Identification of high-risk factors for recurrence of colon cancer following complete mesocolic excision: An 8-year retrospective study

Abstract

Background Colon cancer recurrence is a common adverse outcome for patients after complete mesocolic excision (CME) and greatly affects the near-term and long-term prognosis of patients. This study aimed to develop a machine learning model that can identify high-risk factors before, during, and after surgery, and predict the occurrence of postoperative colon cancer recurrence. Methods The study included 1187 patients with colon cancer, including 110 patients who had recurrent colon cancer. The researchers collected 44 characteristic variables, including patient demographic characteristics, basic medical history, preoperative examination information, type of surgery, and intraoperative information. Four machine learning algorithms, namely extreme gradient boosting (XGBoost), random forest (RF), support vector machine (SVM), and k-nearest neighbor algorithm (KNN), were used to construct the model. The researchers evaluated the model using the k-fold cross-validation method, ROC curve, calibration curve, decision curve analysis (DCA), and external validation. Results Among the four prediction models, the XGBoost algorithm performed the best. The ROC curve results showed that the AUC value of XGBoost was 0.962 in the training set and 0.952 in the validation set, indicating high prediction accuracy. The XGBoost model was stable during internal validation using the k-fold cross-validation method. The calibration curve demonstrated high predictive ability of the XGBoost model. The DCA curve showed that patients who received interventional treatment had a higher benefit rate under the XGBoost model. The external validation set’s AUC value was 0.91, indicating good extrapolation of the XGBoost prediction model. Conclusion The XGBoost machine learning algorithm-based prediction model for colon cancer recurrence has high prediction accuracy and clinical utility.

Support Vector Machine Approaches for Tumor Classification and Survival Prediction in Cancer Patients: A Multi-Omics Data Analysis

“…Earlier to preparing the SVM models, broad preprocessing steps were embraced. This included information normalization to guarantee consistency over distinctive omics stages, feature selection to recognize the foremost instructive biomarkers, and dimensionality diminishment procedures such as central component examination (PCA) to relieve the revile of dimensionality [11].…”