A five-lncRNA model predicting overall survival in gastric cancer compared with normal tissues

Unveiling the secrets of gastrointestinal mucous adenocarcinoma survival after surgery with artificial intelligence: A population-based study

BACKGROUND

Research on gastrointestinal mucosal adenocarcinoma (GMA) is limited and controversial, and there is no reference tool for predicting postoperative survival.

AIM

To investigate the prognosis of GMA and develop predictive model.

METHODS

From the Surveillance, Epidemiology, and End Results database, we collected clinical information on patients with GMA. After random sampling, the patients were divided into the discovery (70% of the total, for model training), validation (20%, for model evaluation), and completely blind test cohorts (10%, for further model evaluation). The main assessment metric was the area under the receiver operating characteristic curve (AUC). All collected clinical features were used for Cox proportional hazard regression analysis to determine factors influencing GMA's prognosis.

RESULTS

This model had an AUC of 0.7433 [95% confidence intervals (95%CI): 0.7424-0.7442] in the discovery cohort, 0.7244 (GMA: 0.7234-0.7254) in the validation cohort, and 0.7388 (95%CI: 0.7378-0.7398) in the test cohort. We packaged it into Windows software for doctors' use and uploaded it. Mucinous gastric adenocarcinoma had the worst prognosis, and these were protective factors of GMA: Regional nodes examined [hazard ratio (HR): 0.98, 95%CI: 0.97-0.98, P < 0.001)] and chemotherapy (HR: 0.62, 95%CI: 0.58-0.66, P < 0.001).

CONCLUSION

The deep learning-based tool developed can accurately predict the overall survival of patients with GMA postoperatively. Combining surgery, chemotherapy, and adequate lymph node dissection during surgery can improve patient outcomes.

Unveiling the secrets of gastrointestinal mucous adenocarcinoma survival after surgery with artificial intelligence: A population-based study

BACKGROUND

Research on gastrointestinal mucosal adenocarcinoma (GMA) is limited and controversial, and there is no reference tool for predicting postoperative survival.

AIM

To investigate the prognosis of GMA and develop predictive model.

METHODS

From the Surveillance, Epidemiology, and End Results database, we collected clinical information on patients with GMA. After random sampling, the patients were divided into the discovery (70% of the total, for model training), validation (20%, for model evaluation), and completely blind test cohorts (10%, for further model evaluation). The main assessment metric was the area under the receiver operating characteristic curve (AUC). All collected clinical features were used for Cox proportional hazard regression analysis to determine factors influencing GMA’s prognosis.

RESULTS

This model had an AUC of 0.7433 [95% confidence intervals (95%CI): 0.7424-0.7442] in the discovery cohort, 0.7244 (GMA: 0.7234-0.7254) in the validation cohort, and 0.7388 (95%CI: 0.7378-0.7398) in the test cohort. We packaged it into Windows software for doctors’ use and uploaded it. Mucinous gastric adenocarcinoma had the worst prognosis, and these were protective factors of GMA: Regional nodes examined [hazard ratio (HR): 0.98, 95%CI: 0.97-0.98, P < 0.001)] and chemotherapy (HR: 0.62, 95%CI: 0.58-0.66, P < 0.001).

CONCLUSION

The deep learning-based tool developed can accurately predict the overall survival of patients with GMA postoperatively. Combining surgery, chemotherapy, and adequate lymph node dissection during surgery can improve patient outcomes.

Emerging role of long non-coding RNA JPX in malignant processes and potential applications in cancers

ABSTRACT

Long non-coding RNAs (lncRNAs) reportedly function as important modulators of gene regulation and malignant processes in the development of human cancers. The lncRNA JPX is a novel molecular switch for X chromosome inactivation and differentially expressed JPX has exhibited certain clinical correlations in several cancers. Notably, JPX participates in cancer growth, metastasis, and chemoresistance, by acting as a competing endogenous RNA for microRNA, interacting with proteins, and regulating some specific signaling pathways. Moreover, JPX may serve as a potential biomarker and therapeutic target for the diagnosis, prognosis, and treatment of cancer. The present article summarizes our current understanding of the structure, expression, and function of JPX in malignant cancer processes and discusses its molecular mechanisms and potential applications in cancer biology and medicine.

Survival nomogram for different grades of gastric cancer patients based on SEER database and external validation cohort

Background

Influencing factors varied among gastric cancer (GC) for different differentiation grades which affect the prognosis accordingly. This study aimed to develop a nomogram to effectively identify the overall survival (OS).

Methods

Totally, 9,568 patients with GC were obtained from the SEER database as the training cohort and internal validation cohort. We then retrospectively enrolled patients diagnosed with GC to construct the external validation cohort from the First Affiliated Hospital of Anhui Medical University. The prognostic factors were integrated into the multivariate Cox regression to construct a nomogram. To test the accuracy of the model, we used the calibration curves, receiver operating characteristics (ROC) curves, C-index, and decision curve analysis (DCA).

Results

Race chemotherapy, tumor size, and other four factors were significantly associated with the prognosis of Grade III GC Patients. On this basis, we developed a nomogram. The discrimination of the nomogram revealed good prognostic accuracy The results of the area under the curve (AUC) calculated by ROC for five-year survival were 0.828 and 0.758 in the training set and external validation cohort, higher than that of the TNM staging system. The calibration plot revealed that the estimated risk was close to the actual risk. DCA also suggested an excellent predictive value of the nomogram. Similar results were obtained in Grade-I and Grade-II GC patients.

Conclusions

The nomogram developed in this study and other findings could help individualize the treatment of GC patients and assist clinicians in their shared decision-making with patients.

N6-methyladenosine-related lncRNAs identified as potential biomarkers for predicting the overall survival of Asian gastric cancer patients

Objective

Gastric cancer (GC) is one of the most prevalent malignant tumors in Asian countries. Studies have proposed that lncRNAs can be used as diagnostic and prognostic indicators of GC due to the high specificity of lncRNAs expression involvement in GC. Recently, N6-methyladenosine (m6A) has also emerged as an important modulator of the expression of lncRNAs in GC. This study aimed at establishing a novel m6A-related lncRNAs prognostic signature that can be used to construct accurate models for predicting the prognosis of GC in the Asian population.

Methods

First, the levels of m6A modification and m6A methyltransferases expression in GC samples were determined using dot blot and western blot analyses. Next, we evaluated the lncRNAs expression profiles and the corresponding clinical data of 88 Asian GC patients retrieved from The Cancer Genome Atlas (TCGA) database. Differential expression of m6A-related lncRNAs between GC and normal tissues was investigated. The relationship between these target lncRNAs and potential immunotherapeutic signatures was also analyzed. Gene set enrichment analysis (GSEA) was performed to identify the malignancy-associated pathways. Univariate Cox regression, LASSO regression, and multivariate Cox regression analyses were performed to establish a novel prognostic m6A-related lncRNAs prognostic signature. Moreover, we constructed a predictive nomogram and determined the expression levels of nine m6A-related lncRNAs in 12 pairs of clinical samples.

Results

We found that m6A methylation levels were significantly increased in GC tumor samples compared to adjacent normal tissues, and the increase was positively correlated with tumor stage. Patients were then divided into two clusters (cluster 1 and cluster 2) based on the differential expression of the m6A-related lncRNAs. Results showed that there was a significant difference in survival probability between the two clusters (p = 0.018). Notably, the low survival rate in cluster 2 may be associated with high expression of immune cells (resting memory CD4⁺ T cells, p = 0.027; regulatory T cells, p = 0.0018; monocytes, p = 0.00095; and resting dendritic cells, p = 0.015), and low expression of immune cells (resting NK cells, p = 0.033; and macrophages M1, p = 0.045). Enrichment analysis indicated that malignancy-associated biological processes were more common in the cluster 2 subgroup. Finally, the risk model comprising of six m6A-related lncRNAs was identified as an independent predictor of prognoses, which could divide patients into high- or low-risk groups. Time-dependent ROC analysis suggested that the risk score could accurately predict the prognosis of GC patients. Patients in the high-risk group had worse outcomes compared to patients in the low-risk group, and the risk score showed a positive correlation with immune cells (resting memory CD4⁺ T cells, R = 0.31, P = 0.038; regulatory T cells, R = 0.42, P = 0.0042; monocytes, R = 0.42, P = 0.0043). However, M1 macrophages (R = -0.37, P = 0.012) and resting NK cells (R = -0.31, P = 0.043) had a negative correlation with risk scores. Furthermore, analysis of clinical samples validated the weak positive correlation between the risk score and tumor stage.

Conclusions

The risk model described here, based on the six m6A-related lncRNAs signature, and may predict the clinical prognoses and immunotherapeutic response in Asian GC patients.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-022-09801-z.