Unknown

Dataset Information

0

An Immune-Related Gene Panel for Preoperative Lymph Node Status Evaluation in Advanced Gastric Cancer.


ABSTRACT: Background and Aim: Gastric cancer (GC) is the common leading cause of cancer-related death worldwide. Immune-related genes (IRGs) may potentially predict lymph node metastasis (LNM). We aimed to develop a preoperative model to predict LNM based on these IRGs. Methods: In this paper, we compared and evaluated three machine learning models to predict LNM based on publicly available gene expression data from TCGA-STAD. The Pearson correlation coefficient (PCC) method was utilized to feature selection according to its relationships with LN status. The performance of the model was assessed using the area under the curve (AUC) and F1 score. Results: The Naive Bayesian model showed better performance and was constructed based on 26 selected gene features, with AUCs of 0.741 in the training set and 0.688 in the test set. The F1 score in the training set and test set was 0.652 and 0.597, respectively. Furthermore, Naive Bayesian model based on 26 IRGs is the first diagnostic tool for the identification of LNM in advanced GC. Conclusion: These results indicate that our new methods have the value of auxiliary diagnosis with promising clinical potential.

SUBMITTER: Yang Y 

PROVIDER: S-EPMC7789469 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

altmetric image

Publications

An Immune-Related Gene Panel for Preoperative Lymph Node Status Evaluation in Advanced Gastric Cancer.

Yang Yuan Y   Zheng Ya Y   Zhang Hongling H   Miao Yandong Y   Wu Guozhi G   Zhou Lingshan L   Wang Haoying H   Ji Rui R   Guo Qinghong Q   Chen Zhaofeng Z   Wang Jiangtao J   Wang Yuping Y   Zhou Yongning Y  

BioMed research international 20201207


<i>Background and Aim</i>: Gastric cancer (GC) is the common leading cause of cancer-related death worldwide. Immune-related genes (IRGs) may potentially predict lymph node metastasis (LNM). We aimed to develop a preoperative model to predict LNM based on these IRGs. <i>Methods</i>: In this paper, we compared and evaluated three machine learning models to predict LNM based on publicly available gene expression data from TCGA-STAD. The Pearson correlation coefficient (PCC) method was utilized to  ...[more]

Similar Datasets

| S-EPMC7233118 | biostudies-literature
| S-EPMC8181876 | biostudies-literature
| S-EPMC6883384 | biostudies-literature
| S-EPMC6011414 | biostudies-literature
| S-EPMC8058421 | biostudies-literature
| S-EPMC7327347 | biostudies-literature
| S-EPMC6691572 | biostudies-literature
| S-EPMC4814744 | biostudies-literature
| S-EPMC4312122 | biostudies-literature
| S-EPMC8066490 | biostudies-literature