Prediction of Incontinence after Robot-Assisted Radical Prostatectomy: Development and Validation of a 24-Month Incontinence Nomogram

Development of Machine Learning Algorithm to Predict the Risk of Incontinence After Robot-Assisted Radical Prostatectomy

Introduction: Predicting postoperative incontinence beforehand is crucial for intensified and personalized rehabilitation after robot-assisted radical prostatectomy. Although nomograms exist, their retrospective limitations highlight artificial intelligence (AI)'s potential. This study seeks to develop a machine learning algorithm using robot-assisted radical prostatectomy (RARP) data to predict postoperative incontinence, advancing personalized care. Materials and Methods: In this propsective observational study, patients with localized prostate cancer undergoing RARP between April 2022 and January 2023 were assessed. Preoperative variables included age, body mass index, prostate-specific antigen (PSA) levels, digital rectal examination (DRE) results, Gleason score, International Society of Urological Pathology grade, and continence and potency questionnaires responses. Intraoperative factors, postoperative outcomes, and pathological variables were recorded. Urinary continence was evaluated using the Expanded Prostate cancer Index Composite questionnaire, and machine learning models (XGBoost, Random Forest, Logistic Regression) were explored to predict incontinence risk. The chosen model's SHAP values elucidated variables impacting predictions. Results: A dataset of 227 patients undergoing RARP was considered for the study. Post-RARP complications were predominantly low grade, and urinary continence rates were 74.2%, 80.7%, and 91.4% at 7, 13, and 90 days after catheter removal, respectively. Employing machine learning, XGBoost proved the most effective in predicting postoperative incontinence risk. Significant variables identified by the algorithm included nerve-sparing approach, age, DRE, and total PSA. The model's threshold of 0.67 categorized patients into high or low risk, offering personalized predictions about the risk of incontinence after surgery. Conclusions: Predicting postoperative incontinence is crucial for tailoring rehabilitation after RARP. Machine learning algorithm, particularly XGBoost, can effectively identify those variables more heavily, impacting the outcome of postoperative continence, allowing to build an AI-driven model addressing the current challenges in post-RARP rehabilitation.

Prediction models for urinary incontinence after robotic-assisted laparoscopic radical prostatectomy: a systematic review

Even though robotic-assisted laparoscopic radical prostatectomy (RARP) is superior to open surgery in reducing postoperative complications, 6-20% of patients still experience urinary incontinence (UI) after surgery. Therefore, many researchers have established predictive models for UI occurrence after RARP, but the predictive performance of these models is inconsistent. This study aims to systematically review and critically evaluate the published prediction models of UI risk for patients after RARP. We conducted a comprehensive literature search in the databases of PubMed, Cochrane Library, Web of Science, and Embase. Literature published from inception to March 20, 2024, which reported the development and/or validation of clinical prediction models for the occurrence of UI after RARP. We identified seven studies with eight models that met our inclusion criteria. Most of the studies used logistic regression models to predict the occurrence of UI after RARP. The most common predictors included age, body mass index, and nerve sparing procedure. The model performance ranged from poor to good, with the area under the receiver operating characteristic curves ranging from 0.64 to 0.98 in studies. All the studies have a high risk of bias. Despite their potential for predicting UI after RARP, clinical prediction models are restricted by their limited accuracy and high risk of bias. In the future, the study design should be improved, the potential predictors should be considered from larger and representative samples comprehensively, and high-quality risk prediction models should be established. And externally validating models performance to enhance their clinical accuracy and applicability.

Systematic review on urinary continence rates after robot-assisted laparoscopic radical prostatectomy

OBJECTIVE

The objective was to investigate the current evidence and discern urinary continence rates post robot-assisted laparoscopic radical prostatectomy (RALP).

METHODS

A systematic review of the literature was carried out, searching the Embase, Scopus and PubMed databases between 1 January 2000 and 1 May 2020. The search terms "Robotic prostatectomy AND continence" were employed. Articles were selected in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Statistical analysis was performed using the programme R; cumulative analysis of percentage of men continent was calculated.

RESULTS

A total of 3101 abstracts and 50 full text articles were assessed, with 22 publications included (n = 2813 patients). There were 21 randomised controlled trials and one partly randomised controlled trial with four publications comparing RALP to other prostate cancer treatments. Thirteen studies explored different RALP techniques, and five studies examined vesicourethral anastomosis (VUA). There were statistically significant improvements in early urinary continence rates in three studies analysing reconstructive techniques (83% vs 60%, p = 0.04; 26.5% vs 15.4%, p = 0.016; 77% vs 44.1%, p ≤ 0.001). Long-term continence rates were not significantly improved across all studies assessing reconstruction. One study comparing RALP vs laparoscopic radical prostatectomy (LRP) demonstrated a statistically significant improvement in continence at 3 months (80% vs 73.3%, p < 0.001); 6 months (83.3% vs 81.4%, p < 0.001); 12 months (95% vs 83.3%, p < 0.001) and 24 months (96.7% vs 85%, p < 0.001). Early continence was less favourable for RALP when compared to brachytherapy (BT) patients at 3 months (86% vs 98.7%, p < 0.05) and 6 months (90.5% vs 98.7%, p < 0.05).

CONCLUSION

Early continence rates were improved across numerous techniques in RALP. These results were not translated into significantly improved long-term outcomes. Continence rates following RALP were favourable compared to LRP, similar to ORP and less favourable compared to BT. Our findings suggest that post-RALP continence can be further improved with alterations in robotic technique.

The association of smoking with urinary and sexual function recovery following radical prostatectomy for localized prostate cancer: a systematic review and meta-analysis

BACKGROUND

Urinary and sexual dysfunction after radical prostatectomy remains a major cause of morbidity, despite widespread availability of pharmacological and rehabilitative treatments. Smoking is a modifiable risk factor known to correlate with erectile and urinary dysfunction and we hypothesise that smoking cessation may improve post-prostatectomy urinary and sexual function recovery. Our objective is to systematically evaluate literature describing the association of smoking status with urinary and sexual function in men following radical prostatectomy.

METHODS

In total, 310 unique records were identified through a systematic search of the MEDLINE, EMBASE, Scopus, Web of Science, CINAHL and CENTRAL databases up to February 2023. Nine studies reported smoking status and post radical prostatectomy urinary and sexual function outcomes in men with localized prostate cancer. Risk of bias was assessed and meta-analysis included six studies.

RESULTS

Smokers had inferior erectile function after prostatectomy compared to non-smokers (OR 0.73, [95% CI 0.56-0.95]) during follow-up, while urinary incontinence was not statistically different between groups (OR 1.20, [95% CI 0.75-1.91]). Smoking cessation improved the EPIC-26 sexual domain score with 6.6 points on average [p = 0.03] to a clinically significant maximum of 12.5 points at 18-24 months.

CONCLUSIONS

Smoking is associated with impaired sexual function recovery after radical prostatectomy and quitting may improve sexual function >18 months. Current evidence shows no such association for urinary outcomes. Further studies are needed to corroborate findings.

Correlation of urinary continence recovery with various factors after Robot assisted radical prostatectomy

BACKGROUND

In addition to ensuring cancer control, prevention of incontinence which significantly impact patients' quality of life, is also an important issue in robot-assisted radical prostatectomy (RARP) operations. In this study, we aimed to find the correlation of urinary continence recovery with various factors after Robot assisted radical prostatectomy.

METHODS

This study included 162 patients treated with RARP with perioperative data and at least 1 year of follow-up. Also, the preoperative, intraoperative, and postoperative parameters of the patients were analyzed. The continence recovery rate in our study was assessed at 6th week, 3rd month, 6th month, 9th month, and 12th month, post-surgery. Logistic regression analysis evaluated the association between the predictive factors and urinary continence recovery in the early and late stages.

RESULTS

The majority of patients with prostate cancer present in sixth decade of life. The majority of our patients (56.7%) were categorized as high risk using D'Amico classification. The continence rate in our study at 6th week, 3rd month, 6th month, 9th month, and 12th month were 40.1%, 72.2%, 85.2%, 89.5%, and 91.4%, respectively. No improvement in continence status was observed after 1 year in our study. There was significant correlation of age with continence status at 6th week, 3rd month, and 6th month. The young age is associated with early recovery of continence. At 3 and 9 months, the non-diabetics cases achieved significantly higher continence rates than diabetics (p < 0.05) which shows that diabetes causes delay in attainment of continence.

CONCLUSION

The young age may be associated with early recovery of continence, but further validation requires large number of cases. We attributed good continence recovery rate to meticulous dissection and preservation of good urethral length.

Validation of Claims Data for Absorbing Pads as a Measure for Urinary Incontinence after Radical Prostatectomy, a National Cross-Sectional Analysis

The use of healthcare insurance claims data for urinary incontinence (UI) pads has the potential to serve as an objective measure for assessing post-radical prostatectomy UI rates, but its validity for this purpose has not been established. The aim of this study is to correlate claims data with Patient Reported Outcome Measures (PROMs) for UI pad use. Patients who underwent RP in the Netherlands between September 2019 and February 2020 were included. Incontinence was defined as the daily use of ≥1 pad(s). Claims data for UI pads at 12-15 months after RP were extracted from a nationwide healthcare insurance database in the Netherlands. Participating hospitals provided PROMS data. In total, 1624 patients underwent RP. Corresponding data of 845 patients was provided by nine participating hospitals, of which 416 patients were matched with complete PROMs data. Claims data and PROMs showed 31% and 45% post-RP UI (≥1 pads). UI according to claims data compared with PROMs had a sensitivity of 62%, specificity of 96%, PPV of 92%, NPV of 75% and accuracy of 81%. The agreement between both methods was moderate (κ = 0.60). Claims data for pads moderately align with PROMs in assessing post-prostatectomy urinary incontinence and could be considered as a conservative quality indicator.

Radical Prostatectomy and Anatomical Controversies: The Urethral Sphincter and the Elusive Continence Mechanisms

Prostate cancer incidence is rising [...].

Patient's Desire and Real Availability Concerning Supportive Measures Accompanying Radical Prostatectomy: Differences between Certified Prostate Cancer Centers and Non-Certified Centers Based on Patient-Reported Outcomes within the Cross-Sectional Study Improve

Certification as a prostate cancer center requires the offer of several supportive measures to patients undergoing radical prostatectomy (RP). However, it remains unclear how patients estimate the relevance of these measures and whether the availability of these measures differs between certified prostate cancer centers (CERTs) and non-certified centers (NCERTs). In 20 German urologic centers, a survey comprising questions on the relevance of 15 supportive measures was sent to 1000 patients at a median of 15 months after RP. Additionally, patients were asked to rate the availability of these measures using a four-item Likert scale. The aim of this study was to compare these ratings between CERTs and NCERTs. The response rate was 75.0%. In total, 480 patients underwent surgery in CERTs, and 270 in NCERTs. Patients rated 6/15 supportive measures as very relevant: preoperative medical counselling concerning treatment options, a preoperative briefing answering last questions, preoperative pelvic floor exercises (PFEs), postoperative PFEs, postoperative social support, and postoperative rehabilitation addressing physical fitness recovery. These ratings showed no significant difference between CERTs and NCERTs (p = 0.133-0.676). In addition, 4/9 of the remaining criteria were rated as more detailed by patients in CERTs. IMPROVE represents the first study worldwide to evaluate a patient-reported assessment of the supportive measures accompanying RP. Pertinent offers vary marginally between CERTs and NCERTs.

Management of Urinary Incontinence Following Radical Prostatectomy: Challenges and Solutions

Urinary incontinence is a common and debilitating problem in patients undergoing radical prostatectomy. Current methods developed to treat urinary incontinence include conservative treatments, such as lifestyle education, pelvic muscle floor training, pharmacotherapy, and surgical treatments, such as bulking agents use, artificial urinary sphincter implants, retrourethral transobturator slings, and adjustable male sling system. Pelvic floor muscle exercise is the most common management to improve the strength of striated muscles of the pelvic floor to try to recover the sphincter weakness. Antimuscarinic drugs, phosphodiesterase inhibitors, duloxetine, and a-adrenergic drugs have been proposed as medical treatments for urinary incontinence after radical prostatectomy. Development of new surgical techniques, new surgical tools and materials, such as male slings, has provided an improvement of outcomes after UI surgery. Such improvement is still ongoing, and the uptake of new devices might lead to even better outcomes after UI surgery.

The development and assessment of a predicting nomogram for the recovery of immediate urinary continence following laparoscopic radical prostatectomy

Purpose

This study aimed to develop a nomogram to predict the recovery of immediate urinary continence in laparoscopic radical prostatectomy (LRP) patients.

Methods

A prediction model was developed based on a dataset of 154 LRP patients. Immediate urinary continence was defined as free from using pads within 7 days after the removal of the urinary catheter. The least absolute shrinkage and selection operator regression (LASSO) model was applied to screen the features. Multivariate logistic regression analysis was used to establish prediction model integrating the features selected from the LASSO regression analysis. Receiver operating curve (ROC), calibration and decision curve analysis (DCA) were used to assess the model's discrimination, calibration and clinical utility.

Results

The identified features of the prediction model included age, body mass index (BMI) and three pelvic anatomic parameters measured by MRI: membranous urethral length (MUL), intravesical prostatic protrusion length (IPPL) and puborectalis muscle width (PMW). The nomogram showed good discrimination with an are under the curve(AUC) of 0.914 (95% CI, 0.865-0.959, p < 0.001). Moreover, good calibration was showed in the model. Lastly, DCA showed that the nomogram was clinically useful.

Conclusion

The developed novel nomogram that can predict the possibility for post-prostatectomy patients to recover immediate urinary continence could be used as a counseling tool to explain urinary incontinence to patients after LRP.

A comparison of machine learning models for predicting urinary incontinence in men with localized prostate cancer

Introduction

Urinary incontinence (UI) is a common side effect of prostate cancer treatment, but in clinical practice, it is difficult to predict. Machine learning (ML) models have shown promising results in predicting outcomes, yet the lack of transparency in complex models known as "black-box" has made clinicians wary of relying on them in sensitive decisions. Therefore, finding a balance between accuracy and explainability is crucial for the implementation of ML models. The aim of this study was to employ three different ML classifiers to predict the probability of experiencing UI in men with localized prostate cancer 1-year and 2-year after treatment and compare their accuracy and explainability.

Methods

We used the ProZIB dataset from the Netherlands Comprehensive Cancer Organization (Integraal Kankercentrum Nederland; IKNL) which contained clinical, demographic, and PROM data of 964 patients from 65 Dutch hospitals. Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM) algorithms were applied to predict (in)continence after prostate cancer treatment.

Results

All models have been externally validated according to the TRIPOD Type 3 guidelines and their performance was assessed by accuracy, sensitivity, specificity, and AUC. While all three models demonstrated similar performance, LR showed slightly better accuracy than RF and SVM in predicting the risk of UI one year after prostate cancer treatment, achieving an accuracy of 0.75, a sensitivity of 0.82, and an AUC of 0.79. All models for the 2-year outcome performed poorly in the validation set, with an accuracy of 0.6 for LR, 0.65 for RF, and 0.54 for SVM.

Conclusion

The outcomes of our study demonstrate the promise of using non-black box models, such as LR, to assist clinicians in recognizing high-risk patients and making informed treatment choices. The coefficients of the LR model show the importance of each feature in predicting results, and the generated nomogram provides an accessible illustration of how each feature impacts the predicted outcome. Additionally, the model's simplicity and interpretability make it a more appropriate option in scenarios where comprehending the model's predictions is essential.