Development of a novel machine learning-based predictive risk calculator for radical cystectomy.

Positive Surgical Margins in Soft Tissue Following Radical Cystectomy for Bladder Cancer and Cancer Specific Survival

To construct and validate the best predictive model for 28-day death risk in patients with septic shock based on different supervised machine learning algorithms. The patients with septic shock meeting the Sepsis-3 criteria were selected from Medical Information Mart for Intensive Care-IV v2.0 (MIMIC-IV v2.0). According to the principle of random allocation, 70% of these patients were used as the training set, and 30% as the validation set. Relevant predictive variables were extracted from three aspects: demographic characteristics and basic vital signs, serum indicators within 24 hours of intensive care unit (ICU) admission and complications possibly affecting indicators, functional scoring and advanced life support. The predictive efficacy of models constructed using five mainstream machine learning algorithms including decision tree classification and regression tree (CART), random forest (RF), support vector machine (SVM), linear regression (LR), and super learner [SL; combined CART, RF and extreme gradient boosting (XGBoost)] for 28-day death in patients with septic shock was compared, and the best algorithm model was selected. The optimal predictive variables were determined by intersecting the results from LASSO regression, RF, and XGBoost algorithms, and a predictive model was constructed. The predictive efficacy of the model was validated by drawing receiver operator characteristic curve (ROC curve), the accuracy of the model was assessed using calibration curves, and the practicality of the model was verified through decision curve analysis (DCA). A total of 3 295 patients with septic shock were included, with 2 164 surviving and 1 131 dying within 28 days, resulting in a mortality of 34.32%. Of these, 2 307 were in the training set (with 792 deaths within 28 days, a mortality of 34.33%), and 988 in the validation set (with 339 deaths within 28 days, a mortality of 34.31%). Five machine learning models were established based on the training set data. After including variables at three aspects, the area under the ROC curve (AUC) of RF, SVM, and LR machine learning algorithm models for predicting 28-day death in septic shock patients in the validation set was 0.823 [95% confidence interval (95%CI) was 0.795-0.849], 0.823 (95%CI was 0.796-0.849), and 0.810 (95%CI was 0.782-0.838), respectively, which were higher than that of the CART algorithm model (AUC = 0.750, 95%CI was 0.717-0.782) and SL algorithm model (AUC = 0.756, 95%CI was 0.724-0.789). Thus above three algorithm models were determined to be the best algorithm models. After integrating variables from three aspects, 16 optimal predictive variables were identified through intersection by LASSO regression, RF, and XGBoost algorithms, including the highest pH value, the highest albumin (Alb), the highest body temperature, the lowest lactic acid (Lac), the highest Lac, the highest serum creatinine (SCr), the highest Ca2+, the lowest hemoglobin (Hb), the lowest white blood cell count (WBC), age, simplified acute physiology score III (SAPS III), the highest WBC, acute physiology score III (APS III), the lowest Na+, body mass index (BMI), and the shortest activated partial thromboplastin time (APTT) within 24 hours of ICU admission. ROC curve analysis showed that the Logistic regression model constructed with above 16 optimal predictive variables was the best predictive model, with an AUC of 0.806 (95%CI was 0.778-0.835) in the validation set. The calibration curve and DCA curve showed that this model had high accuracy and the highest net benefit could reach 0.3, which was significantly outperforming traditional models based on single functional score [APS III score, SAPS III score, and sequential organ failure assessment (SOFA) score] with AUC (95%CI) of 0.746 (0.715-0.778), 0.765 (0.734-0.796), and 0.625 (0.589-0.661), respectively. The Logistic regression model, constructed using 16 optimal predictive variables including pH value, Alb, body temperature, Lac, SCr, Ca2+, Hb, WBC, SAPS III score, APS III score, Na+, BMI, and APTT, is identified as the best predictive model for the 28-day death risk in patients with septic shock. Its performance is stable, with high discriminative ability and accuracy.

ObjectiveThe presence of pancreaticobiliary maljunction (PBM) in pediatric patients with congenital choledochal malformation significantly impacts clinical management and surgical decision-making. Current preoperative evaluation of PBM coexistence remains challenging in children, while intraoperative cholangiography does not consistently provide diagnostic-quality imaging. This study aims to develop machine learning-based algorithm models for detecting pancreaticobiliary maljunction (PBM) in children with congenital choledochal malformation.MethodsWe conducted a retrospective study utilizing data from patients with congenital choledochal malformation treated at our center between January 2019 and January 2024. Demographic characteristics, clinical features, and preoperative laboratory parameters were processed through rigorous data curation and feature engineering pipelines. Cases were allocated via random sampling into training (80%) and hold-out test (20%) cohorts, maintaining strict separation between training and test cohorts. Seven machine learning algorithms - Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), Light Gradient Boosting Machine (LightGBM), and K-Nearest Neighbors (KNN) - were implemented with five-fold cross-validation. An ensemble voting classifier was specifically constructed using these models. Model performance was quantified through comprehensive metrics including area under the ROC curve (AUC), sensitivity, specificity, positive/negative predictive values, accuracy, precision, recall, and F1-score. This study employed the nonparametric bootstrap method to estimate the confidence interval for the area under the receiver operating characteristic curve (AUC). SHapley Additive exPlanations (SHAP) was employed for model interpretability, with feature importance rankings determined by absolute SHAP value magnitudes.ResultsIn a cohort of 803 pediatric patients with congenital choledochal malformation, 628 (78.2%) demonstrated concurrent pancreaticobiliary maljunction. We developed a detection model incorporating 43 clinical features, with Random Forest showing optimal performance. An ensemble voting classifier integrating seven machine learning algorithms achieved enhanced discriminative performance (AUC: 0.87 (0.81, 0.92); Recall: 0.91 (0.85, 0.95); F1-score: 0.91 (0.87, 0.94)). Key features contributing to PBM detection included: laboratory markers and clinical parameters.ConclusionBy integrating preoperative clinical symptoms and laboratory parameters, machine learning algorithms demonstrated significant detection capability in identifying PBM among pediatric congenital choledochal malformation patients, with the RF model achieving superior performance metrics among all base models. The developed ensemble voting classifier provides valuable preoperative guidance for surgical planning and clinical management, enabling detection of PBM comorbidity before surgery in congenital choledochal malformation cases.

Commentary on “Surveillance guidelines based on recurrence patterns after radical cystectomy for bladder cancer: the Canadian Bladder Cancer Network experience.” Yafi FA, Aprikian AG, Fradet Y, Chin JL, Izawa J, Rendon R, Estey E, Fairey A, Cagiannos I, Lacombe L, Lattouf JB, Bell D, Saad F, Drachenberg D, Kassouf W. Department of Surgery (Urology), McGill University, Quebec, Canada: BJU Int

Urinary tract infections (UTIs) are a major cause of emergency hospital admissions, but it remains challenging to diagnose them reliably. Application of machine learning (ML) to routine patient data could support clinical decision-making. We developed a ML model predicting bacteriuria in the ED and evaluated its performance in key patient groups to determine scope for its future use to improve UTI diagnosis and thus guide antibiotic prescribing decisions in clinical practice. We used retrospective electronic health records from a large UK hospital (2011-2019). Non-pregnant adults who attended the ED and had a urine sample cultured were eligible for inclusion. The primary outcome was predominant bacterial growth ≥104 cfu/mL in urine. Predictors included demography, medical history, ED diagnoses, blood tests, and urine flow cytometry. Linear and tree-based models were trained via repeated cross-validation, re-calibrated, and validated on data from 2018/19. Changes in performance were investigated by age, sex, ethnicity, and suspected ED diagnosis, and compared to clinical judgement. Among 12,680 included samples, 4,677 (36.9%) showed bacterial growth. Relying primarily on flow cytometry parameters, our best model achieved an area under the ROC curve (AUC) of 0.813 (95% CI 0.792-0.834) in the test data, and achieved both higher sensitivity and specificity compared to proxies of clinician's judgement. Performance remained stable for white and non-white patients but was lower during a period of laboratory procedure change in 2015, in patients ≥65 years (AUC 0.783, 95% CI 0.752-0.815), and in men (AUC 0.758, 95% CI 0.717-0.798). Performance was also slightly reduced in patients with recorded suspicion of UTI (AUC 0.797, 95% CI 0.765-0.828). Our results suggest scope for use of ML to inform antibiotic prescribing decisions by improving diagnosis of suspected UTI in the ED, but performance varied with patient characteristics. Clinical utility of predictive models for UTI is therefore likely to differ for important patient subgroups including women <65 years, women ≥65 years, and men. Tailored models and decision thresholds may be required that account for differences in achievable performance, background incidence, and risks of infectious complications in these groups.

Objective: To evaluate health-related quality of life (HR-QoL) outcomes in elderly patients with different type of urinary diversion (UD), ileal conduit (IC) and ileal orthotopic neobladder (IONB), after radical cystectomy (RC) for bladder cancer, by using validated self-reported cancer-specific instruments. Patients and Methods: We retrospectively reviewed 77 patients who received an IC or an IONB after RC. HR-QoL was assessed with specific and validated disease questionnaires, administered at last follow-up. Result: At univariate analysis, at a mean follow-up of 60.91 ± 5.63 months, IONB results were favourable with regard to the following HR-QoL aspects: nausea and vomiting (p = 0.045), pain (p = 0.049), appetite loss (p = 0.03), constipation (p = 0.000), financial impact (p = 0.012) and cognitive functioning (p = 0.000). This last functional aspect was significantly worse in female patients (p = 0.029). Emotional functioning was significantly better in patients without long-term complications (p = 0.016). At multivariate analysis, male gender and IONB were independent predictors of better cognitive functioning, while long-term complications negatively affected emotional functioning. Conclusions: Obtained results suggest that an IONB can also be suitable for elderly patients compared with an IC with few and selected advantages in favour of the former UD. Preoperative patient’s selection, counselling, education and active participation in the decision-making process lead to a more suitable choice of treatment.

Survival of Patients with Chronic Kidney Disease Treated with Radical Cystectomy and Risk Factors of Glomerular Filtration Rate Loss Following Radical Cystectomy: Two Systematic Reviews and Meta-analyses of Interplay Between Radical Cystectomy and Renal Function

Background: Carotid intima-media thickness (IMT) can identify subjects at increased atherosclerotic cardiovascular disease (ASCVD) risk and can guide future treatment. However, U.S. Preventive Services Task Force has reaffirmed its previous recommendation against screening for asymptomatic carotid artery stenosis in the general adult population. Hypothesis: The aim of the study was to assess the relationship between 10-year cardiovascular risk and carotid IMT in medical check-up participants. The measurement of carotid IMT might be a valuable tool for educating and reducing the CVD risk factors in individual subject. Methods: Adults aged 50 to 69 years were eligible for the study if they did not have a history of ASCVD or stroke. The ASCVD risk estimator (http://tools.acc.org/ASCVD-Risk-Estimator) was used for the calculation of the 10-year CVD risk. For the study, the maximum IMT of both carotid arteries were measured and the mean value of them was used for analysis. Results: A total of 265 patients were enrolled in this study. The mean age was 58 years, and 28% were women. The mean IMT was significantly correlated with the 10-year CVD risk in all participants (r=0.180, P=0.003). Among men, the mean IMT was 0.81±0.13 mm and 64 (33.5%) participants had ≥10% 10-year CVD risk. Significant difference was observed in the mean IMT between ≥10% 10-year CVD risk group and &lt;10% 10-year CVD risk group (P=0.025). With women, the mean IMT was 0.78±0.10 mm and 6 (8.1%) participants had ≥10% 10-year CVD risk. There was no significant difference in the mean IMT between the groups (p=0.291). In all participants, the cutoff value of the carotid IMT for ≥10% 10-year CVD risk was 0.87 mm (sensitivity, 37.1%; specificity, 87.1%) and area under the ROC curve (AUC) was 0.618 (95% CI, 0.56-0.58, P=0.003). In men, the cutoff value of the carotid IMT for ≥10% 10-year CVD risk was 0.86 mm (sensitivity, 37.5%; specificity, 81.1%). The AUC was 0.606 (95% CI, 0.53-0.68, P=0.015). Conclusions: Though routine sonographic screening for carotid artery has little supporting evidence, our study suggested that there may be an opportunity for reducing the rate of ASCVD and stroke through the tailored sonographic examination in high risk subjects.

BackgroundMultivariable risk calculators (RCs) predicting prostate cancer (PCa) aim to reduce unnecessary workup (e.g., MRI and biopsy) by selectively identifying those men at risk for PCa or clinically significant PCa (csPCa) (Gleason ≥7). The lack of an adequate comparison makes choosing between RCs difficult for patients, clinicians and guideline developers. We aim to perform a head-to-head comparison of seven well known RCs predicting biopsy outcome.MethodsOur study comprised 7,119 men from ten independent contemporary cohorts in Europe and Australia, who underwent prostate biopsy between 2007 and 2015. We evaluated the performance of the ERSPC RPCRC, Finne, Chun, ProstataClass, Karakiewicz, Sunnybrook, and PCPT 2.0 (HG) RCs in predicting the presence of any PCa and csPCa. Performance was assessed by discrimination, calibration and net benefit analyses.ResultsA total of 3,458 (48%) PCa were detected; 1,784 (25%) men had csPCa. No particular RC stood out predicting any PCa: pooled area under the ROC-curve (AUC) ranged between 0.64 and 0.72. The ERSPC RPCRC had the highest pooled AUC 0.77 (95% CI: 0.73–0.80) when predicting csPCa. Decision curve analysis (DCA) showed limited net benefit in the detection of csPCa, but that can be improved by a simple calibration step. The main limitation is the retrospective design of the study.ConclusionsNo particular RC stands out when predicting biopsy outcome on the presence of any PCa. The ERSPC RPCRC is superior in identifying those men at risk for csPCa. Net benefit analyses show that a multivariate approach before further workup is advisable.

Objective: To evaluate perioperative outcomes and early survival in a series of octogenarians who underwent radical cystectomy (RC) and urinary diversion for bladder cancer. Patients and Methods: We retrospectively evaluated the clinical records of 44 patients aged ≥80 years who underwent open RC and urinary diversion at 2 high-volume centers between July 2013 and December 2015. Estimated blood loss (EBL), transfusion rate, and length of hospital stay (LOS) were evaluated. Ninety-day postoperative complications were stratified according to the type of urinary diversion. Univariable analysis was performed to identify predictors of overall and major complications. Overall survival (OS) was estimated using the Kaplan-Meier method. Results: Median age was 83 years (interquartile range [IQR] 81-85). Age-adjusted Charlson score was ≥4 in 37 (84%) patients, and American Society of Anesthesiologists score was ≥3 in 34 (77%) patients. Ileal conduit (IC) was performed in 21/44 (48%) cases, cutaneous ureterostomy (CU) in 20/44 (45%), and no urinary diversion was required for 3 (7%) dialytic patients. Median EBL was 700 mL (IQR 500-1,000) and 23 (52%) patients required blood transfusion. Median LOS was 13 days (IQR 10-18). Overall complications were recorded in 29 (66%) patients, with major complications observed in 12 (27%), with death occurring in 1. No differences in complications were observed between IC and CU. The 2-year OS estimate was 62.5%. Conclusions: Open RC in octogenarians has an acceptable rate of major complications and mortality. IC should be considered a good urinary diversion in these patients.

There is paucity of studies on the predictors of bladder cancer (BC) management costs. We aimed to determine predictors of costs associated with radical cystectomy (RC) for BC. We conducted a retrospective analysis in a cohort of 2,759 patients who underwent RC for BC between 2000 and 2009. We analyzed predictors of pre-surgery, RC, post-surgery, and total costs. The following variables were considered as potential predictors: age, gender, hospital/surgeon case load, academic hospital, and geo-administrative region. Multivariate linear regression was used to determine predictors. Predictors of pre-surgery costs were: age (β = 808.64, P < 0.0001) and having surgery in an academic hospital (β = 511.42, P = 0.003). Increased RC costs were associated with age (β = 196.73, P = 0.0006), hospital/surgeon annual load (β = 484.45 and β = 254.21, P < 0.0001, respectively). Having surgery in academic hospitals and geographic region were significant predictors of low RC costs (β = -1085.82 and β = -449.31, P < 0.0001, respectively). Increasing age and the presence of post-operative complications were predictors of high post-operative costs (β = 623.48, β = 5781.44, P = 0.01, respectively), while hospital load was associated with low post-surgery costs (β = -949.79, P < 0.0001). Patients' age and surgery performed by high-volume health providers were predictive factors of high RC costs. Low RC costs were associated with surgeries performed in academic hospitals.

Outcomes for a large series of radical cystectomies for bladder cancer

Adverse Pathology After Neoadjuvant Chemotherapy and Radical Cystectomy: The Role of Adjuvant Chemotherapy.

This research evaluates 20 advanced convolutional neural network (CNN) architectures for classifying mushroom diseases in Agaricus bisporus, utilizing a custom dataset of 3195 images (2464 infected and 731 healthy mushrooms) captured under uniform white-light conditions. The consistent illumination in the dataset enhances the robustness and practical usability of the assessed models. Using a weighted scoring system that incorporates precision, recall, F1-score, area under the ROC curve (AUC), and average precision (AP), ResNet-50 achieved the highest overall score of 99.70%, demonstrating outstanding performance across all disease categories. DenseNet-201 and DarkNet-53 followed closely, confirming their reliability in classification tasks with high recall and precision values. Confusion matrices and ROC curves further validated the classification capabilities of the models. These findings underscore the potential of CNN-based approaches for accurate and efficient early detection of mushroom diseases, contributing to more sustainable and data-driven agricultural practices.

The aim of this study was to examine preoperative patients' characteristics associated with the urinary diversion (UD) type (continent vs. incontinent) after radical cystectomy (RC) and UD-associated postoperative complications. In 2011, 679 bladder cancer patients underwent RC at 18 European tertiary care centers. Data were prospectively collected within the 'PROspective MulticEnTer RadIcal Cystectomy Series 2011' (PROMETRICS 2011). Logistic regression models assessed the impact of preoperative characteristics on UD type and evaluated diversion-related complication rates. Of 570 eligible patients, 28.8, 2.6, 59.3, and 9.3% received orthotopic neobladders, continent cutaneous pouches, ileal conduits, and ureterocutaneostomies, respectively. In multivariable analyses, female sex (odds ratio [OR] 3.9; p = 0.002), American Society of Anesthesiologists score ≥3 (OR 2.3; p = 0.02), an age-adjusted Charlson Comorbidity Index ≥3 (OR 4.1; p < 0.001), and a positive biopsy of the prostatic urethra in the last transurethral resection of the bladder prior to RC (OR 4.9; p = 0.03) were independently associated with incontinent UD. There were no significant differences in 30- and/or 90-day complication rates between the UD types. Perioperative transfusion rates and 90-day mortality were significantly associated with incontinent UD (p < 0.001, respectively). Limitations included the small sample size and a certain level of heterogeneity in the application of clinical pathways between the different participating centers. Within this prospective contemporary cohort of European RC patients treated at tertiary care centers, the majority of patients received an incontinent UD. Female sex and pre-existing comorbidities were associated with receiving an incontinent UD. The risk of overall complications did not vary according to UD type.