A three-gene novel predictor for improving the prognosis of cervical cancer

A Clinical Decision Support System for Assessing the Risk of Cervical Cancer: Development and Evaluation Study

Background

Cervical cancer has been recognized as a preventable type of cancer. As the assessment of all the risk factors of a disease is challenging for physicians, information technology and risk assessment models have been used to estimate the degree of risk.

Objective

The aim of this study was to develop a clinical decision support system to assess the risk of cervical cancer.

Methods

This study was conducted in 2 phases in 2021. In the first phase of the study, 20 gynecologists completed a questionnaire to determine the essential parameters for assessing the risk of cervical cancer, and the data were analyzed using descriptive statistics. In the second phase of the study, the prototype of the clinical decision support system was developed and evaluated.

Results

The findings revealed that the most important parameters for assessing the risk of cervical cancer consisted of general and specific parameters. In total, the 8 parameters that had the greatest impact on the risk of cervical cancer were selected. After developing the clinical decision support system, it was evaluated and the mean values of sensitivity, specificity, and accuracy were 85.81%, 93.82%, and 91.39%, respectively.

Conclusions

The clinical decision support system developed in this study can facilitate the process of identifying people who are at risk of developing cervical cancer. In addition, it can help to increase the quality of health care and reduce the costs associated with the treatment of cervical cancer.

An immune-associated ten-long noncoding RNA signature for predicting overall survival in cervical cancer

BACKGROUND

Several immune-associated long non-coding RNA (lncRNA) signatures have been reported as prognostic models in different types of cancers; however, the immune-associated lncRNA signature for predicting overall survival (OS) in cervical cancer is unknown.

METHODS

The lncRNA expression profiles and clinical data of cervical cancer were acquired from The Cancer Genome Atlas (TCGA) dataset. Immune-associated genes were extracted from the Molecular Signatures Database (MSigDB), and the immune-associated lncRNAs were extracted for Cox regression analysis. Principal component analysis (PCA) was used to distinguish the high and low risk status of cervical cancer patients. Gene Set Enrichment Analysis (GSEA) was used for functional analyses.

RESULTS

Cox regression analyses and the least absolute shrinkage and selection operator (LASSO) Cox regression model were used to construct an immune-associated ten-lncRNA signature (containing AL021807.1, AL109976.1, LINC02446, MIR4458HG, AC004540.2, AC009065.8, AC083809.1, AC055822.1, AP000904.1, and FBXL19-AS1) for predicting OS in cervical cancer. The signature segregated the cervical cancer patients into 2 groups (high-risk group and low-risk group). The Kaplan-Meier survival curves of AL021807.1, AL109976.1, LINC02446, and MIR4458HG were statistically significant (P<0.05) and the others (including AC004540.2, AC009065.8, AC083809.1, AC055822.1, AP000904.1, and FBXL19-AS1) were not statistically significant (P>0.05). The Kaplan-Meier survival curves of the signature were statistically significant (P=1.134e-10), and the 5-year survival rate was 0.444 in the high-risk group [95% confidence interval (CI): 0.334 to 0.590] and 0.884 in the low-risk group (95% CI: 0.807 to 0.969). The area under curve (AUC) of the receiver operating characteristic (ROC) curve of the signature was 0.833. The concordance index (C-index) of the signature was 0.788 (95% CI: 0.730 to 0.846, P=1.884778e-22). The PCA successfully distinguished the high-risk group and low-risk group based on the signature. The GSEA showed that the signature-related protein coding genes (PCGs) may participate in immunologic biological processes and pathways.

CONCLUSIONS

This study revealed that the immune-associated ten-lncRNA signature is an independent factor for cervical cancer prognosis prediction, providing a bright future for immunotherapy of cervical cancer patients.

Identification of a tumor microenvironment-related gene signature to improve the prediction of cervical cancer prognosis

Background

Previous studies have found that the microenvironment of cervical cancer (CESC) affects the progression and treatment of this disease. Thus, we constructed a multigene model to assess the survival of patients with cervical cancer.

Methods

We scored 307 CESC samples from The Cancer Genome Atlas (TCGA) and divided them into high and low matrix and immune scores using the ESTIMATE algorithm for differential gene analysis. Cervical cancer patients were randomly divided into a training group, testing group and combined group. The multigene signature prognostic model was constructed by Cox analyses. Multivariate Cox analysis was applied to evaluate the significance of the multigene signature for cervical cancer prognosis. Prognosis was assessed by Kaplan–Meier curves comparing the different groups, and the accuracy of the prognostic model was analyzed by receiver operating characteristic-area under the curve (ROC-AUC) analysis and calibration curve. The Tumor Immune Estimation Resource (TIMER) database was used to analyze the relationship between the multigene signature and immune cell infiltration.

Results

We obtained 420 differentially expressed genes in the tumor microenvironment from 307 patients with cervical cancer. A three-gene signature (SLAMF1, CD27, SELL) model related to the tumor microenvironment was constructed to assess patient survival. Kaplan–Meier analysis showed that patients with high risk scores had a poor prognosis. The ROC-AUC value indicated that the model was an accurate predictor of cervical cancer prognosis. Multivariate cox analysis showed the three-gene signature to be an independent risk factor for the prognosis of cervical cancer. A nomogram combining the three-gene signature and clinical features was constructed, and calibration plots showed that the nomogram resulted in an accurate prognosis for patients. The three-gene signature was associated with T stage, M stage and degree of immune infiltration in patients with cervical cancer.

Conclusions

This research suggests that the developed three-gene signature may be applied as a biomarker to predict the prognosis of and personalized therapy for CESC.

Identification of a Transcriptomic Prognostic Signature by Machine Learning Using a Combination of Small Cohorts of Prostate Cancer

Determining which treatment to provide to men with prostate cancer (PCa) is a major challenge for clinicians. Currently, the clinical risk-stratification for PCa is based on clinico-pathological variables such as Gleason grade, stage and prostate specific antigen (PSA) levels. But transcriptomic data have the potential to enable the development of more precise approaches to predict evolution of the disease. However, high quality RNA sequencing (RNA-seq) datasets along with clinical data with long follow-up allowing discovery of biochemical recurrence (BCR) biomarkers are small and rare. In this study, we propose a machine learning approach that is robust to batch effect and enables the discovery of highly predictive signatures despite using small datasets. Gene expression data were extracted from three RNA-Seq datasets cumulating a total of 171 PCa patients. Data were re-analyzed using a unique pipeline to ensure uniformity. Using a machine learning approach, a total of 14 classifiers were tested with various parameters to identify the best model and gene signature to predict BCR. Using a random forest model, we have identified a signature composed of only three genes (JUN, HES4, PPDPF) predicting BCR with better accuracy [74.2%, balanced error rate (BER) = 27%] than the clinico-pathological variables (69.2%, BER = 32%) currently in use to predict PCa evolution. This score is in the range of the studies that predicted BCR in single-cohort with a higher number of patients. We showed that it is possible to merge and analyze different small and heterogeneous datasets altogether to obtain a better signature than if they were analyzed individually, thus reducing the need for very large cohorts. This study demonstrates the feasibility to regroup different small datasets in one larger to identify a predictive genomic signature that would benefit PCa patients.

A Novel Four-Gene Prognostic Signature as a Risk Biomarker in Cervical Cancer

Background

Cervical cancer (CC) is a major malignancy affecting women worldwide, with limited treatment options for patients with advanced disease. The aim of this study was to identify novel prognostic biomarkers for CC.

Methods

RNA-Seq data from four Gene Expression Omnibus datasets (GSE5787, GSE6791, GSE26511, and GSE63514) were used to identify differentially expressed genes (DEGs) between CC and normal cervical tissues. Functional and enrichment analyses of the DEGs were performed using the Search Tool for the Retrieval of Interacting Genes/Proteins (STRING) database and the Database for Annotation, Visualization, and Integrated Discovery (DAVID). The Oncomine database, Cytoscape software, and Kaplan-Meier survival analyses were used for in-depth screening of hub DEGs. The Cox regression was then used to develop a prognostic signature, which was in turn used to create a nomogram.

Results

A total of 207 DEGs were identified in the tissue samples, eight of which were prognostically significant in terms of overall survival (OS). Thereafter, a novel four-gene signature consisting of DSG2, MMP1, SPP1, and MCM2 was developed and validated using stepwise Cox analysis. The area under the receiver operating characteristic (ROC) curve (AUC) values were 0.785, 0.609, and 0.686 in the training, verification, and combination groups, respectively. The protein expression levels of the four genes were well validated by the western blotting. Moreover, the nomogram analysis showed that a combination of this four-gene signature plus lymph node metastasis (LNM) status effectively predicted the 1- and 3-year OS probabilities of CC patients with accuracies of 69.01% and 83.93%, respectively.

Conclusions

We developed a four-gene signature that can accurately predict the prognosis in terms of OS, of CC patients, and could be a valuable tool for designing treatment strategies.