The impact of previous cancer on overall survival of bladder cancer patients and the establishment of nomogram for overall survival prediction

Competitive Risk Model for Specific Mortality Prediction in Patients with Bladder Cancer: A Population-Based Cohort Study with Machine Learning

Background

Noncancer death accounts for a high proportion of all patients with bladder cancer, while these patients are often excluded from the survival analysis, which increases the selection bias of the study subjects in the prediction model.

Methods

Clinicopathological information of bladder cancer patients was retrieved from the Surveillance, Epidemiology, and End Results (SEER) database, and the patients were categorized at random into the training and validation cohorts. The random forest method was used to calculate the importance of clinical variables in the training cohort. Multivariate and univariate analyses were undertaken to assess the risk indicators, and the prediction nomogram based on the competitive risk model was constructed. The model's performance was evaluated utilizing the calibration curve, consistency index (C index), and the area under the receiver operator characteristic curve (AUC).

Results

In total, we enrolled 39285 bladder cancer patients in the study (27500 patients were allotted to the training cohort, whereas 11785 were allotted to the validation cohort). A competitive risk model was constructed to predict bladder cancer-specific mortality. The overall C index of patients in the training cohort was 0.876, and the AUC values were 0.891, 0.871, and 0.853, correspondingly, for 1-, 3-, and 5-year cancer-specific mortality. On the other hand, the overall C index of patients in the validation cohort was 0.877, and the AUC values were 0.894, 0.870, and 0.847 for 1-, 3-, and 5-year correspondingly, suggesting a remarkable predictive performance of the model.

Conclusions

The competitive risk model proved to be of great accuracy and reliability and could help clinical decision-makers improve their management and approaches for managing bladder cancer patients.

Clinical features of patients with pancreatic ductal adenocarcinoma with a history of other primary malignancies: A retrospective analysis

Patients with pancreatic ductal adenocarcinoma (PDAC) that have a history of other primary malignancies are not well documented. The current study therefore aimed to evaluate the clinicopathological characteristics of patients with PDAC with or without a history of other primary malignancies. A total of 102 patients with surgically treated PDAC that presented with or without a history of other primary malignancies were retrospectively analyzed. A total of 25 patients (24.5%) had a history of other primary malignancies (age, with history of other primary malignancy vs. without, 74.2 vs. 68.9 years; P=0.005) and the reason for consultation (P<0.001) differed significantly between the groups with a history of other primary malignancies [HoM(+)] and without a history of other primary malignancies [HoM(-)]. Incidental indications during malignancy follow-up was the most common reason for the diagnosis of PDAC in the HoM(+) group. Conversely, there were no significant differences in the resectability (P=0.645), complete resection rate (P=0.774) and final stage (P=0.474) between the two groups. Disease-free survival was also not significantly different between the two groups (P=0.184). However, overall survival was significantly poorer in the HoM(+) group compared with the HoM(-) group (P=0.003). A history of other primary malignancies was also an independent predictor of poor overall survival (hazard ratio, 2.416; 95% confidence interval, 1.324-4.406; P=0.004). In conclusion, patients with PDAC and a history of other primary malignancies had significantly poorer overall survival than their counterparts, despite no differences in disease-free survival.