LncRNA Prognostic Risk Scoring Model for Gastrointestinal Tumors Based on TCGA Database
10.3971/j.issn.1000-8578.2022.21.1159
- VernacularTitle:基于TCGA数据库的消化道肿瘤LncRNA预后风险评分模型
- Author:
Menghan LI
1
,
2
;
Qiong XIAO
;
Peng GAO
;
Yu FU
;
Chenrui SUN
;
Yongxi SONG
Author Information
1. Department of Surgical Oncology and General Surgery, The First Hospital of China Medical University
2. Key Laboratory of Precision Diagnosis and Treatment of Gastrointestinal Tumors (China Medical University), Ministry of Education, Shenyang 110001, China
- Publication Type:Research Article
- Keywords:
Gastrointestinal neoplasms;
TCGA database;
Prognosis;
Lasso regression
- From:
Cancer Research on Prevention and Treatment
2022;49(6):606-611
- CountryChina
- Language:Chinese
-
Abstract:
Objective To establish a lncRNA prognostic risk model for gastrointestinal tumors based on the TCGA database and evaluate the prognosis of patients. Methods We collected the data of patients with esophageal cancer, gastric cancer, colon cancer and rectal cancer in the TCGA database. Univariate Cox analysis, Lasso and multivariate Cox analysis were performed to construct the prognostic risk scoring model. The model was validated and tested for independence. Time-dependent ROC curve analysis was performed to evaluate the clinical application value of the model. Results We established a prognostic risk model based on 13 lncRNAs. The three-year AUC of the training set and the validation set were 0.746 and 0.704, respectively. The pan-cancer data set was divided into high- and low-risk groups for survival analysis. The 5-year survival rate of the low-risk group was significantly higher than that of the high-risk group; among all cancer types, the five-year survival rates of the low-risk group were higher than those of the high-risk group. Multivariate Cox analysis showed that the risk score could be an independent indicator of prognosis. Conclusion The 13-gene prognostic risk score model is constructed successfully. The risk score obtained by this model can be used as an independent prognostic predictor of the patients with gastrointestinal cancer.
