Machine Learning Based Approaches to diagnosis and detection of cancerous and non-pancreatic cancerous conditions

Pancreatic cancer is one of those diseases that progress through the stages swiftly and is challenging to diagnose or recognize in its early stages. This paper covers the state-of-the-art methods for predicting cancer survival of patients from pancreatic ductal adenocarcinoma cancer (PDAC). As computerization and technology have advanced, machine learning has become a widely used technique in many disciplines, including medicine. It has become more and more common, especially in the diagnosis of cancer. Using a collection of urine biomarkers from the open-access Kaggle database, researchers were able to determine the best model for diagnosing PDAC in patients. Owing to the iterative nature of models like Random forest, Gradient boosting, Catboost classifier were taken into consideration for the purpose of classifying the disease diagnosis. Accuracy, loss, precision and F1-score criteria were utilized to compare the classification performance of the various approaches. The results suggests that catboost classifier performs better with an accuracy of 91.89% for diagnosis and prediction of pancreatic cancer.