Chronic inflammation is thought to be the leading cause of colorectal cancer, and interleukin-10 (IL10) has been identified as a potent immunomodulatory cytokine that regulates inflammatory responses in the gastrointestinal tract. Although several single nucleotide polymorphisms (SNPs) in IL10 have been associated with the risk of colorectal cancer, their prognostic significance has not been determined. Two hundred and eighty-two colorectal cancer patients were genotyped for two candidate cancer-associated SNPs in IL10. The associations of these SNPs with distant metastasis-free survival and overall survival were evaluated by Kaplan-Meier analysis and Cox regression model. The minor homozygote GG genotype of IL10 rs3021094 was significantly associated with a 3.30-fold higher risk of death compared with the TT+TG genotypes (P=0.011). The patients with IL10 rs3021094 GG genotype also had a poorer overall survival in Kaplan-Meier analysis (log-rank P=0.007) and in multivariate Cox regression model (P=0.044) adjusting for age, gender, carcinoembryonic antigen levels, tumor differentiation, stage, lymphovascular invasion, and perineural invasion. In conclusion, our results suggest that IL10 rs3021094 might be a valuable prognostic biomarker for colorectal cancer patients.
Aged ; Alleles ; Carcinoembryonic Antigen/blood ; Cell Differentiation ; Colorectal Neoplasms/*genetics/mortality/pathology ; Female ; Genotype ; Homozygote ; Humans ; Interleukin-10/*genetics ; Kaplan-Meier Estimate ; Lymphatic Metastasis ; Male ; Middle Aged ; Neoplasm Staging ; *Polymorphism, Single Nucleotide ; Regression Analysis ; Tumor Markers, Biological/genetics

Background/Aims: Despite the high efficacy of direct-acting antivirals (DAAs), approximately 1–3% of hepatitis C virus (HCV) patients fail to achieve a sustained virological response. We conducted a nationwide study to investigate risk factors associated with DAA treatment failure. Machine-learning algorithms have been applied to discriminate subjects who may fail to respond to DAA therapy. Methods: We analyzed the Taiwan HCV Registry Program database to explore predictors of DAA failure in HCV patients. Fifty-five host and virological features were assessed using multivariate logistic regression, decision tree, random forest, eXtreme Gradient Boosting (XGBoost), and artificial neural network. The primary outcome was undetectable HCV RNA at 12 weeks after the end of treatment. Results: The training (n=23,955) and validation (n=10,346) datasets had similar baseline demographics, with an overall DAA failure rate of 1.6% (n=538). Multivariate logistic regression analysis revealed that liver cirrhosis, hepatocellular carcinoma, poor DAA adherence, and higher hemoglobin A1c were significantly associated with virological failure. XGBoost outperformed the other algorithms and logistic regression models, with an area under the receiver operating characteristic curve of 1.000 in the training dataset and 0.803 in the validation dataset. The top five predictors of treatment failure were HCV RNA, body mass index, α-fetoprotein, platelets, and FIB-4 index. The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the XGBoost model (cutoff value=0.5) were 99.5%, 69.7%, 99.9%, 97.4%, and 99.5%, respectively, for the entire dataset. Conclusions Machine learning algorithms effectively provide risk stratification for DAA failure and additional information on the factors associated with DAA failure.