Disease-Free Survival Prediction in Recurrent Cervical Cancer using Naive Bayes Machine Learning Algorithm

Cervical cancer ranks amongst the most common causes of death for women. The primary objective of this research is to use artificial intelligence based Naive bayes machine learning algorithm to use of different procedures that affect patients chances of surviving if their disease recurs. The Naive Bayes approach, that analyze clinical details and estimate disease-free survival in recurrent cervical carcinoma, is utilized throughout this work. If an initial treatments are unsuccessful for the medical professionals then they want to know how the other methods may affect the long term survival of patients. From the dataset by selecting the most important features through feature selection methods this give the progress to select the better treatment and results for patients. Surgical sample is collected from the certain reoccurring location to verify the recurrence by diagnostic. The clinical research’s results may offer significant details regarding the root cause and characteristics of the recurrent illness. Machine learning algorithms can use Disease free survival (DFS) information from cervical cancer patients to forecast how long patients would likely be free from disease progression. The predictive algorithms determined the chance of achieving prolonged DFS through examining multiple variables, which includes as methods of treatment, recurring sites, and histological classifications. Disease free survival is predicted using Naive Bayes classifier with high level of accuracy. This model is tested with 5 different classifiers and Naive Bayes attains high level of accuracy.