Optimal Allocation of Chemotherapy Schemes for Metastatic Colon Cancer in Colombia

Construction of the survival nomograms for colon cancer patients of different ages based on the SEER database

INTRODUCTION

Three nomograms for predicting the outcomes of early- and late-onset colon cancer (COCA) among patients not stratified by age were constructed using data in the Epidemiology and End Results (SEER) database (1975-2019). The accuracy of the nomogram was then assessed.

METHOD

Clinical data of 6107 patients with COCA were obtained from the SEER database. The patients were randomly divided into training and validation cohorts in a ratio of 7:3. Univariate and multivariate COX analyses of factors that could independently impact the prognosis of COCA were performed, and the corresponding nomograms for early-onset and late-onset COCA were constructed. Calibration curves, ROC curves, and C-index were used to determine the predictive accuracy. The discriminatory ability of the nomograms to assess their clinical utility, which was compared with the TNM staging system of the 8th edition of AJCC, was verified using survival analysis.

RESULT

Tumor primary site, ethnicity, and serum carcinoembryonic antigen (CEA) level significantly impacted the prognosis of colon cancer. Race, brain metastasis, and CEA were independent factors for predicting COCA prognosis. C-index, ROC, and calibration curves demonstrated that the three nomograms were accurate and superior to the traditional TNM staging system. Among the three nomograms, the early-onset COCA nomogram had the highest predictive accuracy, followed by that of colon cancer not stratified by age.

CONCLUSION

Three nomograms for patients not stratified by age, early-onset colon cancer, and late-onset colon cancer were constructed. The accuracies of the nomograms were good and were all superior to the conventional TNM staging system. The early- and late-onset COCA nomograms are useful for clinical management and individualized treatment of COCA patients at different ages.

Construction and validation of nomograms combined with novel machine learning algorithms to predict early death of patients with metastatic colorectal cancer

Purpose

The purpose of this study was to investigate the clinical and non-clinical characteristics that may affect the early death rate of patients with metastatic colorectal carcinoma (mCRC) and develop accurate prognostic predictive models for mCRC.

Method

Medical records of 35,639 patients with mCRC diagnosed from 2010 to 2019 were obtained from the SEER database. All the patients were randomly divided into a training cohort and a validation cohort in a ratio of 7:3. X-tile software was utilized to identify the optimal cutoff point for age and tumor size. Univariate and multivariate logistic regression models were used to determine the independent predictors associated with overall early death and cancer-specific early death caused by mCRC. Simultaneously, predictive and dynamic nomograms were constructed. Moreover, logistic regression, random forest, CatBoost, LightGBM, and XGBoost were used to establish machine learning (ML) models. In addition, receiver operating characteristic curves (ROCs) and calibration plots were obtained to estimate the accuracy of the models. Decision curve analysis (DCA) was employed to determine the clinical benefits of ML models.

Results

The optimal cutoff points for age were 58 and 77 years and those for tumor size of 45 and 76. A total of 15 independent risk factors, namely, age, marital status, race, tumor localization, histologic type, grade, N-stage, tumor size, surgery, radiation, chemotherapy, bone metastasis, brain metastasis, liver metastasis, and lung metastasis, were significantly associated with the overall early death rate of patients with mCRC and the cancer-specific early death rate of patients with mCRC, following which nomograms were constructed. The ML models revealed that the random forest model accurately predicted outcomes, followed by logistic regression, CatBoost, XGBoost, and LightGBM models. Compared with other algorithms, the random forest model provided more clinical benefits than other models and can be used to make clinical decisions in overall early death and specific early death caused by mCRC.

Conclusion

ML algorithms combined with nomograms may play an important role in distinguishing early deaths owing to mCRC and potentially help clinicians make clinical decisions and follow-up strategies.

Survival Nomogram for Metastasis Colon Cancer Patients Based on SEER Database

Introduction: A prediction model for the 1-, 3-, and 5-year survival rates of metastatic colon cancer (mCC) patients was developed by analyzing important risk factors for the prognosis of mCC patients based on the SEER database.

Method: The characteristic of 10,946 patients diagnosed with mCC between 2010 and 2015 was obtained from the SEER database. The population was randomly divided into a training cohort and an internal validation cohort in a 7:3 ratio. Univariate and multivariate cox for independent predictors of mCC prognosis were performed, and nomogram was constructed. The accuracy of the model was verified by calibration curves, ROC curves, and C-index, and the clinical utility of the model was analyzed using decision analysis curves.

Result: Age, primary site, grade, surgery, and other eight factors were significantly associated with the prognosis of mCC patients, and these predictors were included in the construction of the nomogram. The C-index was 0.731 (95% CI 0.725–0.737) and 0.736 (95% CI 0.726–0.746) for the training cohort and the validation set, respectively. The results of the ROC curve analysis indicated that the area under the curve (AUC) exceeded 0.7 for both the training cohort and the validation set at 1, 3, and 5 years.

Conclusion: The constructed prediction model had an excellent predictive accuracy, which will help clinical decision-making of mCC patients after surgery and individualized treatment.