RESUMO
Given the relatively poor understanding of the expression and functional effects of the N6-methyladenosine (m6A) RNA methylation on colorectal cancer (CRC), we attempted to measure its prognostic value and clinical significance. We comprehensively screened 37 m6A-related prognostic long non-coding RNAs (lncRNAs) with significant differences in expression based on 21 acknowledged regulators of m6A modification and data on 473 colorectal cancer tissues and 41 para-cancer tissues obtained from the TCGA database. Accordingly, we classified 473 CRC patients into two clusters by consensus clustering on the basis of significantly different survival outcomes. We also found a potential correlation between m6A-related prognostic lncRNAs and BRAF-KRAS expression, as well as immune cell infiltration. Then, we established a prognostic model by selecting 16 m6A-related prognostic lncRNAs via LASSO Cox analysis and grouped the CRC patients into low- and high-risk groups to calculate risk scores. Then, we performed stratified sampling to validate and confirm our model by categorising the 473 samples into a training group (N = 208) and a testing group (N = 205) in a 1:1 ratio. The survival curve showed a distinct clinical outcome in the low- and high-risk subgroups. We reconfirmed the reliability and independence of the prognostic model through various measures: risk curve, heat map and univariate and multivariate Cox analyses. To ensure that the outcomes were applicable to clinical settings, we performed stratified analyses on different clinical features, such as age, lymph node status and clinical stage. CRC patients with downregulated m6A-related gene expression, lower immune score, distant metastasis, lymph node metastasis or more advanced clinical staging had higher risk scores, indicating less-desirable outcomes. Moreover, we explored the immunology of colorectal cancer cells. The risk score showed positive correlations with eosinophils, M2 macrophages and neutrophils. In summary, our effort revealed the significance of m6A RNA methylation regulators in colorectal cancer, and the prognostic model we constructed may be used as an essential reference for predicting the outcome of CRC patients.
RESUMO
BACKGROUND: It is necessary to identify patients at risk of developing lymph node metastasis prior to papillary thyroid carcinoma (PTC) surgery. This can be challenging due to limiting factors, and an artificial intelligence algorithm may be a viable option. OBJECTIVE: In this study, we aimed to evaluate whether combining an artificial intelligence algorithm (support vector machine and probabilistic neural network) and clinico-pathologic data can preoperatively predict lymph node metastasis of papillary thyroid carcinoma (PTC). METHODS: We retrospectively examined 251 PTCs with lymph node metastasis and 194 PTCs without lymph node metastasis. The artificial intelligence algorithm included the support vector machine (SVM) and the probabilistic neural network (PNN). RESULTS: The ACR TI-RADS (Thyroid Imaging, Reporting and Data System), number of tumours, no well-defined margin, lymph node status and rim calcification on ultrasonography (US), age, sex, tumour size, and presence of Hashimoto's thyroiditis were significantly more frequent among PTCs with central lymph node metastasis than those without metastasis (P<0.05). The PNN classifier revealed an F1 score of 0.88 on the central lymph node metastasis test set. The SVM classifier revealed an F1 score of 0.93 on the lateral lymph node metastasis test set. Our study demonstrates that combining artificial intelligence algorithms and clinico-pathologic data can effectively predict the lymph node metastasis of papillary thyroid carcinoma prior to surgery.
