A Genomic-clinicopathologic Nomogram for the Preoperative Prediction of Lymph Node Metastasis in Bladder Cancer

Using machine learning to develop preoperative model for lymph node metastasis in patients with bladder urothelial carcinoma

BACKGROUND

Lymph node metastasis (LNM) is associated with worse prognosis in bladder urothelial carcinoma (BUC) patients. This study aimed to develop and validate machine learning (ML) models to preoperatively predict LNM in BUC patients treated with radical cystectomy (RC).

METHODS

We retrospectively collected demographic, pathological, imaging, and laboratory information of BUC patients who underwent RC and bilateral lymphadenectomy in our institution. Patients were randomly categorized into training set and testing set. Five ML algorithms were utilized to establish prediction models. The performance of each model was assessed by the area under the receiver operating characteristic curve (AUC) and accuracy. Finally, we calculated the corresponding variable coefficients based on the optimal model to reveal the contribution of each variable to LNM.

RESULTS

A total of 524 and 131 BUC patients were finally enrolled into training set and testing set, respectively. We identified that the support vector machine (SVM) model had the best prediction ability with an AUC of 0.934 (95% confidence interval [CI]: 0.903-0.964) and accuracy of 0.916 in the training set, and an AUC of 0.855 (95%CI: 0.777-0.933) and accuracy of 0.809 in the testing set. The SVM model contained 14 predictors, and positive lymph node in imaging contributed the most to the prediction of LNM in BUC patients.

CONCLUSIONS

We developed and validated the ML models to preoperatively predict LNM in BUC patients treated with RC, and identified that the SVM model with 14 variables had the best performance and high levels of clinical applicability.

Development and validation of a preoperative nomogram to predict lymph node metastasis in patients with bladder urothelial carcinoma

PURPOSE

Predicting lymph node metastasis (LNM) in patients with bladder urothelial carcinoma (BUC) before radical cystectomy aids clinical decision making. Here, we aimed to develop and validate a nomogram to preoperatively predict LNM in BUC patients.

METHODS

Patients with histologically confirmed BUC, who underwent radical cystectomy and bilateral lymphadenectomy, were retrospectively recruited from two institutions. Patients from one institution were enrolled in the primary cohort, while those from the other were enrolled in the external validation cohort. Patient demographic, pathological (using transurethral resection of the bladder tumor specimens), imaging, and laboratory data were recorded. Univariate and multivariate logistic regression analyses were performed to explore the independent preoperative risk factors and develop the nomogram. Internal and external validation was conducted to assess nomogram performance.

RESULTS

522 and 215 BUC patients were enrolled in the primary and external validation cohorts, respectively. We identified tumor grade, infiltration, extravesical invasion, LNM on imaging, tumor size, and serum creatinine levels as independent preoperative risk factors, which were subsequently used to develop the nomogram. The nomogram showed a good predictive accuracy, with area under the receiver operator characteristic curve values of 0.817 and 0.825 for the primary and external validation cohorts, respectively. The corrected C-indexes, calibration curves (after 1000 bootstrap resampling), decision curve analysis results, and clinical impact curves demonstrated that the nomogram performed well in both cohorts and was highly clinically applicable.

CONCLUSION

We developed a nomogram to preoperatively predict LNM in BUC, which was highly accurate, reliable, and clinically applicable.

Artificial Intelligence in the Advanced Diagnosis of Bladder Cancer-Comprehensive Literature Review and Future Advancement

Artificial intelligence is highly regarded as the most promising future technology that will have a great impact on healthcare across all specialties. Its subsets, machine learning, deep learning, and artificial neural networks, are able to automatically learn from massive amounts of data and can improve the prediction algorithms to enhance their performance. This area is still under development, but the latest evidence shows great potential in the diagnosis, prognosis, and treatment of urological diseases, including bladder cancer, which are currently using old prediction tools and historical nomograms. This review focuses on highly significant and comprehensive literature evidence of artificial intelligence in the management of bladder cancer and investigates the near introduction in clinical practice.

Predicting Lymph Node Metastasis Status from Primary Muscle-Invasive Bladder Cancer Histology Slides Using Deep Learning: A Retrospective Multicenter Study

BACKGROUND

Accurate prediction of lymph node metastasis (LNM) status in patients with muscle-invasive bladder cancer (MIBC) before radical cystectomy can guide the use of neoadjuvant chemotherapy and the extent of pelvic lymph node dissection. We aimed to develop and validate a weakly-supervised deep learning model to predict LNM status from digitized histopathological slides in MIBC.

METHODS

We trained a multiple instance learning model with an attention mechanism (namely SBLNP) from a cohort of 323 patients in the TCGA cohort. In parallel, we collected corresponding clinical information to construct a logistic regression model. Subsequently, the score predicted by the SBLNP was incorporated into the logistic regression model. In total, 417 WSIs from 139 patients in the RHWU cohort and 230 WSIs from 78 patients in the PHHC cohort were used as independent external validation sets.

RESULTS

In the TCGA cohort, the SBLNP achieved an AUROC of 0.811 (95% confidence interval [CI], 0.771-0.855), the clinical classifier achieved an AUROC of 0.697 (95% CI, 0.661-0.728) and the combined classifier yielded an improvement to 0.864 (95% CI, 0.827-0.906). Encouragingly, the SBLNP still maintained high performance in the RHWU cohort and PHHC cohort, with an AUROC of 0.762 (95% CI, 0.725-0.801) and 0.746 (95% CI, 0.687-0.799), respectively. Moreover, the interpretability of SBLNP identified stroma with lymphocytic inflammation as a key feature of predicting LNM presence.

CONCLUSIONS

Our proposed weakly-supervised deep learning model can predict the LNM status of MIBC patients from routine WSIs, demonstrating decent generalization performance and holding promise for clinical implementation.

Novel, alternative splicing signature to detect lymph node metastasis in prostate adenocarcinoma with machine learning

Background

The presence of lymph node metastasis leads to a poor prognosis for prostate cancer (Pca). Recently, many studies have indicated that gene signatures may be able to predict the status of lymph nodes. The purpose of this study is to probe and validate a new tool to predict lymph node metastasis (LNM) based on alternative splicing (AS).

Methods

Gene expression profiles and clinical information of prostate adenocarcinoma cohort were retrieved from The Cancer Genome Atlas (TCGA) database, and the corresponding RNA-seq splicing events profiles were obtained from the TCGA SpliceSeq. Limma package was used to identify the differentially expressed alternative splicing (DEAS) events between LNM and non-LNM groups. Eight machine learning classifiers were built to train with stratified five-fold cross-validation. SHAP values was used to explain the model.

Results

333 differentially expressed alternative splicing (DEAS) events were identified. Using correlation filter and the least absolute shrinkage and selection operator (LASSO) method, a 96 AS signature was identified that had favorable discrimination in the training set and validated in the validation set. The linear discriminant analysis (LDA) was the best classifier after 100 iterations of training. The LDA classifier was able to distinguish between LNM and non-LNM with an area under the receiver operating curve of 0.962 ± 0.026 in the training set (D1 = 351) and 0.953 in the validation set (D2 = 62). The decision curve analysis plot proved the clinical application of the AS-based model.

Conclusion

Machine learning combined with AS data could robustly distinguish between LNM and non-LNM in Pca.

Pelvic lymph node dissection in prostate and bladder cancers

Prostate cancer and bladder cancer accounts for approximately 13.5% and 3% of all male cancers and all newly diagnosed cancers (regardless sex), respectively. Thus, these cancers represent a major health and economic burden globally. The knowledge of lymph node status is an integral part of the management of any solid tumor. In the urological field, pelvic lymph node dissection (PLND) is of paramount importance in the diagnosis, management, and prognosis of prostate and bladder cancers. However, PLND may be associated with several comorbidities. In this narrative review, the most recent updates concerning the patterns and incidence of lymph node metastasis, the role of different imaging studies and nomograms in determining patients' eligibility for PLND, and the anatomical templates of PLND in urologic patients with bladder or prostate cancer will be discussed.

Development and validation of a prognostic nomogram for adult patients with renal sarcoma: A retrospective study based on the SEER database

Background

Renal sarcoma (RS) is rarely seen in clinical practice. The purpose of this study was to develop a prognostic nomogram model, which could predict the probability of overall survival (OS) and cancer-specific survival (CSS) in adult patients with RS.

Methods

Patients diagnosed with RS were recruited from the SEER database between 2004 and 2015, and randomized to two cohorts: the training cohort and the validation cohort. Uni- and multivariate Cox regression analyses in the training cohort were used to screen independent prognostic factors for OS and CSS. Prognostic nomograms for OS and CSS were created separately for adult RS patients based on independent risk factors. The area under the receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) were used to validate the nomograms.

Results

A total of 232 eligible patients were recruited, including 162 in the training cohort and 70 in the validation cohort. Sex, histological type, SEER stage, and surgery were independent prognostic factors for OS, while histological type, SEER stage, surgery, chemotherapy were independent prognostic factors for CSS. Based on the above independent prognostic factors, prognostic nomograms for OS and CSS were created respectively. In the training cohort, the AUCs of the nomograms for OS and CSS were 0.742 and 0.733, respectively. In the validation cohort, the AUCs of the nomograms for OS and CSS were 0.837 and 0.758, respectively. The calibration curves of the nomograms showed high consistencies between the predicted and actual survival rates. Finally, the DCA demonstrated that the nomograms in the wide high-risk threshold had a higher net benefit than the SEER stage.

Conclusion

A prognostic nomogram for renal sarcoma was created and validated for reliability and usefulness in our study, which assisted urologists in accurately assessing the prognosis of adult RS patients.

Identification of leucine-rich repeat-containing protein 59 (LRRC59) located in the endoplasmic reticulum as a novel prognostic factor for urothelial carcinoma

BACKGROUND

Urothelial carcinoma (UC) is one of the most common cancers worldwide. The biological heterogeneity of UCs causes considerable difficulties in predicting treatment outcomes and usually leads to clinical mismanagement. The identification of more sensitive and efficient predictive biomarkers is important in the diagnosis and classification of UCs. Herein, we report leucine-rich repeat-containing protein 59 (LRRC59) located in the endoplasmic reticulum as a novel predictive factor and potential therapeutic target for UCs.

METHODS

Using whole-slide image analysis in our cohort of 107 UC samples, we performed immunohistochemistry to evaluate the prognostic value of LRRC59 expression in UCs. In vitro experiments using RNAi were conducted to explore the role of LRRC59 in promoting UC cell proliferation and migration.

RESULTS

A significant correlation between LRRC59 and unfavorable prognosis of UCs in our cohort was demonstrated. Subsequent clinical analysis also revealed that elevated expression levels of LRRC59 were significantly associated with higher pathological grades and advanced stages of UC. Subsequently, knockdown of LRRC59 in UM-UC-3 and T24 cells using small interfering RNA significantly inhibited cell proliferation and migration, resulting in cell cycle arrest at the G1 phase. Conversely, the overexpression of LRRC59 in UC cells enhanced cell proliferation and migration. An integrated bioinformatics analysis revealed a significant functional network of LRRC59 involving protein misfolding, ER stress, and ubiquitination. Finally, in vitro experiments demonstrated that LRRC59 modulates ER stress signaling.

CONCLUSIONS

LRRC59 expression was significantly correlated with UC prognosis. LRRC59 might not only serve as a novel prognostic biomarker for risk stratification of patients with UC but also exhibit as a potential therapeutic target in UC that warrants further investigation.

Diagnostic accuracy of preoperative lymph node staging of bladder cancer according to different lymph node locations: A multicenter cohort from the European Association of Urology - Young Academic Urologists

BACKGROUND

The preoperative lymph node (LN) staging of bladder cancer (BCa) addresses the subsequent therapeutic strategy and influences patient's prognosis. However, sparce evidence exists regarding the accuracy of conventional cross-sectional imaging, such as computed tomography or magnetic resonance imaging, in correctly detect LN status. We aimed to assess the diagnostic accuracy of conventional cross-sectional imaging in detecting preoperative LN involvement among BCa patients treated with radical cystectomy and pelvic lymph node dissection.

METHODS

We retrospectively analyzed data of 1,104 patients who underwent preoperative LN staging with computed tomography or magnetic resonance imaging and subsequent radical cystectomy with pelvic lymph node dissection for BCa between 1997 and 2017 at three tertiary referral centers. Patients receiving neoadjuvant chemotherapy were excluded. We assessed the concordance between clinical (cN) and pathological LN (pN) status, defined as the accuracy of imaging in detecting LN involvement using pathological specimen as reference; concordance was expressed according to Cohen's kappa coefficient. Location-based sub-analyses were performed, distinguishing among external iliac, intern iliac, obturator, common iliac, presacral and paraaortic LNs.

RESULTS

Among 870 cN0 patients, 68.9% were confirmed pN0 at pathological report; while among 234 cN+ patients, 50.5% were found with LN metastases at pathological specimen. Overall, conventional imaging showed slight concordance (64.9%) between cN and pN stages (sensitivity: 30%; specificity: 84%). At sub-analysis, no agreement between cN and pN status was found in each LN location, with the only exception of common iliac LNs with slight concordance (37.5%). Common iliac LNs achieved the highest sensitivity and positive likelihood ratio (15% and 2.4, respectively) compared to other LN locations.

CONCLUSIONS

Overall, preoperative cross-sectional imaging exhibited a slight concordance between cN and pN status. Our location-based sub-analyses showed unsatisfactory results in each LN location- Thus, nomograms combining morphological patterns with serological and clinicopathological features are urgently required.

Prediction of Prognosis and Recurrence of Bladder Cancer by ECM-Related Genes

Background

Bladder cancer (BLCA) is one of the most common cancers and ranks ninth among all cancers. Extracellular matrix (ECM) genes activate a number of pathways that facilitate tumor development. This study is aimed at providing models to predict BLCA survival and recurrence by ECM genes.

Methods

Expression data from BLCA samples in GSE32894, GSE13507, GSE31684, GSE32548, and TCGA-BLCA cohorts were downloaded and analyzed. The ECM-related genes were obtained by differentially expressed gene analysis, stage-associated gene analysis, and random forest variable selection. The ECM was constructed in GSE32894 by the hub ECM-related genes and validated in GSE13507, GSE31684, GSE32548, and TCGA-BLCA cohorts. The correlations of the ECM score with cells (T cells, fibroblasts, etc.) and the response to immunotherapeutic drugs were investigated. Four machine learning models were selected and used to construct models to predict the recurrence of BLCA. A total of 15 paired BLCA and normal tissue specimens, human immortalized uroepithelial cell lines, and bladder cancer cell lines were selected for the validation of the difference in expression of FSTL1 between normal tissues and BLCA.

Results

Six ECM genes (CTHRC1, MMP11, COL10A1, FSTL1, SULF1, and COL5A3) were recognized to be the hub ECM-related genes. The ECM score of each BLCA patient was calculated using these six selected ECM-related genes. BLCA patients with a high ECM score group had significantly lower overall survival rates than patients in the low ECM score group. We found that the ECM score was positively associated with immune cells and fibroblasts and negatively correlated with tumor purity. When treated with immunotherapy, BLCA patients with a high ECM score presented a high response rate and better prognosis. We also found that the combination of FSTL1, stage, age, and gender achieved an AUC value of 0.76 in predicting bladder cancer recurrence. Based on the RT-qPCR results of FSTL1 gene expression, there was an overall decrease in the mRNA expression of FSTL1 in cancer tissues compared to their adjacent normal tissues. Subsequent in vitro validation demonstrated that the FSTL1 expression was downregulated at the gene and protein level compared to that in SVH cells.

Conclusion

Taken together, our results indicate that ECM-related genes correlate with immune cells, overall survival, and recurrence of BLCA. This study provides a machine learning model for predicting the survival and recurrence of BLCA patients.

Biomarkers in muscle invasive bladder cancer

Muscle invasive bladder cancer (MIBC) carries a poor prognosis with a 5-year overall survival rate of 40-50%. For localized disease, radical treatment options are cystectomy or radiotherapy with or without a radiosensitiser. Neoadjuvant or adjuvant chemotherapy is often delivered in addition to either. Metastatic disease can be treated with palliative systemic chemotherapy or immunotherapy. Standard clinicopathological information is insufficient to guide treatment decisions in several clinical scenarios in MIBC and there has been substantial effort to identify predictive and prognostic biomarkers. Despite this, no biomarker has been sufficiently qualified in prospective clinical trials to justify routine use. In this chapter we discuss these biomarkers and provide insight into the significant unmet need for robust biomarkers to inform treatment decisions and ultimately improve outcomes for bladder cancer patients.

Establishment of A Nomogram for Predicting the Prognosis of Soft Tissue Sarcoma Based on Seven Glycolysis-Related Gene Risk Score

Background: Soft tissue sarcoma (STS) is a group of tumors with a low incidence and a complex type. Therefore, it is an arduous task to accurately diagnose and treat them. Glycolysis-related genes are closely related to tumor progression and metastasis. Hence, our study is dedicated to the development of risk characteristics and nomograms based on glycolysis-related genes to assess the survival possibility of patients with STS.

Methods: All data sets used in our research include gene expression data and clinical medical characteristics in the Genomic Data Commons Data Portal (National Cancer Institute) Soft Tissue Sarcoma (TCGA SARC) and GEO database, gene sequence data of corresponding non-diseased human tissues in the Genotype Tissue Expression (GTEx).Next, transcriptome data in TCGA SARC was analyzed as the training set to construct a glycolysis-related gene risk signature and nomogram, which were confirmed in external test set.

Results: We identified and verified the 7 glycolysis-related gene signature that is highly correlated with the overall survival (OS) of STS patients, which performed excellently in the evaluation of the size of AUC, and calibration curve. As well as, the results of the analysis of univariate and multivariate Cox regression demonstrated that this 7 glycolysis-related gene characteristic acts independently as an influence predictor for STS patients. Therefore, a prognostic-related nomogram combing 7 gene signature with clinical influencing features was constructed to predict OS of patients with STS in the training set that demonstrated strong predictive values for survival.

Conclusion: These results demonstrate that both glycolysis-related gene risk signature and nomogram were efficient prognostic indicators for patients with STS. These findings may contribute to make individualize clinical decisions on prognosis and treatment.

Construction of a ceRNA network and a genomic-clinicopathologic nomogram to predict survival for HBV-related HCC

Some lncRNA-associated competing endogenous RNAs (ceRNAs) are considered as potential biomarkers for targeted therapies and prognosis in human cancer. In our present study, we aimed to construct a ceRNA network and establish a genomic-clinicopathologic nomogram to provide insights into the molecular mechanisms and predict survival for HBV-related HCC. The Cancer Genome Atlas (TCGA) database was applied to collect the data of LIHC RNA-seq dataset and miRNA-seq dataset as well as the clinicopathological information. Identification of differentially expressed RNAs (mRNAs, lncRNAs, and miRNAs) between HBV-related HCC samples and normal samples was conducted using Limma package in R. The Database for Annotation, Visualization, and Integrated Discovery (DAVID) was used for performing the functional enrichment analysis of differentially expressed mRNAs. The ceRNA network was carried out using Cytoscape. The LASSO-penalized Cox regression analysis was implemented to identify HCC-related lncRNAs, and the multivariate Cox regression analysis was conducted for the establishment of a genomic-clinicopathology nomogram. A total of 1859 DEmRNAs, 113 DElncRNAs, and 89 DEmiRNAs were screened out etween HBV-related HCC samples and normal samples. A ceRNA network including 44 DEmRNAs, 7 DElncRNAs, and 20 DEmiRNAs was constructed. 7 DElncRNAs (PVT1, LINC01138, LINC02499, AL355488.2, FGF14-AS2, MAFG-AS1 and LINC00261) were finally identified as prognostic indicators. The area under the curve reached 0.8169 for the 7-lncRNA signature. The predictive accuracy and clinical application value were remarkably high for the genomic-clinicopathologic nomogram integrating the histological grade and the 7-gene-based prognostic index. Taken together, we have established a ceRNA network with HBV-related HCC-specific DElncRNAs, DEmiRNAs, and DEmRNAs. Furthermore, the genome-wide data of lncRNA expression were analyzed using the TCGA database, and a 7-lncRNA signature was identified as a potential prognostic predictor for HBV-related HCC patients. Novel functional studies were provided by our current findings for elucidating the molecular mechanism of lncRNA in HBV-related HCC.

Artificial intelligence in urological oncology: An update and future applications

There continues to be rapid developments and research in the field of Artificial Intelligence (AI) in Urological Oncology worldwide. In this review we discuss the basics of AI, application of AI per tumour group (Renal, Prostate and Bladder Cancer) and application of AI in Robotic Urological Surgery. We also discuss future applications of AI being developed with the benefits to patients with Urological Oncology.

Emerging Biomarkers for Predicting Bladder Cancer Lymph Node Metastasis

Bladder cancer is one of the leading causes of cancer deaths worldwide. Early detection of lymph node metastasis of bladder cancer is essential to improve patients' prognosis and overall survival. Current diagnostic methods are limited, so there is an urgent need for new specific biomarkers. Non-coding RNA and m6A have recently been reported to be abnormally expressed in bladder cancer related to lymph node metastasis. In this review, we tried to summarize the latest knowledge about biomarkers, which predict lymph node metastasis in bladder cancer and their mechanisms. In particular, we paid attention to the impact of non-coding RNA on lymphatic metastasis of bladder cancer and its specific molecular mechanisms, as well as some prediction models based on imaging, pathology, and biomolecules, in an effort to find more accurate diagnostic methods for future clinical application.

Lymphatic metastasis of bladder cancer: Molecular mechanisms, diagnosis and targeted therapy

Bladder cancer is the most common and lethal cancer of the urinary system. Lymphatic metastasis is the primary and main metastatic type of bladder cancer, leading to an extremely poor prognosis in patients. Therefore, a better understanding of molecular mechanisms may provide potential targets for the diagnosis and treatment of lymphatic metastasis in bladder cancer. Herein, we summarize the current knowledge of molecular mechanisms of the lymphatic metastasis in bladder cancer, including lymphangiogenesis and its regulators, noncoding RNAs, and microenvironment-associated molecules. Novel radiomics and genomics approaches have substantially improved the preoperative diagnostic accuracy of lymph node metastasis in patients with bladder cancer. Newly discovered targets may lead to promising therapeutic strategies for clinical intervention in lymphatic metastasis of bladder cancer. More basic and translational studies need to be conducted to further clarify the molecular mechanisms, and identify predictive markers and therapeutic targets of lymphatic metastasis for bladder cancer patients.

Development and Internal Validation of Model Predicting Postoperative Blood Loss Risk Among Children with Pulmonary Atresia Undergoing Cardiopulmonary Bypass

To develop and internally validate nomogram predicting postoperative blood loss risk among pediatric patients with pulmonary atresia (PA) undergoing cardiopulmonary bypass (CPB). All patients aged from 6 months to 6 years with PA who underwent surgery at Fuwai Hospital from June 2015 to December 2019 were selected. And the prediction nomogram model was developed in the training set based on the selected patients. The demographic characteristics and laboratory data from each enrolled patient were gathered. Postoperative blood loss was defined as a blood loss exceeding 20.0 ml/kg within the first 24 postoperative hours. The least absolute shrinkage and selection operator (LASSO) method was used to optimize feature selection for multivariate logistic regression analysis that was applied to build a nomogram composed of all the features selected in the LASSO algorithm. The concordance index (C-index), calibration plot, and decision curve analysis (DCA) were used to evaluate the discrimination, calibration, and clinical net benefit of the nomogarm, respectively. Finally, internal validation was performed using the bootstrap technique. Of the 66 pediatric patients in the training set, 21 (31.82%) and 45 (68.18%) patients were assigned into bleeding group and non-bleeding group, respectively. The first postoperative 24-h blood loss in the bleeding group was significantly higher than that in the non-bleeding group during ICU stay (P = 0.000). Multivariate logistic regression analysis showed that, the immediate postoperative prothrombin time (odds ratio = 1.419, 95% confidence interval: 1.094-1.841, P = 0.008), the immediate postoperative platelet count (odds ratio = 0.985, 95% confidence interval: 0.973-0.997, P = 0.015) and the immediate postoperative red blood cell (RBC) count (odds ratio = 0.335, 95% confidence interval: 0.166-0.667, P = 0.002) were independent predictors of postoperative blood loss risk. The model presented favorable calibration and good discrimination with satisfactory calibration curve and a C-index of 0.858 (95% confidence interval: 0.758-0.958). High C-index value of 0.837 was achieved in the internal validation. The DCA revealed that the nomogram was great clinical effect when intervention was decided among nearly the entire range of threshold probabilities. We developed and internally validated an accurate nomogram to assist in the clinical decision-making concerning the presence of postoperative blood loss in pediatric patients with PA undergoing CPB. However, the nomogram should be endorsed by external validation before it can be recommended for routine practice.

15-lncRNA-Based Classifier-Clinicopathologic Nomogram Improves the Prediction of Recurrence in Patients with Hepatocellular Carcinoma

Background

Our study aims to develop a lncRNA-based classifier and a nomogram incorporating the genomic signature and clinicopathologic factors to help to improve the accuracy of recurrence prediction for hepatocellular carcinoma (HCC) patients.

Methods

The lncRNA profiling data of 374 HCC patients and 50 normal healthy controls were downloaded from The Cancer Genome Atlas (TCGA). Using univariable Cox regression and least absolute shrinkage and selection operator (LASSO) analysis, we developed a 15-lncRNA-based classifier and compared our classifier to the existing six-lncRNA signature. Besides, a nomogram incorporating the genomic classifier and clinicopathologic factors was also developed. The predictive accuracy and discriminative ability of the genomic-clinicopathologic nomogram were determined by a concordance index (C-index) and calibration curve and were compared with the TNM staging system by the C-index and receiver operating characteristic (ROC) analysis. Decision curve analysis (DCA) was performed to estimate the clinical value of our nomogram.

Results

Fifteen relapse-free survival (RFS-) related lncRNAs were identified, and the classifier, consisting of the identified 15 lncRNAs, could effectively classify patients into the high-risk and low-risk subgroups. The prediction accuracy of the 15-lncRNA-based classifier for predicting 2-year and 5-year RFS was 0.791 and 0.834 in the training set and 0.684 and 0.747 in the validation set, respectively, which was better than the existing six-lncRNA signature. Moreover, the AUC of genomic-clinicopathologic nomogram in predicting RFS were 0.837 in the training set and 0.753 in the validation set, and the C-index of the genomic-clinicopathologic nomogram was 0.78 (0.72-0.83) in the training set and 0.71 (0.65-0.76) in the validation set, which was better than the traditional TNM stage and 15-lncRNA-based classifier. The decision curve analysis further demonstrated that our nomogram had a larger net benefit than the TNM stage and 15-lncRNA-based classifier. The results were confirmed externally.

Conclusion

Compared to the TNM stage, the 15-lncRNAs-based classifier-clinicopathologic nomogram is a more effective and valuable tool to identify HCC recurrence and may aid in clinical decision-making.

Quantifying the Overall Survival Benefit With Early Radical Cystectomy for Patients With Histologically Confirmed T1 Non-muscle-invasive Bladder Cancer

INTRODUCTION

The objective of this study was to examine the overall survival (OS) in patients diagnosed with high-grade T1 non-muscle-invasive bladder cancer treated with early radical cystectomy versus local treatment of the primary tumor, defined as endoscopic management with or without intravesical chemotherapy or immunotherapy.

PATIENTS AND METHODS

We identified 4900 patients with histologically confirmed, clinically non-metastatic high-grade T1 bladder cancer undergoing surgical intervention using the National Cancer Database for the period 2010 to 2015. Multivariable logistic regression was used to examine predictors for the receipt of early radical cystectomy (defined as radical cystectomy within 90 days of diagnosis). We then employed multivariable Cox proportional hazards regression models and Kaplan-Meier curves to evaluate the OS according to surgical treatment (early radical cystectomy vs. local treatment).

RESULTS

A minority (23.7%) of patients underwent early radical cystectomy. Independent predictors of undergoing early radical cystectomy included lower age, White race, and lower comorbidity status. The median OS was 74.0 months for patients diagnosed with high-grade T1 bladder cancer. The 1- and 5-year survival rates of patients undergoing early radical cystectomy were 94.8% and 71.0%, whereas they were 85.2% and 52.4%, for patients undergoing initial local treatment, respectively (P < .001). Compared with patients undergoing local treatment, patients undergoing early radical cystectomy had a lower risk of all-cause mortality (hazard ratio, 0.78; 95% confidence interval, 0.67-0.91; P = .002).

CONCLUSION

In this cohort of patients presenting with high-grade T1 non-muscle-invasive bladder cancer, we found that early radical cystectomy was associated with an OS benefit compared with initial local treatment.

A novel genomic-clinicopathologic nomogram to improve prognosis prediction of hepatocellular carcinoma

There is a lack of precise and clinical accessible model to predict the prognosis of hepatocellular carcinoma (HCC) in clinic practice currently. Here, an inclusive nomogram was developed by integrating genomic markers and clinicopathologic factors for predicting the outcome of patients with HCC. A total of 365 samples of HCC were obtained from the Cancer Genome Atlas (TCGA) database. The LASSO analysis was carried out to identify HCC-related mRNAs, and the multivariate Cox regression analysis was used to construct a genomic-clinicopathologic nomogram. As results, 9 mRNAs were finally identified as prognostic indicators, including RGCC, CDH15, XRN2, RAB3IL1, THEM4, PIF1, MANBA, FKTN and GABARAPL1, and used to establish a 9-mRNA classifier. Additionally, an inclusive nomogram was built up by combining the 9-mRNA classifier (P < 0.001) and clinicopathologic factors including age (P = 0.006) and metastasis (P < 0.001) to predict the mortality of HCC patients. Time-dependent receiver operating characteristic, index of concordance and calibration analyses indicated favorable accuracy of the model. Decision curve analysis suggested that appropriate intervention according to the established nomogram will bring net benefit when threshold probability was above 25%. The genomic-clinicopathologic model could be a reliable tool for predicting the mortality, helping determining the individualized treatment and probably improving HCC survival.

Identification of a 13‑mRNA signature for predicting disease progression and prognosis in patients with bladder cancer

There are no reliable criteria to assess risk of progression of non-muscle invasive bladder cancer to muscle invasive bladder cancer. The aim of the present study was to identify potential markers based on gene expression profiling to improve predictive power of disease progression and prognosis in patients with bladder cancer. In the present study, we screened seventy-three differentially expressed genes by analyzing bladder cancer samples with or without progression. Forty-seven prognosis-related genes were screened, 13 of which were identified to build a progression-associated gene signature using the LASSO regression method. Based on this 13-mRNA signature, patients were divided into high- and low-risk groups, with different prognostic outcomes. The gene signature was an independent prognostic factor for overall survival. Receiver operating characteristic analysis suggested that the signature performed well in the validation cohort and its predictive power outperformed other several published signatures. CTHRC1, MMP11, AEBP1, SNCAIP, COL1A1 and S100A8 were identified as hub genes and their expression levels were detected using reverse transcriptase-quantitative polymerase chain reaction. The expression of CTHRC1 was elevated in aggressive bladder cancer compared with non-invasive type, which suggests CTHRC1 may be a valuable biomarker for prediction of prognosis and progression of bladder cancer. Collectively, this 13-mRNA signature may be useful in predicting disease progression and prognosis, thereby contributing to individualized management of patients with bladder cancer.

Communication Of Cancer Cells And Lymphatic Vessels In Cancer: Focus On Bladder Cancer

Bladder cancer is one of the most commonly diagnosed cancers worldwide and causes the highest lifetime treatment costs per patient. Bladder cancer is most likely to metastasize through lymphatic ducts, and once the lymph nodes are involved, the prognosis is poorly and finitely improved by current modalities. The underlying metastatic mechanism for bladder cancer is thus becoming a research focus to date. To identify relevant published data, an online search of the PubMed/Medline archives was performed to locate original articles and review articles regarding lymphangiogenesis and lymphatic metastasis in urinary bladder cancer (UBC), and was limited to articles in English published between 1998 and 2018. A further search of the clinical trials.gov search engine was conducted to identify both trials with results available and those with results not yet available. Herein, we summarized the unique mechanisms and biomarkers involved in the malignant progression of bladder cancer as well as their emerging roles in therapeutics, and that current data suggests that lymphangiogenesis and lymph node invasion are important prognostic factors for UBC. The growing knowledge about their roles in bladder cancers provides the basis for novel therapeutic strategies. In addition, more basic and clinical research needs to be conducted in order to identify further accurate predictive molecules and relevant mechanisms.

Development and Validation of an MRI-Based Radiomics Signature for the Preoperative Prediction of Lymph Node Metastasis in Bladder Cancer

Background

Preoperative lymph node (LN) status is important for the treatment of bladder cancer (BCa). However, a proportion of patients are at high risk for inaccurate clinical nodal staging by current methods. Here, we report an accurate magnetic resonance imaging (MRI)-based radiomics signature for the individual preoperative prediction of LN metastasis in BCa.

Methods

In total, 103 eligible BCa patients were divided into a training set (n = 69) and a validation set (n = 34). And 718 radiomics features were extracted from the cancerous volumes of interest (VOIs) on T2-weighted MRI images. A radiomics signature was constructed using the least absolute shrinkage and selection operator (LASSO) algorithm in the training set, whose performance was assessed and then validated in the validation set. Stratified analyses were also performed. Based on the multivariable logistic regression analysis, a radiomics nomogram was developed incorporating the radiomics signature and selected clinical predictors. Discrimination, calibration and clinical usefulness of the nomogram were assessed.

Findings

Consisting of 9 selected features, the radiomics signature showed a favorable discriminatory ability in the training set with an AUC of 0.9005, which was confirmed in the validation set with an AUC of 0.8447. Encouragingly, the radiomics signature also showed good discrimination in the MRI-reported LN negative (cN0) subgroup (AUC, 0.8406). The nomogram, consisting of the radiomics signature and the MRI-reported LN status, showed good calibration and discrimination in the training and validation sets (AUC, 0.9118 and 0.8902, respectively). The decision curve analysis indicated that the nomogram was clinically useful.

Interpretation

The MRI-based radiomics nomogram has the potential to be used as a non-invasive tool for individualized preoperative prediction of LN metastasis in BCa. External validation is further required prior to clinical implementation.