Neuro-Fuzzy Modeling: An Accurate and Interpretable Method for Predicting Bladder Cancer Progression

Predicting non-muscle invasive bladder cancer outcomes using artificial intelligence: a systematic review using APPRAISE-AI

Accurate prediction of recurrence and progression in non-muscle invasive bladder cancer (NMIBC) is essential to inform management and eligibility for clinical trials. Despite substantial interest in developing artificial intelligence (AI) applications in NMIBC, their clinical readiness remains unclear. This systematic review aimed to critically appraise AI studies predicting NMIBC outcomes, and to identify common methodological and reporting pitfalls. MEDLINE, EMBASE, Web of Science, and Scopus were searched from inception to February 5th, 2024 for AI studies predicting NMIBC recurrence or progression. APPRAISE-AI was used to assess methodological and reporting quality of these studies. Performance between AI and non-AI approaches included within these studies were compared. A total of 15 studies (five on recurrence, four on progression, and six on both) were included. All studies were retrospective, with a median follow-up of 71 months (IQR 32-93) and median cohort size of 125 (IQR 93-309). Most studies were low quality, with only one classified as high quality. While AI models generally outperformed non-AI approaches with respect to accuracy, c-index, sensitivity, and specificity, this margin of benefit varied with study quality (median absolute performance difference was 10 for low, 22 for moderate, and 4 for high quality studies). Common pitfalls included dataset limitations, heterogeneous outcome definitions, methodological flaws, suboptimal model evaluation, and reproducibility issues. Recommendations to address these challenges are proposed. These findings emphasise the need for collaborative efforts between urological and AI communities paired with rigorous methodologies to develop higher quality models, enabling AI to reach its potential in enhancing NMIBC care.

A novel pathway to detect muscle-invasive bladder cancer based on integrated clinical features and VI-RADS score on MRI: results of a prospective multicenter study

Purpose

To determine the clinical, pathological, and radiological features, including the Vesical Imaging-Reporting and Data System (VI-RADS) score, independently correlating with muscle-invasive bladder cancer (BCa), in a multicentric national setting.

Method and Materials

Patients with BCa suspicion were offered magnetic resonance imaging (MRI) before trans-urethral resection of bladder tumor (TURBT). According to VI-RADS, a cutoff of ≥ 3 or ≥ 4 was assumed to define muscle-invasive bladder cancer (MIBC). Trans-urethral resection of the tumor (TURBT) and/or cystectomy reports were compared with preoperative VI-RADS scores to assess accuracy of MRI for discriminating between non-muscle-invasive versus MIBC. Performance was assessed by ROC curve analysis. Two univariable and multivariable logistic regression models were implemented including clinical, pathological, radiological data, and VI-RADS categories to determine the variables with an independent effect on MIBC.

Results

A final cohort of 139 patients was enrolled (median age 70 [IQR: 64, 76.5]). MRI showed sensitivity, specificity, PPV, NPV, and accuracy for MIBC diagnosis ranging from 83–93%, 80–92%, 67–81%, 93–96%, and 84–89% for the more experienced readers. The area under the curve (AUC) was 0.95 (0.91–0.99). In the multivariable logistic regression model, the VI-RADS score, using both a cutoff of 3 and 4 (P < .0001), hematuria (P = .007), tumor size (P = .013), and concomitant hydronephrosis (P = .027) were the variables correlating with a bladder cancer staged as ≥ T2. The inter-reader agreement was substantial (k = 0.814).

Conclusions

VI-RADS assessment scoring proved to be an independent predictor of muscle-invasiveness, which might implicate a shift toward a more aggressive selection approach of patients’ at high risk of MIBC, according to a novel proposed predictive pathway.

A systematic review of the applications of Expert Systems (ES) and machine learning (ML) in clinical urology

BACKGROUND

Testing a hypothesis for 'factors-outcome effect' is a common quest, but standard statistical regression analysis tools are rendered ineffective by data contaminated with too many noisy variables. Expert Systems (ES) can provide an alternative methodology in analysing data to identify variables with the highest correlation to the outcome. By applying their effective machine learning (ML) abilities, significant research time and costs can be saved. The study aims to systematically review the applications of ES in urological research and their methodological models for effective multi-variate analysis. Their domains, development and validity will be identified.

METHODS

The PRISMA methodology was applied to formulate an effective method for data gathering and analysis. This study search included seven most relevant information sources: WEB OF SCIENCE, EMBASE, BIOSIS CITATION INDEX, SCOPUS, PUBMED, Google Scholar and MEDLINE. Eligible articles were included if they applied one of the known ML models for a clear urological research question involving multivariate analysis. Only articles with pertinent research methods in ES models were included. The analysed data included the system model, applications, input/output variables, target user, validation, and outcomes. Both ML models and the variable analysis were comparatively reported for each system.

RESULTS

The search identified n = 1087 articles from all databases and n = 712 were eligible for examination against inclusion criteria. A total of 168 systems were finally included and systematically analysed demonstrating a recent increase in uptake of ES in academic urology in particular artificial neural networks with 31 systems. Most of the systems were applied in urological oncology (prostate cancer = 15, bladder cancer = 13) where diagnostic, prognostic and survival predictor markers were investigated. Due to the heterogeneity of models and their statistical tests, a meta-analysis was not feasible.

CONCLUSION

ES utility offers an effective ML potential and their applications in research have demonstrated a valid model for multi-variate analysis. The complexity of their development can challenge their uptake in urological clinics whilst the limitation of the statistical tools in this domain has created a gap for further research studies. Integration of computer scientists in academic units has promoted the use of ES in clinical urological research.

Artificial intelligence in bladder cancer prognosis: a pathway for personalized medicine

PURPOSE OF REVIEW

This review aims to provide an update of the results of studies published in the last 2 years involving the use of artificial intelligence in bladder cancer (BCa) prognosis.

RECENT FINDINGS

Recently, many studies evaluated various artificial intelligence models to predict BCa evolution using either deep learning or machine learning. Many trials evidenced a better prediction of recurrence-free survival and overall survival for muscle invasive BCa (MIBC) for deep learning-based models compared with clinical stages. Improvements in imaging associated with the development of deep learning neural networks and radiomics seem to improve post neo-adjuvant chemotherapy response. One study showed that digitalized histology could predict nonmuscle invasive BCa recurrence.

SUMMARY

BCa prognosis could be better assessed using artificial intelligence models not only in the case of MIBC but also NMIBC. Many studies evaluated its role for the prediction of overall survival and recurrence-free survival but there is still little data in the case of NMIBC. Recent findings showed that artificial intelligence could lead to a better assessment of BCa prognosis before treatment and to personalized medicine.

Bladder cancer in the time of machine learning: Intelligent tools for diagnosis and management

Machine learning (ML) is the subfield of artificial intelligence (AI), born from the marriage between statistics and computer science, with the unique purpose of building prediction algorithms able to improve their performances by automatically learning from massive data sets. The availability of ever-growing computational power and highly evolved pattern recognition software has led to the spread of ML-based systems able to perform complex tasks in bioinformatics, medical imaging, and diagnostics. These intelligent tools could be the answer to the unmet need for non-invasive and patient-tailored instruments for the diagnosis and management of bladder cancer (BC), which are still based on old technologies and unchanged nomograms. We reviewed the most significant evidence on ML in the diagnosis, prognosis, and management of bladder cancer, to find out if these intelligent technologies are ready to be introduced into the daily clinical practice of the urologist.

Toward development of PreVoid alerting system for nocturnal enuresis patients: A fuzzy-based approach for determining the level of liquid encased in urinary bladder

Preventive and accurate assessment of bladder voiding dysfunctions necessitates measuring the amount of liquid encapsulated within urinary bladder walls in a non-invasive and real-time manner. The real-time monitoring of urine levels helps patients with urological disorders such as Nocturnal Enuresis (NE) by preventing the occurrence of enuresis via a pre-void stage alerting system. Although some advances have been achieved toward developing a non-invasive approach for determining the amount of accumulated urine inside the bladder, there is still a lack of an easy-to-implement technique which is suitable to embed in a wearable pre-warning device. This study aims to develop a machine-learning empowered technique to quantify to what extent an individual's bladder is filled by observing the filling-voiding pattern of a patient over a training period. In this experiment, a pulse-echo sonar element is used to generate ultrasound pulses while the probe surface is positioned perpendicular to the bladder's position. From the reflected echoes, four features which show sufficient sensitiveness and therefore could be modulated noticeably by different levels of liquid encased in the bladder, are extracted. The extracted features are then fed into a novel intelligent decision support system- known as FECOC - which is based on hybridization of fuzzy inference systems (FIS) and error correcting output codes (ECOC). The proposed scheme tends to achieve better results when examined in real case studies.

A deep-learning model using automated performance metrics and clinical features to predict urinary continence recovery after robot-assisted radical prostatectomy

OBJECTIVES

To predict urinary continence recovery after robot-assisted radical prostatectomy (RARP) using a deep learning (DL) model, which was then used to evaluate surgeon's historical patient outcomes.

SUBJECTS AND METHODS

Robotic surgical automated performance metrics (APMs) during RARP, and patient clinicopathological and continence data were captured prospectively from 100 contemporary RARPs. We used a DL model (DeepSurv) to predict postoperative urinary continence. Model features were ranked based on their importance in prediction. We stratified eight surgeons based on the five top-ranked features. The top four surgeons were categorized in 'Group 1/APMs', while the remaining four were categorized in 'Group 2/APMs'. A separate historical cohort of RARPs (January 2015 to August 2016) performed by these two surgeon groups was then used for comparison. Concordance index (C-index) and mean absolute error (MAE) were used to measure the model's prediction performance. Outcomes of historical cases were compared using the Kruskal-Wallis, chi-squared and Fisher's exact tests.

RESULTS

Continence was attained in 79 patients (79%) after a median of 126 days. The DL model achieved a C-index of 0.6 and an MAE of 85.9 in predicting continence. APMs were ranked higher by the model than clinicopathological features. In the historical cohort, patients in Group 1/APMs had superior rates of urinary continence at 3 and 6 months postoperatively (47.5 vs 36.7%, P = 0.034, and 68.3 vs 59.2%, P = 0.047, respectively).

CONCLUSION

Using APMs and clinicopathological data, the DeepSurv DL model was able to predict continence after RARP. In this feasibility study, surgeons with more efficient APMs achieved higher continence rates at 3 and 6 months after RARP.

Non-muscle invasive bladder cancer risk stratification

INTRODUCTION

Non-muscle invasive bladder cancer (NMIBC) comprises about 70% of all newly diagnosed bladder cancer, and includes tumors with stage Ta, T1 and carcinoma in situ (CIS.) Since, NMIBC patients with progression to muscle-invasive disease tend to have worse prognosis than with patients with primary muscle-invasive disease, there is a need to significantly improve risk stratification and earlier definitive treatment for high-risk NMIBC.

MATERIALS AND METHODS

A detailed Medline search was performed to identify all publications on the topic of prognostic factors and risk predictions for superficial bladder cancer/NMIBC. The manuscripts were reviewed to identify variables that could predict recurrence and progression.

RESULTS

The most important prognostic factor for progression is grade of tumor. T category, tumor size, number of tumors, concurrent CIS, intravesical therapy, response to bacillus Calmette-Guerin at 3- or 6-month follow-up, prior recurrence rate, age, gender, lymphovascular invasion and depth of lamina propria invasion are other important clinical and pathological parameters to predict recurrence and progression in patients with NMIBC. The European Organization for Research and Treatment of Cancer (EORTC) and the Spanish Club UrológicoEspañol de Tratamiento Oncológico (CUETO) risk tables are the two best-established predictive models for recurrence and progression risk calculation, although they tend to overestimate risk and have poor discrimination for prognostic outcomes in external validation. Molecular biomarkers such as Ki-67, FGFR3 and p53 appear to be promising in predicting recurrence and progression but need further validation prior to using them in clinical practice.

CONCLUSION

EORTC and CUETO risk tables are the two best-established models to predict recurrence and progression in patients with NMIBC though they tend to overestimate risk and have poor discrimination for prognostic outcomes in external validation. Future research should focus on enhancing the predictive accuracy of risk assessment tools by incorporating additional prognostic factors such as depth of lamina propria invasion and molecular biomarkers after rigorous validation in multi-institutional cohorts.

Prognostic and Prediction Tools in Bladder Cancer: A Comprehensive Review of the Literature

CONTEXT

This review focuses on risk assessment and prediction tools for bladder cancer (BCa).

OBJECTIVE

To review the current knowledge on risk assessment and prediction tools to enhance clinical decision making and counseling of patients with BCa.

EVIDENCE ACQUISITION

A literature search in English was performed using PubMed in July 2013. Relevant risk assessment and prediction tools for BCa were selected. More than 1600 publications were retrieved. Special attention was given to studies that investigated the clinical benefit of a prediction tool.

EVIDENCE SYNTHESIS

Most prediction tools for BCa focus on the prediction of disease recurrence and progression in non-muscle-invasive bladder cancer or disease recurrence and survival after radical cystectomy. Although these tools are helpful, recent prediction tools aim to address a specific clinical problem, such as the prediction of organ-confined disease and lymph node metastasis to help identify patients who might benefit from neoadjuvant chemotherapy. Although a large number of prediction tools have been reported in recent years, many of them lack external validation. Few studies have investigated the clinical utility of any given model as measured by its ability to improve clinical decision making. There is a need for novel biomarkers to improve the accuracy and utility of prediction tools for BCa.

CONCLUSIONS

Decision tools hold the promise of facilitating the shared decision process, potentially improving clinical outcomes for BCa patients. Prediction models need external validation and assessment of clinical utility before they can be incorporated into routine clinical care.

PATIENT SUMMARY

We looked at models that aim to predict outcomes for patients with bladder cancer (BCa). We found a large number of prediction models that hold the promise of facilitating treatment decisions for patients with BCa. However, many models are missing confirmation in a different patient cohort, and only a few studies have tested the clinical utility of any given model as measured by its ability to improve clinical decision making.

Molecular subtyping of bladder cancer using Kohonen self-organizing maps

Kohonen self-organizing maps (SOMs) are unsupervised Artificial Neural Networks (ANNs) that are good for low-density data visualization. They easily deal with complex and nonlinear relationships between variables. We evaluated molecular events that characterize high- and low-grade BC pathways in the tumors from 104 patients. We compared the ability of statistical clustering with a SOM to stratify tumors according to the risk of progression to more advanced disease. In univariable analysis, tumor stage (log rank P = 0.006) and grade (P < 0.001), HPV DNA (P < 0.004), Chromosome 9 loss (P = 0.04) and the A148T polymorphism (rs 3731249) in CDKN2A (P = 0.02) were associated with progression. Multivariable analysis of these parameters identified that tumor grade (Cox regression, P = 0.001, OR.2.9 (95% CI 1.6–5.2)) and the presence of HPV DNA (P = 0.017, OR 3.8 (95% CI 1.3–11.4)) were the only independent predictors of progression. Unsupervised hierarchical clustering grouped the tumors into discreet branches but did not stratify according to progression free survival (log rank P = 0.39). These genetic variables were presented to SOM input neurons. SOMs are suitable for complex data integration, allow easy visualization of outcomes, and may stratify BC progression more robustly than hierarchical clustering.

Oral cancer prognosis based on clinicopathologic and genomic markers using a hybrid of feature selection and machine learning methods

Background

Machine learning techniques are becoming useful as an alternative approach to conventional medical diagnosis or prognosis as they are good for handling noisy and incomplete data, and significant results can be attained despite a small sample size. Traditionally, clinicians make prognostic decisions based on clinicopathologic markers. However, it is not easy for the most skilful clinician to come out with an accurate prognosis by using these markers alone. Thus, there is a need to use genomic markers to improve the accuracy of prognosis. The main aim of this research is to apply a hybrid of feature selection and machine learning methods in oral cancer prognosis based on the parameters of the correlation of clinicopathologic and genomic markers.

Results

In the first stage of this research, five feature selection methods have been proposed and experimented on the oral cancer prognosis dataset. In the second stage, the model with the features selected from each feature selection methods are tested on the proposed classifiers. Four types of classifiers are chosen; these are namely, ANFIS, artificial neural network, support vector machine and logistic regression. A k-fold cross-validation is implemented on all types of classifiers due to the small sample size. The hybrid model of ReliefF-GA-ANFIS with 3-input features of drink, invasion and p63 achieved the best accuracy (accuracy = 93.81%; AUC = 0.90) for the oral cancer prognosis.

Conclusions

The results revealed that the prognosis is superior with the presence of both clinicopathologic and genomic markers. The selected features can be investigated further to validate the potential of becoming as significant prognostic signature in the oral cancer studies.

Computational Model for Predicting the Chance of Early Resolution in Children With Vesicoureteral Reflux

PURPOSE

Minimally invasive treatment options and concern regarding long-term antibiotics have increased emphasis on predicting the chance of early vesicoureteral reflux resolution. Computational models, such as artificial neural networks, have been used to assist decision making in the clinical setting using complex numeric constructs to solve multivariable problems. We investigated various computational models to enhance the prediction of vesicoureteral reflux resolution.

MATERIALS AND METHODS

We reviewed the records of 205 children with vesicoureteral reflux, including 163 females and 42 males. In addition to reflux grade, several clinical variables were recorded from the diagnostic visit. Outcome was noted as resolved or unresolved at 1 and 2 years after diagnosis. Two separate data sets were prepared for the 1 and 2-year outcomes, sharing the same input features. The data sets were randomized into a modeling set of 155 and a cross-validation set of 50. The model was constructed with several constructs using neUROn++, a set of C++ programs that we developed, to best fit the data.

RESULTS

A linear support vector machine was found to have the highest accuracy with a test set ROC curve area of 0.819 and 0.86 for the 1 and 2-year models, respectively. The model was deployed in JavaScript for ready availability on the Internet, allowing all input variables to be entered and calculating the odds of 1 and 2-year resolution.

CONCLUSIONS

This computational model allowed the use of multiple variables to improve the individualized prediction of early reflux resolution. This is a potentially useful clinical tool regarding treatment decisions for vesicoureteral reflux.

Application of artificial intelligence to the management of urological cancer

PURPOSE

Artificial intelligence techniques, such as artificial neural networks, Bayesian belief networks and neuro-fuzzy modeling systems, are complex mathematical models based on the human neuronal structure and thinking. Such tools are capable of generating data driven models of biological systems without making assumptions based on statistical distributions. A large amount of study has been reported of the use of artificial intelligence in urology. We reviewed the basic concepts behind artificial intelligence techniques and explored the applications of this new dynamic technology in various aspects of urological cancer management.

MATERIALS AND METHODS

A detailed and systematic review of the literature was performed using the MEDLINE and Inspec databases to discover reports using artificial intelligence in urological cancer.

RESULTS

The characteristics of machine learning and their implementation were described and reports of artificial intelligence use in urological cancer were reviewed. While most researchers in this field were found to focus on artificial neural networks to improve the diagnosis, staging and prognostic prediction of urological cancers, some groups are exploring other techniques, such as expert systems and neuro-fuzzy modeling systems.

CONCLUSIONS

Compared to traditional regression statistics artificial intelligence methods appear to be accurate and more explorative for analyzing large data cohorts. Furthermore, they allow individualized prediction of disease behavior. Each artificial intelligence method has characteristics that make it suitable for different tasks. The lack of transparency of artificial neural networks hinders global scientific community acceptance of this method but this can be overcome by neuro-fuzzy modeling systems.