Development and validation of a 4-lncRNA combined prediction model for patients with hepatocellular carcinoma.

BACKGROUND: Hepatocellular carcinoma (HCC) is one of the most common and lethal cancers worldwide. Therefore, it is necessary to develop and validate a novel prognostic model for HCC patients.

OBJECTIVES: To establish an innovative and valuable prediction model of long non-coding RNAs (lncRNAs) for HCC.

MATERIAL AND METHODS: Transcriptome and clinical data from The Cancer Genome Atlas (TCGA) were analyzed globally using bioinformatic approaches. We used Cox and least absolute shrinkage and selection operator (LASSO) regression analyses to screen for prognostic lncRNAs, while receiver operating characteristic (ROC) and Kaplan-Meier curve analyses were used to evaluate the effectiveness of the models. Clinical data from our center were used as a validation set.

RESULTS: In the training set, a prediction model was established based on the expression of AP000844.2, LINC00942, SRGAP3-AS2, and AC010280.2 Hepatocellular carcinoma patients were divided into 2 groups (high-risk group and low-risk group) according to their risk score, and differences in survival were compared between the groups. The clinical data from our center served as a validation set to re-evaluate the effectiveness of the predictive model. The model had an excellent performance. The area under the curve (AUC) of 3-year survival was 0.771, while for 5-year survival it was 0.741, and the concordance index (C-index) was 0.756 (standard error (SE) = 0.023, 95% confidence interval (95% CI) = 0.620-0.891).

CONCLUSIONS: The 4-lncRNA combination model is critically important in evaluating the prognosis of HCC. It is an effective independent prognostic factor, although prospective, multi-center studies are needed to validate our findings.