A gene-based risk score model for predicting recurrence-free survival in patients with hepatocellular carcinoma

Abstract

Background Hepatocellular carcinoma (HCC) remains the most frequent liver cancer, accounting for approximately 90% of primary liver cancers worldwide. The recurrence-free survival (RFS) of HCC patients is a critical factor in devising a personal treatment plan. Thus, it is necessary to accurately forecast the prognosis of HCC patients in clinical practice. Methods Using The Cancer Genome Atlas (TCGA) dataset, we identified genes associated with RFS. A robust likelihood-based survival modeling approach was used to select the best genes for the prognostic model. Then, the GSE76427 dataset was used to evaluate the prognostic model’s effectiveness. Results We identified 1331 differentially expressed genes associated with RFS. Seven of these genes were selected to generate the prognostic model. The validation in both the TCGA cohort and GEO cohort demonstrated that the 7-gene prognostic model can predict the RFS of HCC patients. Meanwhile, the results of the multivariate Cox regression analysis showed that the 7-gene risk score model could function as an independent prognostic factor. In addition, according to the time-dependent ROC curve, the 7-gene risk score model performed better in predicting the RFS of the training set and the external validation dataset than the classical TNM staging and BCLC. Furthermore, these seven genes were found to be related to the occurrence and development of liver cancer by exploring three other databases. Conclusion Our study identified a seven-gene signature for HCC RFS prediction that can be used as a novel and convenient prognostic tool. These seven genes might be potential target genes for metabolic therapy and the treatment of HCC.

Bioinformatics analysis and experimental validation of a novel autophagy-related signature relevant to immune infiltration for recurrence prediction after curative hepatectomy

“…We then validated the reliability and prediction performance of gene signature in two independent HCC cohorts (TCGA HCC cohort and GSE76427 dataset). Compared with existing signatures, our prognostic model exhibited better performance to predict the RFS of HCC patients [28,29].…”

Identification of a novel lipid metabolism-related gene signature for predicting colorectal cancer survival

“…A total of 21 genes were intersection of those identified by differentially expression analysis and univariate Cox regression analysis. After that, a robust likelihood-based survival modeling approach was used to narrow the number of genes and select the best genes for the prognostic model using “survminer” and “survival” R package ( Wang et al, 2021c ). Finally, a total of 11 genes were screened to construct the risk model by using the multivariate Cox regression analysis with a parameter of “direction = both.” To evaluate the survival risk of patients with CRC, a prognostic risk model was constructed using risk coefficients and gene expression as described in previous studies ( Zhang et al, 2020 ; Liu et al, 2021 ).…”

“…Risk score for the signature was evaluated as following algorithm: Riskscore = Coef gene1 *expression gene1 + Coef gene2 *expression gene2 + Coef gene3 *expression gene3 + ...... + Coef genen *expression genen (where “Coef” and “expression” are respectively the coefficient and RNA relative expression value, “gene” represents each selected gene range from 1 to n) ( Wang et al, 2020b ). Briefly, firstly, a robust likelihood-based survival modeling approach was used to narrow the number of genes from 21 key LMGs and the best genes were selected for the prognostic model using “survminer” and “survival” R package ( Wang et al, 2021c ). Secondly, multiple Cox regression analysis was performed to establish prognostic risk model using “survival” R package with a parameter of “direction = “both” ( Wang et al, 2020b ).…”

The Role of Artificial Intelligence in the Detection and Implementation of Biomarkers for Hepatocellular Carcinoma: Outlook and Opportunities

“…This multivariate analysis suggested that the machine learning risk score (HR = 1.5, p = 0.015), AFP values (HR = 1.74, p = 0.012) and TNM staging (HR = 2.01, p = 0.01 for stage III + IV) were all independent recurrence indicators of HCC. Similar studies have been carried out where multiple gene signatures were created and validated with AI assistance and machine learning algorithms in the hopes of prediction of HCC recurrence [63][64][65].…”