Value of combined detection of serum carcino-embryonic antigen, carbohydrate antigen 19-9 and cyclooxygenase-2 in the diagnosis of colorectal cancer

Machine learning-based models for the prediction of breast cancer recurrence risk

Breast cancer is the most common malignancy diagnosed in women worldwide. The prevalence and incidence of breast cancer is increasing every year; therefore, early diagnosis along with suitable relapse detection is an important strategy for prognosis improvement. This study aimed to compare different machine algorithms to select the best model for predicting breast cancer recurrence. The prediction model was developed by using eleven different machine learning (ML) algorithms, including logistic regression (LR), random forest (RF), support vector classification (SVC), extreme gradient boosting (XGBoost), gradient boosting decision tree (GBDT), decision tree, multilayer perceptron (MLP), linear discriminant analysis (LDA), adaptive boosting (AdaBoost), Gaussian naive Bayes (GaussianNB), and light gradient boosting machine (LightGBM), to predict breast cancer recurrence. The area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and F1 score were used to evaluate the performance of the prognostic model. Based on performance, the optimal ML was selected, and feature importance was ranked by Shapley Additive Explanation (SHAP) values. Compared to the other 10 algorithms, the results showed that the AdaBoost algorithm had the best prediction performance for successfully predicting breast cancer recurrence and was adopted in the establishment of the prediction model. Moreover, CA125, CEA, Fbg, and tumor diameter were found to be the most important features in our dataset to predict breast cancer recurrence. More importantly, our study is the first to use the SHAP method to improve the interpretability of clinicians to predict the recurrence model of breast cancer based on the AdaBoost algorithm. The AdaBoost algorithm offers a clinical decision support model and successfully identifies the recurrence of breast cancer.

Predictive Value of Preoperative Serum AFP, CEA, and CA19-9 Levels in Patients with Single Small Hepatocellular Carcinoma: Retrospective Study

Purpose

This study aimed to explore the relationship between the tumor marker score (TMS) and the postoperative recurrence of single small hepatocellular carcinoma (HCC).

Patients and Methods

A total of 409 patients with one resectable HCC with a diameter of 3 cm or less who visited Tianjin Medical University Cancer Institute & Hospital from January 2010 to December 2014 were included in this study. Their alpha-fetoprotein (AFP), carcinoembryonic antigen (CEA), and carbohydrate antigen 19-9 (CA19-9) levels were classified into low and high groups using X-tile software. Each patients' TMS was calculated as the sum of each tumor marker (low = 0; high = 1).

Results

A total of 142 patients were classified as TMS0, 171 as TMS1, and 96 as TMS2. Kaplan–Meier analysis illustrated that TMS could divide the patients into groups with remarkably different prognoses, and the patients with high TMS had worse recurrence-free survival (RFS) than those with low TMS. Multivariate analysis showed that TMS, age, and HBeAg positive were the independent predictors of RFS rate. Subgroup analysis revealed that high TMS was a stable risk factor relative to TMS0. Receiver operating curves showed that the 1-, 3-, and 5-year area under curve (AUC) values of TMS were 0.698, 0.662, and 0.673, respectively. The AUC of TMS was higher than that of other common prognostic models in time-dependent receiver operating curve.

Conclusion

TMS was an independent prognostic factor for the postoperative recurrence of a single small HCC and can provide a well-discriminated risk stratification, thus contributing to prognostic prediction and adjuvant therapeutic development.

Efficacy and Safety of Preoperative Radiotherapy Versus Chemoradiotherapy in Advanced Rectal Cancer: A Meta-analysis of Randomized Controlled Trials

OBJECTIVE

This meta-analysis was conducted to evaluate the safety and efficacy of preoperative radiotherapy (RT) combined with surgery and preoperative chemoradiotherapy (CRT) combined with surgery for locally advanced rectal cancer.

METHODS

PubMed, EMBASE and Cochrane Library were searched to collect published randomized controlled trials of preoperative radiotherapy or preoperative CRT combined with surgery for the treatment of locally advanced rectal cancer. Studies were screened according to inclusion and exclusion criteria, and quality was evaluated; RevMan 5.3 software was used for meta-analysis.

RESULTS

In total, 7 related studies involving 3100 patients with locally advanced rectal cancer were evaluated. The pathological complete response rate, negative lymph node rate, R0 resection rate, and incidence of grade III/IV adverse reactions were lower in the RT group than in the CRT group. In the absence of postoperative chemotherapy, the 5-year local recurrence rate of RT was higher than that of CRT, but there was no significant difference between the groups among those who underwent postoperative chemotherapy. Moreover, there was no significant difference between the groups with regard to the 5-year survival rate, anal-preserving rate, or incidence of anastomotic leakage.

CONCLUSION

Preoperative CRT is better than preoperative RT for the treatment of advanced rectal cancer, though the adverse reaction rate is higher.

Identification of hub genes and functional modules in colon adenocarcinoma based on public databases by bioinformatics analysis

Background

Colon adenocarcinoma (COAD) is one of the most common cancers in the world. Although an extensive effort has been made to elucidate its pathogenesis, the underlying molecular mechanisms and genetic characteristics remain elusive.

Methods

In this study, protein-coding transcript expression profiles of COAD were downloaded from the Cancer RNA-Seq Nexus (CRN) database. They were then integrated to identify the overlapping transcripts expressed in every COAD RNA sequencing (RNA-seq) subset. The functional annotation of these overlapping genes (OLGs) involved noting their biological process (BP), cellular components (CC), molecular function (MF) for Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway in the Database for Annotation, Visualization and Integrated Discovery (DAVID). Protein-protein interaction (PPI) networks were then constructed and analyzed using Search Tool for the Retrieval of Interacting Genes/Proteins (STRING) and Cytoscape 3.8.2.

Results

A total of 10 hub genes and 3 functional modules were screened by the plugin cytoHubba and MCODE, respectively. The plugin ClueGO and DAVID were used for the functional enrichment analyses of both hub genes and modules. The expression of hub genes was verified through the gene expression profiling interactive analysis (GEPIA) database. Survival analysis of the hub genes revealed that low expressions of ADCY5, GNG2, and PTPRC were significantly associated with an improved COAD prognosis. Furthermore, the expression level of ADCY5 in stages I/II was lower than that in stages III/IV, which seems to explain why the low expression of ADCY5 results in a better prognosis.

Conclusions

The identification of hub genes, functional modules, and pathways have the potential to improve our understanding of the causes and underlying molecular events of COAD. The hub gene ADCY5 could also be a prognostic monitoring indicator or therapeutic target in the treatment of COAD.

A novel risk stratification for predicting prognosis of colorectal cancer patients with bone metastasis

Background

Our understanding in prognosis of bone metastasis (BM) from colorectal cancer (CRC) is limited. We aimed to establish a clinical risk stratification for individually predicting the survival of CRC patients with BM.

Methods

A total of 200 CRC patients with BM were included in this study. Survival time from BM diagnosis was estimated using the Kaplan-Meier method. The multivariable COX regression model identified the risk factors on cancer specific survival (CSS). Based on weighted scoring system, the stratification model was constructed to classify patients with BM according to prognostic risk. Discrimination power and calibration ability of risk stratification were measured.

Results

The median CSS time was 11 months after BM diagnosis. Lymph node metastasis, Carbohydrate antigen 199 (CA199) levels, bone involvement, Karnofsky Performance Status (KPS) scores, primary tumor resection, bisphosphonates therapy and radiotherapy were identified as predictors of CSS. Four risk groups were stratified according to weighted scoring system, including low risk, medium risk, medium-high risk and high risk group, with 35, 16, 9 and 5 months of median CSS, respectively (P=0.000). The risk stratification displayed good accuracy in predicting CSS, with acceptable discrimination and calibration.

Conclusions

This novel risk stratification predicts CSS in CRC patient with BM using easily accessible clinicopathologic factors, which is recommended for use in individualized clinical decision making in patient with BM.

Identifying Novel Biomarkers Ready for Evaluation in Low-Prevalence Populations for the Early Detection of Lower Gastrointestinal Cancers: A Systematic Review and Meta-Analysis

INTRODUCTION

Lower gastrointestinal (GI) cancers are a major cause of cancer deaths worldwide. Prognosis improves with earlier diagnosis, and non-invasive biomarkers have the potential to aid with early detection. Substantial investment has been made into the development of biomarkers; however, studies are often carried out in specialist settings and few have been evaluated for low-prevalence populations.

METHODS

We aimed to identify novel biomarkers for the detection of lower GI cancers that have the potential to be evaluated for use in primary care. MEDLINE, Embase, Emcare and Web of Science were systematically searched for studies published in English from January 2000 to October 2019. Reference lists of included studies were also assessed. Studies had to report on measures of diagnostic performance for biomarkers (single or in panels) used to detect colorectal or anal cancers. We included all designs and excluded studies with fewer than 50 cases/controls. Data were extracted from published studies on types of biomarkers, populations and outcomes. Narrative synthesis was used, and measures of specificity and sensitivity were meta-analysed where possible.

RESULTS

We identified 142 studies reporting on biomarkers for lower GI cancers, for 24,844 cases and 45,374 controls. A total of 378 unique biomarkers were identified. Heterogeneity of study design, population type and sample source precluded meta-analysis for all markers except methylated septin 9 (mSEPT9) and pyruvate kinase type tumour M2 (TuM2-PK). The estimated sensitivity and specificity of mSEPT9 was 80.6% (95% CI 76.6-84.0%) and 88.0% (95% CI 79.1-93.4%) respectively; TuM2-PK had an estimated sensitivity of 81.6% (95% CI 75.2-86.6%) and specificity of 80.1% (95% CI 76.7-83.0%).

CONCLUSION

Two novel biomarkers (mSEPT9 and TuM2-PK) were identified from the literature with potential for use in lower-prevalence populations. Further research is needed to validate these biomarkers in primary care for screening and assessment of symptomatic patients.

The diagnostic value of PIVKA-II, AFP, AFP-L3, CEA, and their combinations in primary and metastatic hepatocellular carcinoma

BACKGROUND

Early diagnosis decreases the mortality of hepatocellular carcinoma (HCC). We aimed to investigate the usefulness of PIVKA-II, AFP, AFP-L3, CEA, and their combinations in the diagnosis of primary and metastatic HCC.

METHODS

One hundred and twenty patients with primary HCC (PHC), 115 with metastatic HCC (MHC), 89 with chronic liver disease (CLD), and 116 healthy volunteers were included. The diagnostic values of each marker and their combinations for HCC diagnosis were represented by ROC curve analyses.

RESULTS

PIVKA-II, AFP, and AFP-L3 levels in PHC group were higher than that in normal control, CLD, and MHC groups. CEA levels in MHC group were higher than that in the other three groups. When the four markers were analyzed individually, PIVKA-II showed the highest positive rate in PHC group (76.7%) and CEA showed the highest positive rate in MHC group (69.6%). PIVKA- II showed the largest area under ROC curve (AUC = 0.835) to discriminate PHC group from CLD group. Combined PIVKA-II with AFP-L3 increased the AUC to 0.910. CEA showed the highest AUC (0.849) to discriminate MHC group from CLD group. Combined CEA with PIVKA-II increased the AUC to 0.866. AFP-L3 alone showed the highest AUC (0.890) to discriminate MHC group from PHC group. Combined PIVKA-II with AFP-L3, and CEA increased the AUC to 0.957.

CONCLUSION

PIVKA-II, AFP-L3, AFP, and CEA are effective biomarkers for the diagnosis of PHC and MHC. Their combinations could improve the diagnostic performance compared with each marker used alone in detecting PHC and MHC.

Clinical value of detecting IQGAP3, B7-H4 and cyclooxygenase-2 in the diagnosis and prognostic evaluation of colorectal cancer

Background

The IQ-motif-containing GTPase-activating protein (IQGAP) family comprises three members, IQGAP1, IQGAP2 and IQGAP3. IQGAP3 is the latest addition to the family. This study mainly investigated the novel marker IQGAP3 at serum and tumor tissue levels compared with the markers B7-H4 and cyclooxygenase-2 (COX-2) in patients with colorectal cancer (CRC) and in healthy individuals, aiming to evaluate the diagnostic and prognostic value of IQGAP3 for CRC.

Materials and methods

Serum samples were collected prior to any therapy in 118 CRC patients and as part of a routine examination in 85 healthy individuals. Serum IQGAP3, B7-H4 and COX-2 levels were measured using commercially available ELISA kits. Immunohistochemistry was performed to detect the IQGAP3, B7-H4 and COX-2 in tumor tissues and normal para-carcinoma tissues. The receiver operating characteristics (ROC) curve and the area under the curve (AUC) were used to evaluate and compare the diagnostic value of different serum tumor markers. Univariate and multivariate analyses were performed to identify the prognostic risk factors for CRC.

Results

IQGAP3, B7-H4 and COX-2 showed low or high expression in tumor tissues while no expression in normal para-carcinoma tissues. Serum levels of IQGAP3 in CRC group were significantly higher than those in healthy control group (P < 0.001). The IQGAP3 AUC was 0.799, while the B7-H4 AUC was 0.795 and the COX-2 AUC was 0.796. IQGAP3 seemed to be superior to B7-H4 and COX-2 in detecting CRC, with the highest sensitivity among the three markers. Multivariate analysis showed that T stage, N stage, differentiation degree, TNM stage and both serum and tissue IQGAP3, B7-H4 and COX-2 levels were significant prognostic factors for CRC.

Conclusions

IQGAP3 has a better diagnostic efficacy than B7-H4 and COX-2 in detecting CRC and it has value in predicting the prognosis of patients with CRC.

Higher plasma concentration of TP53-induced glycolysis and apoptosis regulator is associated with a lower risk of colorectal cancer metastasis

Purpose

We aimed to explore the association of plasma TP53-induced glycolysis and apoptosis regulator (TIGAR) level with colorectal cancer (CRC) metastasis.

Methods

A cross-sectional study of 126 CRC patients was conducted in Xiamen, China. Multivariable logistic regression was used to calculate adjusted OR and 95% CIs of plasma TIGAR concentration for CRC metastasis in different models with adjustment for potential confounders. Area under the curve (AUC) of receiver operating characteristic (ROC) curve was used to evaluate the diagnostic value.

Results

CRC patients with metastasis showed significantly decreased plasma TIGAR concentration compared to their controls (1.97±0.64 vs 2.49±0.69 ng/mL [log transformed], P=0.002). Higher plasma TIGAR was significantly associated with the decreased risk of CRC metastasis, and the adjusted OR (95% CI) was 0.134 (0.027–0.676, P=0.015) for per SD increase in plasma TIGAR concentration, and the trend test for increasing tertiles showed a negative trend of plasma TIGAR on risk of CRC metastasis (P for trend test: 0.005). Pearson correlation coefficients of plasma TIGAR with other cancer biomarkers (carbohydrate antigen 50 [CA50], carbohydrate antigen 199 [CA199], carbohydrate antigen 125 [CA125], carbohydrate antigen 724 [CA724], carcinoembryonic antigen [CEA], and ferritin [FER]) was low (P>0.05). AUC (95% CI) of ROC curve of plasma TIGAR for CRC metastasis was comparable to the values of cancer biomarkers (all P-values <0.05).

Conclusion

Higher level of plasma TIGAR was significantly and independently associated with lower risk of CRC metastasis, and its prognostic value on CRC metastasis was comparable to the common cancer biomarkers.