XGSVM Based Ensemble Machine Learning Model For The Early Prediction of Pancreatic Cancer

Pancreatic cancer is one of the most fatal types of cancer due to its delayed prognosis and rapid development. Early diagnosis is crucial for increasing survival rates, but it is still a big barrier. Machine learning (ML) algorithms for the early detection of pancreatic cancer can potentially enhance patient outcomes and diagnosis significantly. Given the notoriously challenging nature of early pancreatic cancer detection, ML provides a means of analyzing large, complicated datasets to find minor patterns that may indicate early illness. This paper proposed an ensemble machine learning method that uses a Support Vector Machine (SVM) and the XGBoost algorithm to detect pancreatic cancer. A dataset comprising imaging data, genetic markers, clinical history, and demographics was constructed from patient having pancreatic cancer. Following the removal of missing data and the normalization of features, the dataset was split into training and test sets. Individual SVM and XGBoost models were then trained using the training data, using the ensemble of decision trees in XGBoost for reliable classification and the ability of SVM to define complex decision boundaries. The XGSVM model was implemented by combining the output of the two models using an ensemble method to increase forecast accuracy. Evaluation of the test set demonstrated the efficacy of the ensemble approach, resulting in a notable improvement in prediction accuracy above individual SVM and XGBoost models. The results of the experiments showed that the proposed model predicted pancreatic cancer more accurately than the conventional methods, with a 95.8% accuracy rate. In conclusion, the XGSVM ensemble model that has been proposed in this paper is a reliable and precise model for predicting pancreatic cancer.