Colorectal cancer is ranked third and fourth in terms of mortality and cancer incidence in the world. While advances in treatment strategies have provided cancer patients with longer survival, potentially harmful second primary cancers can occur. Therefore, second primary colorectal cancer analysis is an important issue with regard to clinical management. In this study, a novel predictive scheme was developed for predicting the risk factors associated with second colorectal cancer in patients with colorectal cancer by integrating five machine learning classification techniques, including support vector machine, random forest, multivariate adaptive regression splines, extreme learning machine, and extreme gradient boosting. A total of 4287 patients in the datasets provided by three hospital tumor registries were used. Our empirical results revealed that this proposed predictive scheme provided promising classification results and the identification of important risk factors for predicting second colorectal cancer based on accuracy, sensitivity, specificity, and area under the curve metrics. Collectively, our clinical findings suggested that the most important risk factors were the combined stage, age at diagnosis, BMI, surgical margins of the primary site, tumor size, sex, regional lymph nodes positive, grade/differentiation, primary site, and drinking behavior. Accordingly, these risk factors should be monitored for the early detection of second primary tumors in order to improve treatment and intervention strategies.

Colorectal cancer (CRC) is the third most common cause of cancer mortality worldwide and the most prevalent cancer in Taiwan. The matrix metalloproteinase (MMP)-11 is a proteolytic enzyme of the MMP family which is involved in extracellular matrix degradation and tissue remodeling. In this study, we focused on the associations of MMP-11 single-nucleotide polymorphisms (SNPs) with CRC susceptibility and clinicopathological characteristics. The MMP-11 SNPs rs131451, rs738791, rs2267029, rs738792, and rs28382575 in 479 controls and 479 patients with CRC were analyzed with real-time polymerase chain reaction. We found that the MMP-11 SNP rs738792 “TC + CC” genotype was significantly associated with perineural invasion in colon cancer patients after controlling for clinical parameters [OR (95% CI) = 1.783 (1.074–2.960); p = 0.025]. The MMP-11 rs131451 “TC + CC” genotypic variants were correlated with greater tumor T status [OR (95% CI):1.254 (1.025–1.534); p = 0.028] and perineural invasion [OR (95% CI):1.773 (1.027–3.062); p = 0.040) in male CRC patients. Furthermore, analyses of The Cancer Genome Atlas (TCGA) revealed that MMP-11 levels were upregulated in colorectal carcinoma tissue compared with normal tissues and were correlated with advanced stage, larger tumor sizes, and lymph node metastasis. Moreover, the data from the Genotype-Tissue Expression (GTEx) database exhibited that the MMP-11 rs738792 “CC” and “CT” genotypic variants have higher MMP-11 expression than the “TT” genotype. In conclusion, our results have demonstrated that the MMP-11 SNPs rs738792 and rs131451 may have potential to provide biomarkers to evaluate CRC disease progression, and the MMP-11 rs131451 polymorphism may shed light on sex discrepancy in CRC development and prognosis.

Colorectal cancer (CRC) is a multifactorial malignancy, and its high incidence and mortality rate remain a global public health burden. Fibroblast growth factor receptor 4 (FGFR4) is a receptor tyrosine kinase that has been shown to play a key role in cancer development and prognosis via the activation of its downstream oncogenic signaling pathways. The present study aimed to explore the impact of FGFR4 gene polymorphisms on the risk and progression of CRC. Three FGFR4 single-nucleotide polymorphisms (SNPs), including rs1966265, rs351855, and rs7708357, were evaluated in 413 CRC cases and 413 gender- and age-matched cancer-free controls. We did not observe any significant association of three individual SNPs with the risk of CRC between the case and control group. However, while assessing the clinicopathological parameters, patients of rectal cancer possessing at least one minor allele of rs1966265 (AG and GG; AOR, 0.236; p = 0.046) or rs351855 (GA and AA; AOR, 0.191; p = 0.022) were found to develop less metastasis as compared to those who are homozygous for the major allele. Further analyses using the datasets from the Genotype-Tissue Expression (GTEx) Portal and The Cancer Genome Atlas (TCGA) revealed that rs351855 regulated FGFR4 expression in many human tissues, and increased FGFR4 levels were associated with the occurrence, advanced stage, and distal metastasis of colon adenocarcinoma. These data suggest that the amino acid change in combination with altered expression levels of FGFR4 due to genetic polymorphisms may affect CRC progression.

Endometrial cancer is one of the most common gynecological malignancies in developed countries. The prevention of the recurrence of endometrial cancer has always been a clinical challenge. Endometrial cancer is asymptomatic in the early stage, and there remains a lack of time-series correlation patterns of clinical pathway transfer, recurrence, and treatment. In this study, the artificial immune system (AIS) combined with bootstrap sampling was compared with other machine learning techniques, which included both supervised and unsupervised learning categories. The back propagation neural network, support vector machine (SVM) with a radial basis function kernel, fuzzy c-means, and ant k-means were compared with the proposed method to verify the sensitivity and specificity of the datasets, and the important factors of recurrent endometrial cancer were predicted. In the unsupervised learning algorithms, the AIS algorithm had the highest accuracy (83.35%), sensitivity (77.35%), and specificity (92.31%); in supervised learning algorithms, the SVM algorithm had the highest accuracy (97.51%), sensitivity (95.02%), and specificity (99.29%). The results of our study showed that histology and chemotherapy are important factors affecting the prediction of recurrence. Finally, behavior code and radiotherapy for recurrent endometrial cancer are important factors for future adjuvant treatment.

Colorectal cancer (CRC) is a prevalent and escalating health issue in Taiwan. This nationwide study delves into the relationship between Human Papillomavirus (HPV) infection and CRC risk, employing population datasets from 2007 to 2017. Cox regression analyses revealed a statistically significant hazard ratio (HR) of 1.73 (95% CI: 1.63–1.83) for CRC in HPV-positive patients, indicating a considerably elevated risk compared to non-infected individuals. Further, stratification by sex showed males with HPV have a higher CRC risk (HR = 1.49, 95% CI: 1.40–1.58) compared to females. Age-related analysis uncovered a progressive increase in CRC risk with advancing age (HR = 34.69 for over 80 years). The study of specific CRC subtypes showed varying risks: HR = 1.74 for the colon, HR = 1.64 for the rectum, and a notably higher HR = 4.72 for the anus. Comorbid conditions such as hypertension (HR = 1.26), diabetes mellitus (HR = 1.32), and abnormal liver function (HR = 1.18) also correlate with significantly increased CRC risks. These findings suggest that HPV is a significant risk factor for CRC, with disparities in risk based on anatomical location, demographic characteristics, and comorbidities, highlighting the need for intervention strategies and targeted prevention.

This study was to identify clinical cancer biomarkers for recurrent gastric cancer survivors using artificial intel-ligence. From a hospital-based cancer registry database in Taiwan, the datasets of the incidence of recurrence and clinical risk features were included in 2476 gastric cancer survivors. We benchmarked Random forest with MLP, C4.5, AdaBoost, and Bagging algorithms on metrics and leveraged synthetic minority oversampling technique (SMOTE) for imbalanced dataset issues, cost-sensitive learning for risk assessment, and SHapley Additive ex-Planations (SHAP) for feature importance analysis in this study. Our proposed Random forest outperformed the other models with an accuracy of 87.9%, a recall rate of 90.5%, an accuracy rate of 86% and F1 of 88.2% on re-current category by a 10-fold cross-validation in a balanced dataset. We identified clinical features of recurrent gastric cancer, which are the top five features, stage, number of regional lymph node involvement, Helicobacter pylori, BMI(body mass index), and gender, which significantly affect the prediction model's output, are worth paying attention to in the following causal effect analysis. Using an artificial intelligence model, the risk factors for recurrent gastric cancer could be identified and cost-effectively ranked according to their feature importance. In addition, they should be crucial clinical features to provide physicians with the knowledge to screen high-risk patients in gastric cancer survivors as well.