Prediction Of Renal Cell Carcinoma Research Articles

Plasma KIM-1 for preoperative prediction of renal cell carcinoma versus benign renal masses, and association with clinical outcomes.

e16518 Background: For patients with suspicious renal masses, it is often unclear which should receive an intervention versus initial surveillance. Both clear cell and papillary renal cell carcinoma overexpress kidney injury molecule-1 (KIM-1) due to their proximal epithelial cell of origin. We investigated whether plasma KIM-1 improves risk stratification of patients with suspicious kidney masses. Methods: Pre-nephrectomy plasma KIM-1 was measured in two independent cohorts of patients with renal masses. Cohort 1, from the prospective K2 trial, included 162 patients found to have ccRCC (cases) and 162 patients with benign renal masses (controls). Cohort 2 included 247 patients with small (cT1a) renal masses from an academic biorepository. Multivariable models were used to assess the relationship between pre-nephrectomy plasma KIM-1, surgical pathology, and subsequent clinical outcomes. Results: In cohort 1, plasma KIM-1 distinguished RCC versus benign masses with AUC-ROC 0.81 (95% CI: 0.76-0.86). In cohort 2 (cT1a renal masses), plasma KIM-1 distinguished RCC versus benign masses with AUC-ROC 0.74 (95% CI: 0.67 to 0.80). Among patients in cohort 2, the prevalence of malignancy was 97% among patients with the highest quartile of KIM-1 compared to 55% among patients with the lowest quartile of KIM-1. Plasma KIM-1 was higher in clear cell RCC and papillary RCC compared to other histologies (p<0.001 in each cohort). Cohort 1 patients had prospective long-term follow-up, and higher pre-nephrectomy KIM-1 was associated with worse metastasis free survival (multivariable MFS HR 1.29 per unit increase in log KIM-1, 95% CI 1.10-1.53) and worse overall survival (multivariable OS HR 1.31 per unit increase in log KIM-1, 95% CI 1.10-1.54). Conclusions: In two independent cohorts of patients with renal masses, elevated baseline plasma KIM-1 is associated with higher risk of malignant pathology, worse metastasis free survival, and higher risk of death. Plasma KIM-1 may be a useful risk stratification tool for patients with suspicious kidney masses.

A novel nine-microRNA-based model to improve prognosis prediction of renal cell carcinoma

BackgroundWith the improved knowledge of disease biology and the introduction of immune checkpoints, there has been significant progress in treating renal cell carcinoma (RCC) patients. Individual treatment will differ according to risk stratification. As the clinical course varies in RCC, it has developed different predictive models for assessing patient’s individual risk. However, among other prognostic scores, no transparent preference model was given. MicroRNA as a putative marker shown to have prognostic relevance in RCC, molecular analysis may provide an innovative benefit in the prophetic prediction and individual risk assessment. Therefore, this study aimed to establish a prognostic-related microRNA risk score model of RCC and further explore the relationship between the model and the immune microenvironment, immune infiltration, and immune checkpoints. This practical model has the potential to guide individualized surveillance protocols, patient counseling, and individualized treatment decision for RCC patients and facilitate to find more immunotherapy targets.MethodsDownloaded data of RCC from the TCGA database for difference analysis and divided it into a training set and validation set. Then the prognostic genes were screened out by Cox and Lasso regression analysis. Multivariate Cox regression analysis was used to establish a predictive model that divided patients into high-risk and low-risk groups. The ENCORI online website and the results of the RCC difference analysis were used to search for hub genes of miRNA. Estimate package and TIMER database were used to evaluate the relationship between risk score and tumor immune microenvironment (TME) and immune infiltration. Based on Kaplan-Meier survival analysis, search for immune checkpoints related to the prognosis of RCC.ResultsThere were nine miRNAs in the established model, with a concordance index of 0.702 and an area under the ROC curve of 0.701. Nine miRNAs were strongly correlated with the prognosis (P < 0.01), and those with high expression levels had a poor prognosis. We found a common target gene PDGFRA of hsa-miR-6718, hsa-miR-1269b and hsa-miR-374c, and five genes related to ICGs (KIR2DL3, TNFRSF4, LAG3, CD70 and TNFRSF9). The immune/stromal score, immune infiltration, and immune checkpoint genes of RCC were closely related to its prognosis and were positively associated with a risk score.ConclusionsThe established nine-miRNAs prognostic model has the potential to facilitate prognostic prediction. Moreover, this model was closely related to the immune microenvironment, immune infiltration, and immune checkpoint genes of RCC.

Efficacy of Pre-operative 18F-FDG PET/CT in Prognostic Prediction in Patients With Renal Cell Carcinoma

Background/Aim: This study analyzed the parameters provided by preoperative 18F-fluorodeoxyglucose positron emission tomography/computed tomography (FDG-PET/CT) for prognostic prediction of renal cell carcinoma (RCC). Patients and Methods: FDG-PET/CT data from 66 clear cell RCC and 19 non-clear cell RCC cases between January 2015 and October 2018 were reviewed retrospectively. We compared the two groups according to recurrence/metastasis to determine prognosis-influencing factors. Multivariate Cox hazard regression models were constructed to evaluate factors potentially predicting disease-free survival (DFS) after adjustment for confounders. DFS was then compared between groups. Results: Standardized uptake values (SUV) of the PET/CT scan were independent predictors of prognosis after adjusting for confounders. RCC cases were divided into two groups by optimal cut-off values. Differences between DFS percentages in high and low SUV groups were significant. Similar results were obtained in clear cell RCC groups. Conclusion: Increased SUV of the PET/CT scan are significant predictors of worse prognoses in patients with surgically resected RCC.

Overall Survival Prediction in Renal Cell Carcinoma Patients Using Computed Tomography Radiomic and Clinical Information

The aim of this work is to investigate the applicability of radiomic features alone and in combination with clinical information for the prediction of renal cell carcinoma (RCC) patients’ overall survival after partial or radical nephrectomy. Clinical studies of 210 RCC patients from The Cancer Imaging Archive (TCIA) who underwent either partial or radical nephrectomy were included in this study. Regions of interest (ROIs) were manually defined on CT images. A total of 225 radiomic features were extracted and analyzed along with the 59 clinical features. An elastic net penalized Cox regression was used for feature selection. Accelerated failure time (AFT) with the shared frailty model was used to determine the effects of the selected features on the overall survival time. Eleven radiomic and twelve clinical features were selected based on their non-zero coefficients. Tumor grade, tumor malignancy, and pathology t-stage were the most significant predictors of overall survival (OS) among the clinical features (p < 0.002, < 0.02, and < 0.018, respectively). The most significant predictors of OS among the selected radiomic features were flatness, area density, and median (p < 0.02, < 0.02, and < 0.05, respectively). Along with important clinical features, such as tumor heterogeneity and tumor grade, imaging biomarkers such as tumor flatness, area density, and median are significantly correlated with OS of RCC patients.

Prediction of Renal Cell Carcinoma Based on Ensemble Learning Methods

Objective: In recent years, ensemble learning methods have gained widespread use for early diagnosis of cancer diseases. In this study, it is aimed to establish a high-performance ensemble learning model for early diagnosis and classification of renal cell carcinomas.Methods: In the study, hemogram and laboratory data of 140 patients with renal cell carcinoma and 140 patients without renal cell carcinoma were included in the study. The data set includes 27 predictors and 1 dependent variable. The data were obtained retrospectively. In the study, classification performances of machine learning methods and ensemble learning methods were compared. In the study, classification performances of boosting, bagging, voting and stacking ensemble learning methods as well as IB1, IBk, Kstar, LWL, REPTree, Random Forest and SMO classifiers were compared.Results: REPTree classifier provided the highest performance among machine learning methods (Accuracy = 0.867). Among the ensemble learning methods, the Stacking ensemble learning method provided the highest performance in Model 6 (Accuracy = 0.906). Stacking ensemble learning methods performed higher than boosting, voting, bagging ensemble methods and machine learning methods.Conclusion: Stacking ensemble learning methods provide successful results in the early diagnosis of renal cell carcinomas. Stacking ensemble learning methods can be used as an alternative to existing methods for diagnosing renal cell carcinoma. In order to further increase the classification performance of the stacking ensemble learning method, it is recommended to choose a meta classifier suitable for the data set and variable types.

Spontaneous perirenal hemorrhage (Wunderlich syndrome): An analysis of 28 cases

IntroductionThis study aimed to analyze the characteristics, etiology, and treatment of a series of patients with spontaneous perirenal hemorrhage (Wunderlich syndrome [WS]). MethodsWe retrospectively reviewed the records of 26 patients hospitalized for WS in a tertiary urological center between 2011 and 2018. All patients were evaluated for perirenal hemorrhage observed on computed tomography (CT) in the emergency department. Clinical variables (age, underlying diseases, symptoms, shock, and hospitalization period), laboratory test results, and radiological and pathological results were reviewed. ResultsThe series included 28 events from 26 patients with a mean follow-up period of 20.2 ± 18.0 months. Flank pain was most common symptoms (92%). Twelve patients (46%) had visible renal lesions and associated hematoma and 14 only showed perirenal hematoma. In six patients with shock (systolic blood pressure < 90 mm Hg), 2 underwent emergency angioembolization. Twelve patients (46%) underwent exploration and total nephrectomy. In the final diagnosis, 4 cases of renal cell carcinoma, 3 of angiomyolipoma, 4 of simple renal cyst, 2 of acquired cystic kidney disease, 4 of sarcoma or other malignancy, 4 of chronic pyelonephritis, and 5 of idiopathic WS were observed. Patient age was associated with prediction of renal cell carcinoma in the patients with WS. ConclusionRenal masses are the main cause of WS, and CT is the diagnostic procedure of choice. Old age is a possible risk factor for renal cell carcinoma in etiology of WS. Surgical treatment is preferred in patients diagnosed with renal malignancy and in cases of hemodynamic instability.

Differentiating papillary type I RCC from clear cell RCC and oncocytoma: application of whole-lesion volumetric ADC measurement

To determine whether objective volumetric whole-lesion apparent diffusion coefficient (ADC) distribution analysis improves upon the capabilities of conventional subjective small region-of-interest (ROI) ADC measurements for prediction of renal cell carcinoma (RCC) subtype. This IRB-approved study retrospectively enrolled 55 patients (152 tumors). Diffusion-weighted imaging DWI was acquired at b values of 0, 250, and 800s/mm2 on a 1.5T system (Aera, Siemens Healthcare). Whole-lesion measurements were performed by a research fellow and reviewed by a fellowship-trained radiologist. Mean, median, skewness, kurtosis, and every 5th percentile ADCs were determined from the whole-lesion histogram. Linear mixed models that accounted for within-subject correlation of lesions were used to compare ADCs among RCC subtypes. Receiver-operating characteristic (ROC) curve analysis with optimal cutoff points from the Youden index was used to test the ability of ADCs to differentiate clear cell RCC (ccRCC), papillary RCC (pRCC), and oncocytoma subtypes. Whole-lesion ADC values were significantly different between pRCC and ccRCC, and between pRCC and oncocytoma, demonstrating strong ability to differentiate subtypes across the quantiles (both P<0.001). Best percentile ROC analysis demonstrated AUC values of 95.2 for ccRCC vs. pRCC; 67.6 for oncocytoma vs. ccRCC; and 95.8 for oncocytoma vs. pRCC. Best percentile ROC analysis further indicated model sensitivities/specificities of 84.5%/93.1% for ccRCC vs. pRCC; 100.0%/10.3% for oncocytoma vs. ccRCC; and 88.5%/93.1% for oncocytoma vs. pRCC. The objective methodology of whole-lesion volumetric ADC measurements maintains the sensitivity/specificity of conventional expert-based ROI analysis, provides information on lesion heterogeneity, and reduces observer bias.

Expression and clinical significance of RCDG1 in renal cell carcinoma: a novel renal cancer‑associated gene.

Recently identified molecular tumor markers have numerous potential applications in the diagnosis, therapy and prognostic prediction of renal cell carcinoma (RCC). Through bioinformatics‑based screening approaches together with validation of western blot and immunohistochemical data, the present study identified a novel renal cancer‑associated gene, preliminarily named Renal Cancer Differentiation Gene 1 (RCDG1), originally known as chromosome 4 open reading frame 46 (C4orf46). RCDG1 expression was evaluated by western blot analysis of RCC and adjacent normal tissues, renal cancer cell lines and normal kidney HEK293T cells. Additionally, RCDG1 expression was assessed in 124 RCC paraffin sections, including 92 paired adjacent normal tissues, by immunohistochemistry. The results showed that RCDG1 was significantly downregulated in RCC tissues as compared with normal adjacent tissues (P<0.001), and the expression of RCDG1 in clear cell (cc) RCC tissues was significantly lower as compared with that of non‑ccRCC tissues (P=0.005). Furthermore, statistical analysis revealed RCDG1 expression was negatively correlated with the Fuhrman grade in ccRCC (P=0.008). A reduction in RCDG1 expression may be associated with the oncogenesis of RCC and the differentiation of ccRCC. Further studies may provide more information about the function of RCDG1 gene in RCC.

Value of microRNAs in molecular typing, diagnosis, and prognosis prediction of renal cell carcinoma: recent progress

Value of microRNAs in molecular typing, diagnosis, and prognosis prediction of renal cell carcinoma: recent progress

Balanced Gradient Boosting from Imbalanced Data for Clinical Outcome Prediction

In clinical outcome prediction, such as disease diagnosis and prognosis, it is often assumed that the class, e.g., disease and control, is equally distributed. However, in practice we often encounter biological or clinical data whose class distribution is highly skewed. Since standard supervised learning algorithms intend to maximize the overall prediction accuracy, a prediction model tends to show a strong bias toward the majority class when it is trained on such imbalanced data. Therefore, the class distribution should be incorporated appropriately to learn from imbalanced data. To address this practically important problem, we proposed balanced gradient boosting (BalaBoost) which reformulates gradient boosting to avoid the overfitting to the majority class and is sensitive to the minority class by making use of the equal class distribution instead of the empirical class distribution. We applied BalaBoost to cancer tissue diagnosis based on miRNA expression data, premature death prediction for diabetes patients based on biochemical and clinical variables and tumor grade prediction of renal cell carcinoma based on tumor marker expressions whose class distribution is highly skewed. Experimental results showed that BalaBoost outperformed the representative supervised learning algorithms, i.e., gradient boosting, Random Forests and Support Vector Machine. Our results led us to the conclusion that BalaBoost is promising for clinical outcome prediction from imbalanced data.