DESIGNING A MULTI-TIER MODEL FOR CERVICAL CANCER PREDICTION USING LEARNING APPROACHES

Abstract

Cervical cancer poses a significant threat to global health, disproportionately affecting low- and middle-income nations. Lifestyle decisions can play a role in increasing the likelihood of cervical cancer. The primary cause of most cervical cancers is Human PapillomaVirus (HPV), an infection transmitted through intimate contact. HPV Pathogens must persist over time to increase the risk of progressing to pre-cancer and cancer. Several factors contribute to the persistence of HPV infection, including age, STIs, sexual history, reproductive factors, tobacco use, and more. Risk assessment algorithms enable the identification of high-risk women, facilitating prioritized screening for cervical cancer. This research presents a lifestyle-based Multi-tier SVM (???????? − ???????????? ) classifier model for predicting cervical cancer risk. The ???????? − ???????????? classifier was implemented to detect the most crucial characteristics. Oversampled data is then used to train and evaluate the performance of the pattern. An accuracy rate of 98.9% was accomplished using the ???????? − ???????????? pattern. This model has the potential to establish a link between risk factors and cervical cancer prediction, facilitating Strategies for prevention and effective management strategies.