Published Paper Details:

The most common gynaecological malignancy that causes serious issues for women if left untreated is cervical cancer. This study exhibits various classification algorithms and demonstrates the benefit of feature selection methodologies for the most accurate cervical cancer disease prediction. The amount of patient digital system data in the healthcare industry is utilised to extract information and predict immune deficiency syndrome, which aids in patients' informed decision-making. To help patients understand the reports' material better, a health recommender system is employed. For feature selection in the proposed model, we employ wrapper techniques with the K Nearest Neighbor (KNN) classifier, and Multi Objective Algorithm (MOA) has been identified. is utilised in this system for feature selection as the most effective evolutionary algorithm to choose the key features with less complexity as compared to other conventional feature selection approaches. The dataset for the implementation and accuracy of the cervical cancer risk classification has been used as the assessment parameter.