Dataset Information

Development and validation of a prognostic model based on metabolic risk score to predict overall survival of endometrial cancer in Chinese patients.

ABSTRACT:

Objective

Metabolic syndrome (MetS) is closely related to the increased risk and poor prognosis of endometrial cancer (EC). The purpose of this study was to analyze the relationship between metabolic risk score (MRS) and EC, and establish a predictive model to predict the prognosis of EC.

Methods

A retrospective study was designed of 834 patients admitted between January 2004 to December 2019. Univariate and multivariate Cox analysis were performed to screen independent prognostic factors for overall survival (OS). A predictive nomogram is built based on independent risk factors for OS. Consistency index (C-index), calibration plots and receiver operating characteristic curve were used to evaluate the predictive accuracy of the nomogram.

Results

The patients were randomly divided into training cohort (n=556) and validation cohort (n=278). The MRS of EC patients, ranging from -8 to 15, was calculated. Univariate and multivariate Cox analysis indicated that age, MRS, FIGO stage, and tumor grade were independent risk factors for OS (p<0.05). The Kaplan-Meier analysis demonstrated that EC patients with low score showed a better prognosis in OS. Then, a nomogram was established and validated based on the above four variables. The C-index of nomogram were 0.819 and 0.829 in the training and validation cohorts, respectively. Patients with high-risk score had a worse OS according to the nomogram.

Conclusion

We constructed and validated a prognostic model based on MRS and clinical prognostic factors to predict the OS of EC patients accurately, which may help clinicians personalize prognostic assessments and effective clinical decisions.

SUBMITTER: Li X

PROVIDER: S-EPMC10627753 | biostudies-literature | 2023 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development and validation of a prognostic model based on metabolic risk score to predict overall survival of endometrial cancer in Chinese patients.

Li Xingchen X Yang Xiao X Cheng Yuan Y Dong Yangyang Y Wang Jingyuan J Wang Jianliu J

Journal of gynecologic oncology 20230605 6

<h4>Objective</h4>Metabolic syndrome (MetS) is closely related to the increased risk and poor prognosis of endometrial cancer (EC). The purpose of this study was to analyze the relationship between metabolic risk score (MRS) and EC, and establish a predictive model to predict the prognosis of EC.<h4>Methods</h4>A retrospective study was designed of 834 patients admitted between January 2004 to December 2019. Univariate and multivariate Cox analysis were performed to screen independent prognostic ...[more]

PMID: 37293802

Similar Datasets

Project description:BackgroundThis study aimed to investigate the differences in the clinicopathological characteristics of younger and older patients with endometrial cancer (EC) and develop a nomogram to assess the prognosis of early onset EC in terms of overall survival.MethodsPatients diagnosed with EC from the Surveillance, Epidemiology, and End Results (SEER) database between 2004 and 2015 were selected. Clinicopathological characteristics were compared between younger and older patients, and survival analysis was performed for both groups. Prognostic factors affecting overall survival in young patients with EC were identified using Cox regression. A nomogram was created and internal validation was performed using the consistency index, decision curve analysis, receiver operating characteristic curves, and calibration curves. External validation used data from 70 patients with early onset EC. Finally, Kaplan-Meier curves were plotted to compare survival outcomes across the risk subgroups.ResultsA total of 1042 young patients and 12,991 older patients were included in this study. Younger patients were divided into training (732) and validation (310) cohorts in a 7:3 ratio. Cox regression analysis identified age, tumorsize, grade, FIGO stage(International Federation of Gynecology and Obstetrics) and surgery as independent risk factors for overall survival, and a nomogram was constructed based on these factors. Internal and external validations demonstrated the good predictive power of the nomogram. In particular, the C-index for the overall survival nomogram was 0.832 [95% confidence interval (0.797-0.844)] in the training cohort and 0.839 (0.810-0.868) in the internal validation cohort. The differences in the Kaplan-Meier curves between the different risk subgroups were statistically significant.ConclusionsIn this study, a nomogram for predicting overall survival of patients with early onset endometrial cancer based on the SEER database was developed to help assess the prognosis of patients and guide clinical treatment.

Project description:Recently, growing evidence has revealed the significant effect of reprogrammed metabolism on pancreatic cancer in relation to carcinogenesis, progression, and treatment. However, the prognostic value of metabolism-related genes in pancreatic cancer has not been fully revealed. We identified 379 differentially expressed metabolic-related genes (DEMRGs) by comparing 178 pancreatic cancer tissues with 171 normal pancreatic tissues in The Cancer Genome Atlas (TCGA) and the Genotype-Tissue Expression project (GTEx) databases. Then, we used univariate Cox regression analysis together with Lasso regression for constructing a prognostic model consisting of 15 metabolic genes. The unified risk score formula and cutoff value were taken into account to divide patients into two groups: high risk and low risk, with the former exhibiting a worse prognosis compared with the latter. The external validation results of the International Cancer Genome Consortium (IGCC) cohort and the Gene Expression Omnibus (GEO) cohort further confirm the effectiveness of this prognostic model. As shown in the receiver operating characteristic (ROC) curve, the area under curve (AUC) values of the risk score for overall survival (OS), disease-specific survival (DSS), and progression-free survival (PFS) were 0.871, 0.885, and 0.886, respectively. Based on the Gene Set Enrichment Analysis (GSEA), the 15-gene signature can affect some important biological processes and pathways of pancreatic cancer. In addition, the prognostic model was significantly correlated with the tumor immune microenvironment (immune cell infiltration, and immune checkpoint expression, etc.) and clinicopathological features (pathological stage, lymph node, and metastasis, etc.). We also built a nomogram based on three independent prognostic predictors (including individual neoplasm status, lymph node metastasis, and risk score) for the prediction of 1-, 3-, and 5-year OS of pancreatic cancer, which may help to further improve the treatment strategy of pancreatic cancer.

Project description:BackgroundNumerous deep learning-based survival models are being developed for various diseases, but those that incorporate both deep learning and transfer learning are scarce. Deep learning-based models may not perform optimally in real-world populations due to variations in variables and characteristics. Transfer learning, on the other hand, enables a model developed for one domain to be adapted for a related domain. Our objective was to integrate deep learning and transfer learning to create a multivariable survival model for lung cancer.MethodsWe collected data from 601,480 lung cancer patients in the Surveillance, Epidemiology, and End Results (SEER) database and 4,512 lung cancer patients in the First Affiliated Hospital of Guangzhou Medical University (GYFY) database. The primary model was trained with the SEER database, internally validated with a dataset from SEER, and externally validated through transfer learning with the GYFY database. The performance of the model was compared with a traditional Cox model by C-indexes. We also explored the model's performance in the setting of missing data and generated the artificial intelligence (AI) certainty of the prediction.ResultsThe C-indexes in the training dataset (SEER full sample) with DeepSurv and Cox model were 0.792 (0.791-0.792) and 0.714 (0.713-0.715), respectively. The values were 0.727 (0.704-0.750) and 0.692 (0.666-0.718) after applying the trained model in the test dataset (GYFY). The AI certainty of the DeepSurv model output was from 0.98 to 1. For transfer learning through fine-tuning, the results showed that the test set could achieve a higher C-index (20% vs. 30% fine-tuning data) with more fine-tuning dataset. Besides, the DeepSurv model was more accurate than the traditional Cox model in predicting with missing data, after random data loss of 5%, 10%, 15%, 20%, and median fill-in missing values.ConclusionsThe model outperformed the traditional Cox model, was robust with missing data and provided the AI certainty of prediction. It can be used for patient self-evaluation and risk stratification in clinical trials. Researchers can fine-tune the pre-trained model and integrate their own database to explore other prognostic factors.

Dataset Information

Development and validation of a prognostic model based on metabolic risk score to predict overall survival of endometrial cancer in Chinese patients.

Objective

Methods

Results

Conclusion

Publications

Development and validation of a prognostic model based on metabolic risk score to predict overall survival of endometrial cancer in Chinese patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets