Waiting in the wings: the emerging role of molecular biomarkers in bladder cancer

Use of machine learning to predict bladder cancer survival outcomes: a systematic literature review

INTRODUCTION

The objective of this systematic review is to summarize the use of machine learning (ML) in predicting overall survival (OS) in patients with bladder cancer.

METHODS

Search terms for bladder cancer, ML algorithms, and mortality were used to identify studies in PubMed and Web of Science as of February 2022. Notable inclusion/exclusion criteria contained the inclusion of studies that utilized patient-level datasets and exclusion of primary gene expression-related dataset studies. Study quality and bias were assessed using the International Journal of Medical Informatics (IJMEDI) checklist.

RESULTS

Of the 14 included studies, the most common algorithms were artificial neural networks (n = 8) and logistic regression (n = 4). Nine articles described missing data handling, with five articles removing patients with missing data entirely. With respect to feature selection, the most common sociodemographic variables were age (n = 9), gender (n = 9), and smoking status (n = 3), with clinical variables most commonly including tumor stage (n = 8), grade (n = 7), and lymph node involvement (n = 6). Most studies (n = 10) were of medium IJMEDI quality, with common areas of improvement being the descriptions of data preparation and deployment.

CONCLUSIONS

ML holds promise for optimizing bladder cancer care through accurate OS predictions, but challenges related to data processing, feature selection, and data source quality must be resolved to develop robust models. While this review is limited by its inability to compare models across studies, this systematic review will inform decision-making by various stakeholders to improve understanding of ML-based OS prediction in bladder cancer and foster interpretability of future models.

Can Peripheral Blood Systemic Immune Response Parameters Predict Oncological Outcomes in Patients with Non-Muscle-Invasive Bladder Cancer?

Background

Many studies have investigated most cancer types - associations with systemic inflammatory response (SIR) parameters. Aim: This study investigated predictive values of SIR parameters in oncological outcomes and survival - to primary non-muscle-invasive bladder cancer (NMIBC) patients.

Materials and Methods

We analyzed 74 primary NMIBC patients. Clinical features, laboratory results, and tumor characteristics were recorded. In addition, the neutrophil-to-lymphocyte ratio (NLR), monocyte-to-lymphocyte ratio (MLR), platelet-to-lymphocyte ratio (PLR), serum C-reactive protein, albumin-to-globulin ratio (AGR), and modified Glasgow prognostic scores (mGPS) were calculated.

Results

The - mean age of the patients was - 67.41 ± 11.31 years, and the follow-up duration was 38.77 ± 19.53 months. We - found no significant NLR, CRP, and AGR - correlations with tumor characteristics and oncological outcomes. There were significant - correlations between MLR and pathological-T-stage and the PLR, pathological-T-stage, and tumor count. Carcinoma in situ was associated with a high mGPS. Multivariate analysis revealed no significant - correlations between systemic inflammatory response parameters and oncological outcomes. Patients with a high mGPS had poor cancer-specific survival. Increased NLR was associated with reduced overall survival.

Conclusions

This study revealed no significant correlation between SIR parameters and oncological outcomes. Therefore, we need more reliable indicators than SIR parameters in NMIBC patients in clinical practice.

Prognostic Role of Preoperative Vascular Cell Adhesion Molecule-1 Plasma Levels in Urothelial Carcinoma of the Bladder Treated With Radical Cystectomy

Background

Angiogenesis-related marker vascular cell adhesion molecule-1 (VCAM-1) has been shown to be elevated in urothelial carcinoma of the bladder (UCB), but its predictive/prognostic role has not been determined. Thus, this study aimed to investigate the predictive/prognostic role of VCAM-1 for patients who have UCB treated with radical cystectomy (RC).

Methods

The study enrolled 1036 patients with clinically non-metastatic advanced UCB who underwent RC, and plasma VCAM-1 was evaluated preoperatively. The correlation of plasma VCAM-1 with pathologic and survival outcomes was assessed using binominal logistic regression and multivariable Cox regression analyses. Discrimination was assessed using the area under the curve and concordance indices. The clinical net benefit was evaluated using decision curve analysis (DCA).

Results

Preoperative VCAM-1 was significantly elevated in patients with adverse pathologic features. Higher VCAM-1 levels were independently associated with increased risk of lymph-node-metastasis (LNM), ≥pT3 disease, and non-organ-confined disease (NOCD (p < 0.001 for each). Preoperative plasma VCAM-1 was independently associated with recurrence-free survival (RFS), cancer-specific survival (CSS), and overall survival (OS) in pre- and postoperative multivariable models. Adding VCAM-1 to these predictive models improved their discriminatory ability to predict all outcomes by a significant margin. In the DCA, VCAM-1 addition to the reference models for prediction of LNM, NOCD, RFS, and CSS resulted in relevant improvement.

Conclusions

Elevated plasma VCAM-1 was associated with biologically and clinically aggressive UCB disease features. After validation, preoperative VCAM-1 may serve as a biomarker to help identify patients likely to benefit from intensified/multimodal therapy. In addition, VCAM-1 improved the discriminatory power of predictive/prognostic models and can be used to refine personalized clinical decision-making.

The Value of Preoperative Plasma VEGF Levels in Urothelial Carcinoma of the Bladder Treated with Radical Cystectomy

BACKGROUND

Elevated preoperative plasma levels of the angiogenesis-related marker VEGF have been associated with worse oncological outcomes in various malignancies.

OBJECTIVE

To investigate the predictive/prognostic role of VEGF in patients with urothelial carcinoma of the bladder (UCB) treated with radical cystectomy (RC).

DESIGN, SETTING, AND PARTICIPANTS

VEGF plasma levels were measured preoperatively in 1036 patients with UCB who underwent RC.

OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS

The correlation between plasma VEGF levels and pathological and survival outcomes was assessed using logistic regression and Cox regression analyses. Discrimination was assessed using the concordance index (C index). The clinical net benefit was evaluated using decision curve analysis (DCA).

RESULTS AND LIMITATIONS

Patients with higher pretreatment plasma VEGF levels had poorer recurrence-free survival (RFS), cancer-specific survival (CSS), and overall survival (OS) according to log-rank tests (all p < 0.001). Higher VEGF levels were not independently associated with higher risk of lymph node metastasis, ≥pT3 disease, or non-organ-confined disease (all p > 0.05). Preoperative plasma VEGF levels were independently associated with RFS, CSS, and OS in preoperative and postoperative multivariable models. However, in all cases the C index increased by <0.02 and there was no improvement in net benefit on DCA. A limitation is that none of the patients received current elements of standard of care such as neoadjuvant chemotherapy.

CONCLUSIONS

Elevated plasma VEGF levels were associated with features of biologically and clinically aggressive disease such as worse survival outcomes among patients with UCB treated with RC. However, VEGF appears to have relatively limited incremental additive value in clinical use. Further study of VEGF for UCB prognostication is warranted before routine use in clinical algorithms.

PATIENT SUMMARY

Currently available models for predicting outcomes in bladder cancer are less than optimal. A protein called vascular endothelial growth factor (VEGF), which is a marker of the formation of blood vessels (angiogenesis), may have a role in predicting survival outcomes in bladder cancer.

TAKE HOME MESSAGE

Elevated plasma VEGF levels are associated with worse survival outcomes for patients with urothelial carcinoma of the bladder (UCB) treated with radical cystectomy. VEGF could be used as a part of a biomarker panel to enhance tools currently used for risk stratification for patients with UCB.

A panel of systemic inflammatory response biomarkers for outcome prediction in patients treated with radical cystectomy for urothelial carcinoma

Objectives

To determine the predictive and prognostic value of a panel of systemic inflammatory response (SIR) biomarkers relative to established clinicopathological variables in order to improve patient selection and facilitate more efficient delivery of peri‐operative systemic therapy.

Materials and Methods

The preoperative serum levels of a panel of SIR biomarkers, including albumin–globulin ratio, neutrophil–lymphocyte ratio, De Ritis ratio, monocyte–lymphocyte ratio and modified Glasgow prognostic score were assessed in 4199 patients treated with radical cystectomy for clinically non‐metastatic urothelial carcinoma of the bladder. Patients were randomly divided into a training and a testing cohort. A machine‐learning‐based variable selection approach (least absolute shrinkage and selection operator regression) was used for the fitting of several multivariable predictive and prognostic models. The outcomes of interest included prediction of upstaging to carcinoma invading bladder muscle (MIBC), lymph node involvement, pT3/4 disease, cancer‐specific survival (CSS) and recurrence‐free survival (RFS). The discriminatory ability of each model was either quantified by area under the receiver‐operating curves or by the C‐index. After validation and calibration of each model, a nomogram was created and decision‐curve analysis was used to evaluate the clinical net benefit.

Results

For all outcome variables, at least one SIR biomarker was selected by the machine‐learning process to be of high discriminative power during the fitting of the models. In the testing cohort, model performance evaluation for preoperative prediction of lymph node metastasis, ≥pT3 disease and upstaging to MIBC showed a 200‐fold bootstrap‐corrected area under the curve of 67.3%, 73% and 65.8%, respectively. For postoperative prognosis of CSS and RFS, a 200‐fold bootstrap corrected C‐index of 73.3% and 72.2%, respectively, was found. However, even the most predictive combinations of SIR biomarkers only marginally increased the discriminative ability of the respective model in comparison to established clinicopathological variables.

Conclusion

While our machine‐learning approach for fitting of the models with the highest discriminative ability incorporated several previously validated SIR biomarkers, these failed to improve the discriminative ability of the models to a clinically meaningful degree. While the prognostic and predictive value of such cheap and readily available biomarkers warrants further evaluation in the age of immunotherapy, additional novel biomarkers are still needed to improve risk stratification.

Subcellular Localization of uc.8+ as a Prognostic Biomarker in Bladder Cancer Tissue

Simple Summary

DNA regions having high sequence similarity among human, rat and mouse genomes are defined as Ultraconserved Regions. Non-coding RNA transcripts originating by these regions may play relevant roles in the onset and progression of multiple cancer types. We recently found that ultra-conserved-transcript-8+ (uc.8+) levels correlate with the grading and staging of bladder cancer. The aim of this study is to systematically evaluate the expression of ultra-conserved-transcript-8+ (uc.8+) in biopsies and assess its intracellular localization. Furthermore, we aimed to correlate uc.8+ levels with clinical parameters and patient survival. Our analysis indicates that uc.8+ can localize both in the cytoplasm and nucleus of bladder cells at early stages of tumorigenesis, while in tumors at advanced stages, uc.8+ has a prevalent cytoplasmic localization. These data provide relevant information about uc.8+ localization as a hallmark of tumor stage. Finally, using advanced computer-based techniques, we predicted the binding of uc.8+ to RNA-binding proteins. Our study overall suggests that uc.8+ localization can be used as a prognostic biomarker for bladder cancer.

Abstract

Non-coding RNA transcripts originating from Ultraconserved Regions (UCRs) have tissue-specific expression and play relevant roles in the pathophysiology of multiple cancer types. Among them, we recently identified and characterized the ultra-conserved-transcript-8+ (uc.8+), whose levels correlate with grading and staging of bladder cancer. Here, to validate uc.8+ as a potential biomarker in bladder cancer, we assessed its expression and subcellular localization by using tissue microarray on 73 human bladder cancer specimens. We quantified uc.8+ by in-situ hybridization and correlated its expression levels with clinical characteristics and patient survival. The analysis of subcellular localization indicated the simultaneous presence of uc.8+ in the cytoplasm and nucleus of cells from the Low-Grade group, whereas a prevalent cytoplasmic localization was observed in samples from the High-Grade group, supporting the hypothesis of uc.8+ nuclear-to-cytoplasmic translocation in most malignant tumor forms. Moreover, analysis of uc.8+ expression and subcellular localization in tumor-surrounding stroma revealed a marked down-regulation of uc.8+ levels compared to the paired (adjacent) tumor region. Finally, deep machine-learning approaches identified nucleotide sequences associated with uc.8+ localization in nucleus and/or cytoplasm, allowing to predict possible RNA binding proteins associated with uc.8+, recognizing also sequences involved in mRNA cytoplasm-translocation. Our model suggests uc.8+ subcellular localization as a potential prognostic biomarker for bladder cancer.

Discovery of Molecular DNA Methylation-Based Biomarkers through Genome-Wide Analysis of Response Patterns to BCG for Bladder Cancer

Background: Bacillus Calmette-Guérin (BCG) immunotherapy, the standard adjuvant intravesical therapy for some intermediate and most high-risk non-muscle invasive bladder cancers (NMIBCs), suffers from a heterogenous response rate. Molecular markers to help guide responses are scarce and currently not used in the clinical setting. Methods: To identify novel biomarkers and pathways involved in response to BCG immunotherapy, we performed a genome-wide DNA methylation analysis of NMIBCs before BCG therapy. Genome-wide DNA methylation profiles of DNA isolated from tumors of 26 BCG responders and 27 failures were obtained using the Infinium MethylationEPIC BeadChip. Results: Distinct DNA methylation patterns were found by genome-wide analysis in the two groups. Differentially methylated CpG sites were predominantly located in gene promoters and gene bodies associated with bacterial invasion of epithelial cells, chemokine signaling, endocytosis, and focal adhesion. In total, 40 genomic regions with a significant difference in methylation between responders and failures were detected. The differential methylation state of six of these regions, localized in the promoters of the genes GPR158, KLF8, C12orf42, WDR44, FLT1, and CHST11, were internally validated by bisulfite-sequencing. GPR158 promoter hypermethylation was the best predictor of BCG failure with an AUC of 0.809 (p-value < 0.001). Conclusions: Tumors from BCG responders and BCG failures harbor distinct DNA methylation profiles. Differentially methylated DNA regions were detected in genes related to pathways involved in bacterial invasion of cells or focal adhesion. We identified candidate DNA methylation biomarkers that may help to predict patient prognosis after external validation in larger, well-designed cohorts.

Antibodies against aberrant glycans as cancer biomarkers

Introduction: The review provides a comprehensive overview about applicability of serological detection of autoantibodies against aberrant glycans as cancer biomarkers.Areas covered: Clinical usefulness of autoantibodies as cancer biomarkers is discussed for seven types of cancers with sensitivity and specificity of such biomarkers provided. Moreover, an option of using serological antibodies against a non-natural form of sialic acid - N-glycolylneuraminic acid (Neu5Gc), which is taken into our bodies together with red meat, as a potential cancer biomarker is discussed shortly as well.Expert opinion: In the final part of the review, we discuss what measures need to be applied for selective implementation of autoantibody assays into a clinical practice. Moreover, we discuss key challenges ahead for reliable and robust detection of autoantibodies against aberrant glycans as biomarkers for disease diagnostics and for stratification of cancer patients.

Tissue biomarkers in nonmuscle-invasive bladder cancer: any role in clinical practice?

PURPOSE OF REVIEW

To summarize recent findings on tissue biomarkers for nonmuscle-invasive bladder cancer (NMIBC) with an emphasis on their prognostic and predictive role.

RECENT FINDINGS

Accurate risk stratification is essential and the major driver in patient counseling regarding surveillance and decision making relative to therapeutic strategies. In NMIBC, there is an unmet need for improving the accuracy of current prognostic and predictive models, which rely only on clinicopathologic features and do not reflect the biological heterogeneity of the cancer in each individual. Studies continuously shed novel light on some processes involved in cancerogenesis, host response and interactions in the tumor's own microenvironment, which may be considered as potential biomarkers and targets for future directed therapies.

SUMMARY

Biomarkers are necessary to transform bladder cancer management and usher in the age of personalized medicine. The clinical use is, however, still limited because of heterogeneity in study design, staining methods and an overall lacking adherence to a structured biomarker testing process.

Beyond BCG: the approaching era of personalised bladder-sparing therapies for non-muscle-invasive urothelial cancers

Progress in the management of non-muscle invasive bladder cancer has been slow. Despite longstanding use of intravesical therapies (e.g., Bacille Calmette-Guerin; BCG) to complement cystoscopic resection of high-grade lesions, many patients still develop recurrences requiring cystectomy, while others suffer side-effects of BCG without definite benefit. Many questions remain: for example, how many patients receive intravesical prophylaxis without efficacy? Which high-risk patients are best managed with early cystectomy? Could systemic therapies and/or radiotherapy extend bladder preservation times? Such questions may soon be refined by clinicopathologic non-muscle invasive bladder cancer signatures that predict sensitivity to cytotoxic, immune and targeted therapies. Hypothesis-based trials using these signatures should lead to more rational adjuvant treatments, longer bladder preservation times, and better quality of life for patients.

Identification of Core Genes and Key Pathways via Integrated Analysis of Gene Expression and DNA Methylation Profiles in Bladder Cancer

Background

Bladder cancer (BC) is the most common urological malignant tumor. In BC, aberrant DNA methylation is believed to be associated with carcinogenesis. Therefore, the identification of key genes and pathways could help determine the potential molecular mechanisms of BC development.

Material/Methods

Microarray data on gene expression and gene methylation were downloaded from the Gene Expression Omnibus (GEO) database. Abnormal methylated/expressed genes were analyzed by GEO2R and statistical software R. Gene Ontology term enrichment and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis were performed using the DAVID database and KOBAS 3.0. STRING and Cytoscape software were used to construct protein–protein interaction (PPI) networks and analyze modules of the PPI network.

Results

A total of 71 hypomethylated/upregulated genes were significantly enriched in cell–cell adhesion and blood vessel development. KEGG pathway analysis highlighted p53 signaling and metabolic pathways. Five core genes in the PPI network were determined: CDH1, DDOST, CASP8, DHX15, and PTPRF. Additionally, 89 hypermethylated/downregulated genes were found. These genes were enriched mostly in cell adhesion and signal transduction. KEGG pathway analysis revealed enrichment in focal adhesion. The top 5 core genes in the PPI network were GNG4, ADCY9, NPY, ADRA2B, and PENK. We found most of the core genes were also significantly altered in the Cancer Genome Atlas database.

Conclusions

Abnormal methylated/expressed genes and key signaling pathways involved in BC were identified through integrated bioinformatics analysis. In the future, these genes may serve as biomarkers for diagnosis and therapeutic targets in BC.