ObjectivesLaryngeal cancer is the most prevalent entity of head and neck cancer. Knowing the trends of incidence and mortality of laryngeal cancer is important for the reduction in related disease burden.DesignPopulation-based observational study.Main outcomes and measuresThe incidence and mortality data of laryngeal cancer were retrieved from the Global Burden of Disease study 2017 online database. The estimated average percentage change was used to quantify the trends of laryngeal cancer incidence and mortality at the global, regional and national levels.ResultsGlobally, the numbers of incident cases and deaths due to laryngeal cancer increased 58.7% and 33.9%, respectively, from 1990 to 2017. However, the overall age-standardised incidence rate (ASIR) and age-standardised mortality rate decreased by 0.99% (95% CI 0.83% to 1.14%) and 1.62% (95% CI 1.50% to 1.74%) per year, respectively. These decreases were ubiquitous worldwide. However, unfavourable trends in the ASIR of laryngeal cancer were also observed in a total of 51 developing countries.ConclusionsThe incidence and mortality rates of laryngeal cancer have significantly decreased at the global level and in most countries over the past three decades. The regions that showed an increasing incidence trend deserve more attention.

Background T1 colorectal cancers have a low lymph node metastasis rate and good prognosis. Thus, endoscopic resection is an attractive choice. This study aimed to describe the value of poorly differentiated cluster grade in identifying endoscopically curable T1 colorectal cancers. Methods We included 183 T1 colorectal cancer patients who underwent curative resection. Univariate and multivariate logistic regressions were used to identify lymph node metastasis predictors. The Akaike information criterion was used to determine whether poorly differentiated cluster grade was the best predictor. Backward regression was used to screen the variables. Survival analyses were conducted to determine the prognostic predictive power of poorly differentiated cluster grade. Correlations among predictors and concordance between our pathologists were also investigated. Results Poorly differentiated cluster grade was an independent predictor for lymph node metastasis (adjusted odds ratio [OR]G 3 = 0.001; 95% confidence interval [95% CI]G 3 =  < 0.001, 0.139) in T1 colorectal cancer patients; moreover, it had the best predictive value (AIC = 61.626) among all indicators. It was also screened for inclusion in the predictive model. Accordingly, a high poorly differentiated cluster grade independently indicated shorter overall survival (hazard ratio [HR]G 2 = 4.315; 95% CIG 2 = 1.506, 12.568; HRG 3 = 5.049; 95% CIG 3 = 1.326, 19.222) and disease-free survival (HRG 3 = 6.621; 95% CIG 3 = 1.472, 29.786). Conclusions Poorly differentiated cluster grade is a vital reference to manage T1 colorectal cancer. It could serve as an indicator to screen endoscopically curable T1 colorectal cancers.

Background To utilize the patient, tumor, and treatment features and compare the performance of machine learning algorithms, develop and validate models to predict overall, disease-free, recurrence-free, and distant metastasis-free survival, and screen important variables to improve the prognosis of patients in clinical settings. Methods More than 1,000 colorectal cancer patients who underwent curative resection were grouped according to 4 survival times (further categorized by 3- and 5-year) and divided into training sets and testing sets (9:1). Each 3-catergory survival time was predicted by 4 machine learning algorithms. The area under the receiver operating characteristic curve (AUC) and average precision (AP) were our accuracy indicators. Vital parameters were screened by multivariate regression models. To achieve better prediction of multi-categorized survival times, we performed 10-fold cross-validation except for the recurrence-free survival model (5-fold cross-validation). We iterated 1000 times after hyperparameter optimization. Results The best AUCs were all greater than 0.90 except for the overall survival model (0.86). The best AP of the disease-free and distant metastasis-free survival models was 82.7%. The models performed well. Some of the important variables we screened were widely used important predictors for colorectal cancer patients’ prognoses, while others were not. Regarding algorithm performance, Logistic Regression, Linear Discriminant Analysis, and Support Vector Machine were chosen for recurrence-free and distant metastasis-free, overall, and disease-free models. Conclusions We constructed an independent, high-accuracy, important variable clarified machine learning architecture for predicting 3-catergorized survival times. This architecture might be a vital reference when managing colorectal cancer patients.

Purpose To utilize the patient, tumor, and treatment features and compare the performance of machine learning algorithms, develop and validate models to predict overall, disease-free, recurrence-free, and distant metastasis-free survival, and screen important variables to improve the prognosis of patients in clinical settings.Methods More than 1000 colorectal cancer patients who underwent curative resection were grouped according to 4 endpoints and divided into testing sets and training sets (9:1). We applied 4 machine learning algorithms to predict 1-, 3-, and 5-year survival times. The area under the receiver operating characteristic curve (AUC) and average precision (AP) were our accuracy indicators. Vital parameters were screened by multivariate regression models. To achieve better prediction of longitudinal oncological outcomes, we performed 10-fold cross-validation except for the recurrence-free survival model (3-fold cross-validation). We iterated 3000 times after hyperparameter optimization and assessed the internal testing sets.Results The best AP values were greater than 80%, except for the overall survival model (69.5%). The best AUCs were all greater than 0.70 except for the recurrence free survival model (0.61). The models performed well. Variables that were widely correlated with prognoses, such as the TNM stage, were selected as important features; however, indirectly related indicators, such as Ki-67 level, were also selected.Conclusion We constructed an independent, high-accuracy "white-box" machine learning system for predicting survival times. This system may help in determining managing strategies for colorectal cancer patients and has future utility in personalized medicine and monitoring.