Dataset Information

Deep learning based prediction of prognosis in nonmetastatic clear cell renal cell carcinoma.

ABSTRACT: Survival analyses for malignancies, including renal cell carcinoma (RCC), have primarily been conducted using the Cox proportional hazards (CPH) model. We compared the random survival forest (RSF) and DeepSurv models with the CPH model to predict recurrence-free survival (RFS) and cancer-specific survival (CSS) in non-metastatic clear cell RCC (nm-cRCC) patients. Our cohort included 2139 nm-cRCC patients who underwent curative-intent surgery at six Korean institutions between 2000 and 2014. The data of two largest hospitals' patients were assigned into the training and validation dataset, and the data of the remaining hospitals were assigned into the external validation dataset. The performance of the RSF and DeepSurv models was compared with that of CPH using Harrel's C-index. During the follow-up, recurrence and cancer-specific deaths were recorded in 190 (12.7%) and 108 (7.0%) patients, respectively, in the training-dataset. Harrel's C-indices for RFS in the test-dataset were 0.794, 0.789, and 0.802 for CPH, RSF, and DeepSurv, respectively. Harrel's C-indices for CSS in the test-dataset were 0.831, 0.790, and 0.834 for CPH, RSF, and DeepSurv, respectively. In predicting RFS and CSS in nm-cRCC patients, the performance of DeepSurv was superior to that of CPH and RSF. In no distant time, deep learning-based survival predictions may be useful in RCC patients.

SUBMITTER: Byun SS

PROVIDER: S-EPMC7806580 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning based prediction of prognosis in nonmetastatic clear cell renal cell carcinoma.

Byun Seok-Soo SS Heo Tak Sung TS Choi Jeong Myeong JM Jeong Yeong Seok YS Kim Yu Seop YS Lee Won Ki WK Kim Chulho C

Scientific reports 20210113 1

Survival analyses for malignancies, including renal cell carcinoma (RCC), have primarily been conducted using the Cox proportional hazards (CPH) model. We compared the random survival forest (RSF) and DeepSurv models with the CPH model to predict recurrence-free survival (RFS) and cancer-specific survival (CSS) in non-metastatic clear cell RCC (nm-cRCC) patients. Our cohort included 2139 nm-cRCC patients who underwent curative-intent surgery at six Korean institutions between 2000 and 2014. The ...[more]

PMID: 33441830

Similar Datasets

Project description:Background:Clear cell renal cell carcinoma (ccRCC) comprises the majority of kidney cancer death worldwide, whose incidence and mortality are not promising. Identifying ideal biomarkers to construct a more accurate prognostic model than conventional clinical parameters is crucial. Methods:Raw count of RNA-sequencing data and clinicopathological data were acquired from The Cancer Genome Atlas (TCGA). Tumor samples were divided into two sets. Differentially expressed genes (DEGs) were screened in the whole set and prognosis-related genes were identified from the training set. Their common genes were used in LASSO and best subset regression which were performed to identify the best prognostic 5 genes. The gene-based risk score was developed based on the Cox coefficient of the individual gene. Time-dependent receiver operating characteristic (ROC) and Kaplan-Meier (KM) survival analysis were used to assess its prognostic power. GSE29609 dataset from GEO (Gene Expression Omnibus) database was used to validate the signature. Univariate and multivariate Cox regression were performed to screen independent prognostic parameters to construct a nomogram. The predictive power of the nomogram was revealed by time-dependent ROC curves and the calibration plot and verified in the validation set. Finally, Functional enrichment analysis of DEGs and 5 novel genes were performed to suggest the potential biological pathways. Results:PADI1, ATP6V0D2, DPP6, C9orf135 and PLG were screened to be significantly related to the prognosis of ccRCC patients. The risk score effectively stratified the patients into high-risk group with poor overall survival (OS) based on survival analysis. AJCC-stage, age, recurrence and risk score were regarded as independent prognostic parameters by Cox regression analysis and were used to construct a nomogram. Time-dependent ROC curves showed the nomogram performed best in 1-, 3- and 5-year survival predictions compared with AJCC-stage and risk score in validation sets. The calibration plot showed good agreement of the nomogram between predicted and observed outcomes. Functional enrichment analysis suggested several enriched biological pathways related to cancer. Conclusions:In our study, we constructed a gene-based model integrating clinical prognostic parameters to predict prognosis of ccRCC well, which might provide a reliable prognosis assessment tool for clinician and aid treatment decision-making in the clinic.

Project description:ObjectivesTo predict CTLA4 expression levels and prognosis of clear cell renal cell carcinoma (ccRCC) by constructing a computed tomography-based radiomics model and establishing a nomogram using clinicopathologic factors.MethodsThe clinicopathologic parameters and genomic data were extracted from 493 ccRCC cases of the Cancer Genome Atlas (TCGA)-KIRC database. Univariate and multivariate Cox regression and Kaplan-Meier analysis were performed for prognosis analysis. Cibersortx was applied to evaluate the immune cell composition. Radiomic features were extracted from the TCGA/the Cancer Imaging Archive (TCIA) (n = 102) datasets. The support vector machine (SVM) was employed to establish the radiomics signature for predicting CTLA4 expression. Receiver operating characteristic curve (ROC), decision curve analysis (DCA), and precision-recall curve were utilized to assess the predictive performance of the radiomics signature. Correlations between radiomics score (RS) and selected features were also evaluated. An RS-based nomogram was constructed to predict prognosis.ResultsCTLA4 was significantly overexpressed in ccRCC tissues and was related to lower overall survival. A higher CTLA4 expression was independently linked to the poor prognosis (HR = 1.458, 95% CI 1.13-1.881, p = 0.004). The radiomics model for the prediction of CTLA4 expression levels (AUC = 0.769 in the training set, AUC = 0.724 in the validation set) was established using seven radiomic features. A significant elevation in infiltrating M2 macrophages was observed in the RS high group (p < 0.001). The predictive efficiencies of the RS-based nomogram measured by AUC were 0.826 at 12 months, 0.805 at 36 months, and 0.76 at 60 months.ConclusionsCTLA4 mRNA expression status in ccRCC could be predicted noninvasively using a radiomics model based on nephrographic phase contrast-enhanced CT images. The nomogram established by combining RS and clinicopathologic factors could predict overall survival for ccRCC patients. Our findings may help stratify prognosis of ccRCC patients and identify those who may respond best to ICI-based treatments.

Project description:BackgroundClear cell renal cell carcinoma (ccRCC) is one of the most common types of malignant adult kidney cancer, and its incidence and mortality are not optimistic. It is well known that tumor-related protein markers play an important role in cancer detection, prognosis prediction, or treatment selection, such as carcinoembryonic antigen (CEA), programmed cell death 1 (PD-1), programmed cell death 1 ligand 1 (PD-L1), and cytotoxic T lymphocyte antigen 4 (CTLA-4), so a comprehensive analysis was performed in this study to explore the prognostic value of protein expression in patients with ccRCC.Materials and methodsProtein expression data were obtained from The Cancer Proteome Atlas (TCPA), and clinical information were downloaded from The Cancer Genome Atlas (TCGA). We selected 445 patients with complete information and then separated them into a training set and testing set. We performed univariate, least absolute shrinkage and selection operator (LASSO) Cox analyses to find prognosis-related proteins (PRPs) and constructed a protein signature. Then, we used stratified analysis to fully verify the prognostic significance of the prognostic-related protein signature score (PRPscore). Besides, we also explored the differences in immunotherapy response and immune cell infiltration level in high and low score groups. The consensus clustering analysis was also performed to identify potential cancer subgroups.ResultsFrom the training set, a total of 233 PRPs were selected, and a seven-protein signature was constructed, including ACC1, AR, MAPK, PDK1, PEA15, SYK, and BRAF. Based on the PRPscore, patients could be divided into two groups with significantly different overall survival rates. Univariate and multivariate Cox regression analyses proved that this signature was an independent prognostic factor for patients (P < 0.001). Moreover, the signature showed a high ability to distinguish prognostic outcomes among subgroups, and the low score group had a better prognosis (P < 0.001) and better immunotherapy response (P = 0.003) than the high score group.ConclusionWe constructed a novel protein signature with robust predictive power and high clinical value. This will help to guide the disease management and individualized treatment of ccRCC patients.

Project description:BackgroundClear-cell renal cell carcinoma (ccRCC) is common and associated with substantial mortality. TNM stage and histopathological grading have been the sole determinants of a patient's prognosis for decades and there are few prognostic biomarkers used in clinical routine. Management of ccRCC involves multiple disciplines such as urology, radiology, oncology, and pathology and each of these specialties generates highly complex medical data. Here, artificial intelligence (AI) could prove extremely powerful to extract meaningful information to benefit patients.ObjectiveIn the study, we developed and evaluated a multimodal deep learning model (MMDLM) for prognosis prediction in ccRCC.Design setting and participantsTwo mixed cohorts of non-metastatic and metastatic ccRCC patients were used: (1) The Cancer Genome Atlas cohort including 230 patients and (2) the Mainz cohort including 18 patients with ccRCC. For each of these patients, we trained the MMDLM on multiscale histopathological images, CT/MRI scans, and genomic data from whole exome sequencing.Outcome measurements and statistical analysisOutcome measurements included Harrell's concordance index (C-index) and also various performance parameters for predicting the 5-year survival status (5YSS). Different visualization techniques were used to make our model more transparent.ResultsThe MMDLM showed great performance in predicting the prognosis of ccRCC patients with a mean C-index of 0.7791 and a mean accuracy of 83.43%. Training on a combination of data from different sources yielded significantly better results compared to when only one source was used. Furthermore, the MMDLM's prediction was an independent prognostic factor outperforming other clinical parameters.InterpretationMultimodal deep learning can contribute to prognosis prediction in ccRCC and potentially help to improve the clinical management of this disease.Patient summaryAn AI-based computer program can analyze various medical data (microscopic images, CT/MRI scans, and genomic data) simultaneously and thereby predict the survival time of patients with renal cancer.

Dataset Information

Deep learning based prediction of prognosis in nonmetastatic clear cell renal cell carcinoma.

Publications

Deep learning based prediction of prognosis in nonmetastatic clear cell renal cell carcinoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets