal exploration for suspected testicular torsion using formal consensus methodology. MATERIALS AND METHODS: A panel of 16 expert urologists, representing adult, paediatric, general, and andrological urology used the RAND/UCLA Appropriateness Consensus Methodology to score a 184 statement pre-meeting questionnaire on the conduct of scrotal exploration for suspected testicular torsion. The collated responses were presented at a face-to-face online meeting and each item was rescored anonymously after a group discussion, facilitated by an independent chair with expertise in consensus methodology. Items were scored for agreement and consensus and the items scored with consensus were used to derive a set of best practice guidelines. RESULTS: Statements scored as with consensus increased from Round 1 (122/184, 66.3%) to Round 2 (149/200, 74.5%). Recommendations were generated in ten categories: consent, assessment under anaesthetic, initial incision, intraoperative decision making, fixation, medical photography, closure, operation note, logistics and follow-up after scrotal exploration. Our statements assume that the decision to operate has already been made. Key recommendations in the consent process included the discussion of the possibility of orchidectomy and the possibility of subsequent infection of the affected testis or wound requiring antibiotic therapy. If after the examination under anaesthesia, the index of suspicion of testicular torsion is lower than previously thought, then the surgeon should still proceed to scrotal exploration as planned. A flow chart guiding decision making dependent on intraoperative findings has been designed. If no torsion is present on exploration and the bell clapper deformity is absent, the testis should not be fixed. When fixing a testis using sutures, 3 or 4-point is acceptable and non-absorbable sutures are preferred. CONCLUSIONS: We have produced consensus recommendations to inform best practice in the conduct of scrotal exploration for suspected testicular torsion.

LEARN: A multi-centre, cross-sectional evaluation of Urology teaching in UK medical schools.

OBJECTIVE: To evaluate the status of UK undergraduate urology teaching against the British Association of Urological Surgeons (BAUS) Undergraduate Syllabus for Urology. Secondary objectives included evaluating the type and quantity of teaching provided, the reported performance rate of General Medical Council (GMC)-mandated urological procedures, and the proportion of undergraduates considering urology as a career. MATERIALS AND METHODS: LEARN was a national multicentre cross-sectional study. Year 2 to Year 5 medical students and FY1 doctors were invited to complete a survey between 3rd October and 20th December 2020, retrospectively assessing the urology teaching received to date. Results are reported according to the Checklist for Reporting Results of Internet E-Surveys (CHERRIES). RESULTS: 7,063/8,346 (84.6%) responses from all 39 UK medical schools were included; 1,127/7,063 (16.0%) were from Foundation Year (FY) 1 doctors, who reported that the most frequently taught topics in undergraduate training were on urinary tract infection (96.5%), acute kidney injury (95.9%) and haematuria (94.4%). The most infrequently taught topics were male urinary incontinence (59.4%), male infertility (52.4%) and erectile dysfunction (43.8%). Male and female catheterisation on patients as undergraduates was performed by 92.1% and 73.0% of FY1 doctors respectively, and 16.9% had considered a career in urology. Theory based teaching was mainly prevalent in the early years of medical school, with clinical skills teaching, and clinical placements in the later years of medical school. 20.1% of FY1 doctors reported no undergraduate clinical attachment in urology. CONCLUSION: LEARN is the largest ever evaluation of undergraduate urology teaching. In the UK, teaching seemed satisfactory as evaluated by the BAUS undergraduate syllabus. However, many students report having no clinical attachments in Urology and some newly qualified doctors report never having inserted a catheter, which is a GMC mandated requirement. We recommend a greater emphasis on undergraduate clinical exposure to urology and stricter adherence to GMC mandated procedures.

Bioengineering solutions for ureteric disorders: clinical need, challenges and opportunities.

OBJECTIVES: To summarise the causes of ureteric damage and the current standard of care, discussing the risks and benefits of available therapeutic options. We then focus on the current and future solutions that can be provided by ureteric bioengineering and provide a description of the ideal characteristics of a bioengineered product. METHODS: We performed a literature search in February 2021 in: Google Scholar, Medline, and Web of Science. Three searches were conducted, investigating: (a) the epidemiology of ureteric pathology, (b) the current standard of care, and (c) the state of the art in ureteric bioengineering. RESULTS: The most-common causes of ureteric damage are iatrogenic injury and external trauma. Current approaches to treatment include stent placement or surgical reconstruction. Reconstruction can be done using either urological tissue or segments of the gastrointestinal tract. Limitations include scarring, strictures, and infections. Several bioengineered alternatives have been explored in animal studies, with variations in the choice of scaffold material, cellular seeding populations, and pre-implantation processing. Natural grafts and hybrid material appear to be associated with superior outcomes. Furthermore, seeding of the scaffold material with stem cells or differentiated urothelial cells allows for better function compared to acellular scaffolds. Some studies have attempted to pre-implant the graft in the omentum prior to reconstruction, but this has yet to prove any definitive benefits. CONCLUSION: There is an unmet clinical need for safer and more effective treatment for ureteric injuries. Urological bioengineering is a promising solution in preclinical studies. However, substantial scientific, logistic, and economic challenges must be addressed to harness its transformative potential in improving outcomes.

Repurposing of drugs for COVID-19: a systematic review and meta-analysis.

INTRODUCTION: The aim of this systematic review was to evaluate the data currently available regarding the repurposing of different drugs for COVID-19 treatment. Participants with suspected or diagnosed COVID-19 were included in this study. The interventions that have been considered were repurposed drugs and comparators that included standard of care treatment or placebo. EVIDENCE ACQUISITION: We searched Ovid-MEDLINE, EMBASE, Cochrane library, clinical trial registration site in the UK(NIHR), Europe (clinicaltrialsregister.eu), US (ClinicalTrials.gov) and internationally (isrctn.com), and reviewed the reference lists of articles for eligible articles published up to April 22, 2020. All studies in English that evaluated the efficacy of the listed drugs were included. Cochrane RoB 2.0 and ROBINS-I tool were used to assess study quality. This systematic review adheres to the PRISMA guidelines. The protocol is available at PROSPERO (CRD42020180915). EVIDENCE SYNTHESIS: From 708 identified studies or clinical trials, 16 studies and 16 case reports met our eligibility criteria. Of these, 6 were randomized controlled trials (763 patients), 7 cohort studies (321 patients) and 3 case series (191 patients). Chloroquine (CQ) had a 100% discharge rate compared to 50% with lopinavir-ritonavir at day 14, however a trial has recommended against a high dosage due to cardiotoxic events. Hydroxychloroquine (HCQ) has shown no significant improvement in negative seroconversion rate which is also seen in our meta-analysis (P=0.68). Adverse events with HCQ have a significant difference compared to the control group (P=0.001). Lopinavir-ritonavir has shown no improvement in time to clinical improvement which is seen in our meta-analyses (P=0.1). Remdesivir has shown no significant improvement in time to clinical improvement but this trial had insufficient power. CONCLUSIONS: Due to the paucity in evidence, it is difficult to establish the efficacy of these drugs in the treatment of COVID-19 as currently there is no significant clinical effectiveness of the repurposed drugs. Further large clinical trials are required to achieve more reliable findings. A risk-benefit analysis is required on an individual basis to weigh out the potential improvement in clinical outcome and viral load reduction compared to the risks of the adverse events.

Development and External Validation of the STRATified CANcer Surveillance (STRATCANS) Multivariable Model for Predicting Progression in Men with Newly Diagnosed Prostate Cancer Starting Active Surveillance.

For men with newly diagnosed prostate cancer, we aimed to develop and validate a model to predict the risk of progression on active surveillance (AS), which could inform more personalised AS strategies. In total, 883 men from 3 European centres were used for model development and internal validation, and 151 men from a fourth European centre were used for external validation. Men with Cambridge Prognostic Group (CPG) 1-2 disease at diagnosis were eligible. The endpoint was progression to the composite endpoint of CPG3 disease or worse (≥CPG3). Model performance at 4 years was evaluated through discrimination (C-index), calibration plots, and decision curve analysis. The final multivariable model incorporated prostate-specific antigen (PSA), Grade Group, magnetic resonance imaging (MRI) score (Prostate Imaging Reporting & Data System (PI-RADS) or Likert), and prostate volume. Calibration and discrimination were good in both internal validation (C-index 0.742, 95% CI 0.694-0.793) and external validation (C-index 0.845, 95% CI 0.712-0.958). In decision curve analysis, the model offered net benefit compared to a 'follow-all' strategy at risk thresholds of ≥0.08 and ≥0.04 in development and external validation, respectively. In conclusion, our model demonstrated good accuracy and clinical utility in predicting the progression on AS at 4 years post-diagnosis. Men with lower risk predictions could subsequently be offered less-intense surveillance. Further external validation in larger cohorts is now required.