Elderly patients over 80 years undergoing colorectal cancer resection: Development and validation of a predictive nomogram for survival

Prognostic model for predicting the survival benefit of adjuvant chemotherapy for elderly patients with stage II colon cancer: a population-based study

OBJECTIVES

Adjuvant chemotherapy benefits in elderly patients with stage II colon cancer (CC) remain controversial. We aimed to construct a nomogram to estimate the chemotherapy survival benefits in elderly patients.

METHODS

The training and testing cohort were patients with stage II CC older than 70 years from the Surveillance, Epidemiology, and End Results (SEER) database, while the external validation cohort included patients from the National Cancer Center (NCC). Cox proportional hazard models were used to determine the covariates associated with overall survival (OS). Using the risk factors identified by Cox proportional hazards regression, a nomogram was developed to predict OS. Nomogram precision was assessed using receiver operating characteristic and calibration curves.

RESULTS

The present study recruited 42 097 and 504 patients from the SEER database and NCC, respectively. The OS of patients who underwent surgery plus adjuvant chemotherapy was considerably longer than patients who underwent surgery alone. The nomogram included variables related to OS, including age, year of diagnosis, sex, AJCC T stage, tumor location, tumor size, harvested lymph nodes, and chemotherapy. According to the nomogram score, the elderly patients were separated into high- and low-risk groups, with high-risk group nomogram scores being greater than the median value, and vice versa. Patients in the high-risk group witnessed worse prognosis and were more likely to benefit from postoperative chemotherapy.

CONCLUSION

This nomogram can be regarded as a useful clinical tool for assessing the potential adjuvant chemotherapy benefits and for predicting survival in elderly patients with stage II CC.

Predictive modeling algorithms for liver metastasis in colorectal cancer: A systematic review of the current literature

This study aims to assess the quality and performance of predictive models for colorectal cancer liver metastasis (CRCLM). A systematic review was performed to identify relevant studies from various databases. Studies that described or validated predictive models for CRCLM were included. The methodological quality of the predictive models was assessed. Model performance was evaluated by the reported area under the receiver operating characteristic curve (AUC). Of the 117 articles screened, seven studies comprising 14 predictive models were included. The distribution of included predictive models was as follows: radiomics (n = 3), logistic regression (n = 3), Cox regression (n = 2), nomogram (n = 3), support vector machine (SVM, n = 2), random forest (n = 2), and convolutional neural network (CNN, n = 2). Age, sex, carcinoembryonic antigen, and tumor staging (T and N stage) were the most frequently used clinicopathological predictors for CRCLM. The mean AUCs ranged from 0.697 to 0.870, with 86% of the models demonstrating clear discriminative ability (AUC > 0.70). A hybrid approach combining clinical and radiomic features with SVM provided the best performance, achieving an AUC of 0.870. The overall risk of bias was identified as high in 71% of the included studies. This review highlights the potential of predictive modeling to accurately predict the occurrence of CRCLM. Integrating clinicopathological and radiomic features with machine learning algorithms demonstrates superior predictive capabilities.