Predictive Nomogram and Risk Factors for 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.

Squamous cell carcinoma of the bladder: Demographics and outcomes associated with surgery and radiotherapy

BACKGROUND AND OBJECTIVES

Squamous cell carcinoma of the bladder (SCCB) is a rare disease composing 2%-5% of all bladder cancers with no consensus regarding treatment. The present study aims to analyze the outcomes of established treatments, namely chemotherapy, radiation, and surgery, to guide clinical decision-making for patients with non-schistosomal SCCB.

METHODS

Patients with bladder SCC diagnosed between 2000 and 2018 were reviewed utilizing data from the Surveillance, Epidemiology, and End Results Registry (SEER) program.

RESULTS

A total of 5653 patients with SCCB were identified; median survival was 13 months and was significantly decreased in patients treated with chemotherapy or radiation (median survival of 9 or 12 months, respectively). Patients treated with both surgery and radiotherapy saw a decreased 5 year overall survival (OS) of 14%, compared to 35% for those treated with surgery alone (p < 0.01). Furthermore, patients treated with surgery, chemotherapy, and radiotherapy saw a decreased 5 year OS of 20%, compared with 25% for those that received surgery and chemotherapy only (p < 0.01). Finally, surgical intervention provided an increased 5 year OS for patients with locoregional disease only; those with distant disease saw no increase in 5 year OS (p < 0.01).

CONCLUSIONS

Based on this study's analysis, radical surgery may be the most effective treatment for this disease.

Preoperative CT-based deep learning radiomics model to predict lymph node metastasis and patient prognosis in bladder cancer: a two-center study

OBJECTIVE

To establish a model for predicting lymph node metastasis in bladder cancer (BCa) patients.

METHODS

We retroactively enrolled 239 patients who underwent three-phase CT and resection for BCa in two centers (training set, n = 185; external test set, n = 54). We reviewed the clinical characteristics and CT features to identify significant predictors to construct a clinical model. We extracted the hand-crafted radiomics features and deep learning features of the lesions. We used the Minimum Redundancy Maximum Relevance algorithm and the least absolute shrinkage and selection operator logistic regression algorithm to screen features. We used nine classifiers to establish the radiomics machine learning signatures. To compensate for the uneven distribution of the data, we used the synthetic minority over-sampling technique to retrain each machine-learning classifier. We constructed the combined model using the top-performing radiomics signature and clinical model, and finally presented as a nomogram. We evaluated the combined model's performance using the area under the receiver operating characteristic, accuracy, calibration curves, and decision curve analysis. We used the Kaplan-Meier survival curve to analyze the prognosis of BCa patients.

RESULTS

The combined model incorporating radiomics signature and clinical model achieved an area under the receiver operating characteristic of 0.834 (95% CI: 0.659-1.000) for the external test set. The calibration curves and decision curve analysis demonstrated exceptional calibration and promising clinical use. The combined model showed good risk stratification performance for progression-free survival.

CONCLUSION

The proposed CT-based combined model is effective and reliable for predicting lymph node status of BCa patients preoperatively.

CRITICAL RELEVANCE STATEMENT

Bladder cancer is a type of urogenital cancer that has a high morbidity and mortality rate. Lymph node metastasis is an independent risk factor for death in bladder cancer patients. This study aimed to investigate the performance of a deep learning radiomics model for preoperatively predicting lymph node metastasis in bladder cancer patients.

KEY POINTS

• Conventional imaging is not sufficiently accurate to determine lymph node status. • Deep learning radiomics model accurately predicted bladder cancer lymph node metastasis. • The proposed method showed satisfactory patient risk stratification for progression-free survival.

Application of machine learning algorithms to predict lymph node metastasis in gastric neuroendocrine neoplasms

Background

Neuroendocrine neoplasms (NENs) are tumors that originate from secretory cells of the diffuse endocrine system and typically produce bioactive amines or peptide hormones. This paper describes the development and validation of a predictive model of the risk of lymph node metastasis among gastric NEN patients based on machine learning platform.

Methods

In this investigation, data from 1256 patients were used, of whom 119 patients from the First Affiliated Hospital of Soochow University in China and 1137 cases from the surveillance epidemiology and end results (SEER) database were combined. Six machine learning algorithms, including the logistic regression model (LR), random forest (RF), decision tree (DT), Naive Bayes (NB), support vector machine (SVM), and k-nearest neighbor algorithm (KNN), were used to build the predictive model. The performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity.

Results

Among the 1256 patients with gastric NENs, 276 patients (21.97 %) developed lymph node metastasis. T stage, tumor size, degree of differentiation, and sex were predictive factors of lymph node metastasis. The RF model achieved the best predictive performance among the six machine learning models, with an AUC, accuracy, sensitivity, and specificity of 0.81, 0.78, 0.76, and 0.82, respectively.

Conclusion

The RF model provided the best prediction and can help physicians determine the lymph node metastasis risk of gastric NEN patients to formulate individualized medical strategies.

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.

Clinical characteristics of bloodstream infections in adult patients with solid tumours and a nomogram for mortality prediction: a 5-year case-controlled retrospective study in a tertiary-level hospital

Background

Bloodstream infections (BSIs) are one of the leading causes of death in cancer patients. Nevertheless, the risk factors of BSIs in solid tumors have rarely been ascertained adequately.

Methods

We conducted a single-center case-controlled retrospective study from 2017 to 2021 among adults with solid tumors in a tertiary-level hospital. The BSIs and control group were matched by the propensity score matching method. We found independent risk factors of occurrence and death of BSIs using univariate and multivariate regression analysis. Additionally, a nomogram was constructed to predict the risk of mortality in BSIs.

Results

Of 602 patients with solid tumors in the study period, 186 had BSIs and 416 had non-BSIs. The incidence of BSIs was 2.0/1,000 admissions (206/102,704), and the 30-day mortality rate was 18.8% (35/186). Compared to the control group, the BSIs had longer hospital stays (24.5 days vs. 20.0 days), and higher frequency complicating with organ failure (10.5% vs. 2.4%), nephropathy (19.6% vs. 3.8%), comorbidities≥3 (35.5% vs. 20.0%), and liver-biliary-pancreatic infections (15.6% vs. 5.3%) (all P<0.001). Among the 186 patients with BSIs, 35 died within 30 days after BSIs. Gram-negative bacteria were the most frequent microorganisms (124/192, 64.6%). Liver cancer, organ failure, a high level of lactate dehydrogenase and septic shock were the independent hazardous factors for death of BSIs. What's more, a nomogram was constructed to predict the 30-day survival rate of BSIs, which was proved to have good accuracy (AUC: 0.854; 95% confidence interval: 0.785~0923) and consistency.

Conclusion

Being aware of the risk factors of BSIs redounds to take preventive measures to reduce the incidence and death of BSIs.

The Impact of the Initial Clinical Presentation of Bladder Cancer on Histopathological and Morphological Tumor Characteristics

This study investigated the impact of the initial clinical presentation of bladder cancer on tumor characteristics. A cross-sectional, retrospective study was performed, and it involved 515 patients who underwent transurethral bladder cancer resection at the University Hospital Center Split between April 2019 and April 2023, excluding recurrent cases. The association between symptomatic versus asymptomatic presentation and bladder cancer characteristics was analyzed. A subgroup analysis compared tumor characteristics between patients with gross and microscopic hematuria. Multiple regression analyses revealed a significant association between symptomatic presentation and the detection of high-grade bladder cancer (OR 3.43, 95% CI 2.22-5.29, p < 0.001), concomitant CIS (OR 3.41, 95% CI 1.31-8.88, p = 0.012), T2 stage bladder cancer (OR 5.79, 95% CI 2.45-13.71, p < 0.001), a higher number of tumors (IRR 1.24, 95% CI 1.07-1.45, p = 0.005), and larger tumor size (B 1.68, 95% CI 1.19-2.18, p < 0.001). In the subgroup analysis, gross hematuria was associated with the detection of high-grade bladder cancer (OR 2.07, 95% CI 1.12-3.84, p = 0.020), T2 stage bladder cancer (OR 6.03, 95% CI 1.42-25.49, p = 0.015), and larger tumor size (B 1.8, 95% CI 0.99-2.6, p < 0.001). The identified associations between symptomatic presentation and unfavorable bladder cancer characteristics, likely attributed to early detection in asymptomatic cases, underscore the importance of additional research in the development of bladder cancer screening strategies.

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.

Surveillance of prognostic risk factors in patients with SCCB using artificial intelligence: a retrospective study

Small cell carcinoma of the bladder (SCCB) is a rare urological tumor. The prognosis of SCCB is abysmal. Therefore, this study aimed to construct nomograms that predict overall survival (OS) and cancer-specific survival (CSS) in SCCB patients. Information on patients diagnosed with SCCB during 2004-2018 was obtained from the Surveillance, Epidemiology, and End Results (SEER) database. Univariate and multivariate Cox regression models analyzed Independent risk factors affecting patients' OS and CSS. Nomograms predicting the OS and CSS were constructed based on the multivariate Cox regression model results. The calibration curve verified the accuracy and reliability of the nomograms, the concordance index (C-index), and the area under the curve (AUC). Decision curve analysis (DCA) assessed the potential clinical value. 975 patients were included in the training set (N = 687) and the validation set (N = 288). Multivariate COX regression models showed that age, marital status, AJCC stage, T stage, M stage, surgical approach, chemotherapy, tumor size, and lung metastasis were independent risk factors affecting the patients' OS. However, distant lymph node metastasis instead AJCC stage is the independent risk factor affecting the CSS in the patients. We successfully constructed nomograms that predict the OS and CSS for SCCB patients. The C index of the training set and the validation set of the OS were 0.747 (95% CI 0.725-0.769) and 0.765 (95% CI 0.736-0.794), respectively. The C index of the CSS were 0.749 (95% CI 0.710-0.773) and 0.786 (95% CI 0.755-0.817), respectively, indicating that the predictive models of the nomograms have excellent discriminative power. The calibration curve and the AUC also show good accuracy and discrimination of the nomograms. To sum up, We established nomograms to predict the OS and CSS of SCCB patients. The nomograms have undergone internal cross-validation and show good accuracy and reliability. The DCA shows that the nomograms have an excellent clinical value that can help doctors make clinical-assisted decision-making.

New nomogram for predicting lymph node positivity in pancreatic head cancer

Background

Pancreatic cancer is one of the most malignant cancers worldwide, and it mostly occurs in the head of the pancreas. Existing laparoscopic pancreaticoduodenectomy (LPD) surgical techniques have has undergone a learning curve, a wide variety of approaches for the treatment of pancreatic cancer have been proposed, and the operation has matured. At present, pancreatic head cancer has been gradually changing from "surgeons' evaluation of anatomical resection" to "biologically inappropriate resection". In this study, the risk of lymph node metastasis in pancreatic head cancer was predicted using common preoperative clinical indicators.

Methods

The preoperative clinical data of 191 patients with pancreatic head cancer who received LPD in the First Affiliated Hospital of Jilin University from May 2016 to December 2021 were obtained. A univariate regression analysis study was conducted, and the indicators with a significance level of P<0.05 were included in the univariate logistic regression analysis into multivariate. Lastly, a nomogram was built based on age, tumor size, leucocyte,albumin(ALB), and lymphocytes/monocytes(LMR). The model with the highest resolution was selected by obtaining the area under a curve. The clinical net benefit of the prediction model was examined using decision curve analyses.Risk stratification was performed by combining preoperative CT scan with existing models.

Results

Multivariate logistic regression analysis found age, tumor size, WBC, ALB, and LMR as five independent factors. A nomogram model was constructed based on the above indicators. The model was calibrated by validating the calibration curve within 1000 bootstrap resamples. The ROC curve achieved an AUC of 0.745(confidence interval of 95%: 0.673-0.816), thus indicating that the model had excellent discriminative skills. DCA suggested that the predictive model achieved a high net benefit in the nearly entire threshold probability range.

Conclusions

This study has been the first to investigate a nomogram for preoperative prediction of lymphatic metastasis in pancreatic head cancer. The result suggests that age, ALB, tumor size, WBC, and LMR are independent risk factors for lymph node metastasis in pancreatic head cancer. This study may provide a novel perspective for the selection of appropriate continuous treatment regimens, the increase of the survival rate of patients with pancreatic head cancer, and the selection of appropriate neoadjuvant therapy patients.

Multidisciplinary Management and Radiotherapy Recommendations for Clinically and Pathologically Node-positive Bladder Cancer

There are limited data regarding the optimal management of patients with pelvic node-positive, but non-metastatic, bladder cancer. Increasing data demonstrate that this is a distinct clinical entity with outcomes bridging between bladder-confined muscle-invasive bladder cancer and metastatic advanced bladder cancer. Guidelines and staging systems have formalized the need to incorporate the unique considerations of management of pelvic node-positive bladder cancer. However, there remains an absence of a definite standard of care. Treatment options include systemic therapy alone, neoadjuvant chemotherapy followed by radical cystectomy, or bladder-preserving trimodality therapy. Furthermore, ongoing studies aim to determine the benefit of incorporating immunotherapy into these treatment paradigms. In this review article, we will discuss the key considerations for management of patients with pelvic node-positive bladder cancer.

Constructing and validating nomograms to predict risk and prognostic factors of distant metastasis in urothelial bladder cancer patients: a population-based retrospective study

BACKGROUND

Urothelial carcinoma is the most common type of bladder cancer worldwide and it has a poor prognosis for patients with distant metastasis. Nomograms are frequently used in clinical research, but no research has evaluated the diagnostic and prognostic factors of distant metastasis in urothelial bladder cancer (UBC).

METHODS

The Surveillance, Epidemiology, and End Results database was used to analyze all patients diagnosed with UBC between 2000 and 2017. Lasso regression was used to identify the potential risk predictive factors for distant metastasis in UBC. Univariate and multivariate Cox proportional hazard regression analyses were performed to determine independent prognostic factors for distant metastasis urothelial bladder cancer (DMUBC). Subsequently, two nomograms were constructed based on the above models. The receiver operating characteristic (ROC), and calibration curves were performed to evaluate the two nomograms.

RESULTS

The study included 73,264 patients with UBC, with 2,129 (2.9%) having distant metastasis at the time of diagnosis. In the diagnostic model, tumor size, histologic type, and stage N and T were all important risk predictive factors for distant metastasis of UBC. In the prognostic model, age, tumor size, surgery, and chemotherapy were independent factors affecting the prognosis of DMUBC. DCA, ROC, calibration, and Kaplan-Meier (K-M) survival curves reveal that the two nomograms can effectively predict the diagnosis and prognosis of DMUBC.

CONCLUSION

The developed nomograms are practical methods for predicting the occurrence risk and prognosis of distant metastasis urothelial bladder cancer patients, which may benefit the clinical decision-making process.

Management of Bladder Cancer Patients with Clinical Evidence of Lymph Node Invasion (cN+)

The purpose of this review is to present the current knowledge about the diagnostic and treatment options for bladder cancer (BCa) patients with clinically positive lymph nodes (cN+). This review shows compaction of CT and MRI performance in preoperative prediction of lymph node invasion (LNI) in BCa patients, along with other diagnostic methods. Most scientific societies do not distinguish cN+ patients in their guidelines; recommendations concern muscle-invasive bladder cancer (MIBC) and differ between associations. The curative treatment that provides the best long-term survival in cN+ patients is a multimodal approach, with a combination of neoadjuvant chemotherapy (NAC) and radical cystectomy (RC) with extended pelvic lymph node dissection (ePLND). The role of adjuvant chemotherapy (AC) remains uncertain; however, emerging evidence indicates comparable outcomes to NAC. Therefore, in cN+ patients who have not received NAC, AC should be implemented. The response to ChT is a crucial prognostic factor for cN+ patients. Recent studies demonstrated the growing importance of immunotherapy, especially in ChT-ineligible patients. Moreover, immunotherapy can be suitable as adjuvant therapy in selected cases. In cN+ patients, the extended template of PLND should be utilized, with the total resected node count being less important than the template. This review is intended to draw special attention to cN+ BCa patients, as the oncological outcomes are significantly worse for this group.