Performance Evaluation of Machine Learning Based Classifier Techniques In Prostate Cancer Prediction using Novel Decision Tree and Naive Bayes Classification Techniques

Prostate cancer is the most diagnosed malignancy worldwide and the sixth leading cause of cancer-related death in men. Diagnosis is primarily based on prostate-specific antigen testing, magnetic resonance imaging scans, and prostate tissue biopsies, although prostate-specific antigen testing for screening remains controversial. New diagnostic technologies are now available, including risk stratification bioassay tests, germline testing, and various positron emission tomography scans. When confined to the prostate, the disease is considered localized and potentially curable. If the disease has spread outside the prostate, bisphosphonates, rank ligand inhibitors, hormonal treatment, chemotherapy, radiopharmaceuticals, immunotherapy, focused radiation, and other targeted therapies can be used. This activity provides a comprehensive review of the current evaluation and management of prostate cancer, highlighting the role of the interprofessional team in improving care for affected patients. The proposed paper discussed ML based classifier techniques for prediction of affected prostate cancer glands. The Decision tree and naïve Bayes classifier are implemented for the prostate cancer patient data. Comparative analysis with the help of classification metrics is presented. The prediction accuracy using decision trees 82% and 79% for Naïve Baye classifier.