Feature Selection Risk Factors Cervical Cancer Using Hybrid Methods Random Forest and FOX-Inspired Optimization Algorithm

Cervical cancer is one of the number four causes of death among women worldwide, with about 604,000 new cases and 324,000 deaths each year. Human Papillomavirus infection is one of the main factors in almost 99% of cervical cancer cases. In addition to HPV, other risk factors such as smoking, long-term use of oral contraceptives, and weak immunity also play an important role. Along with the development of technology and in an effort to detect cervical cancer early, machine learning algorithms have been widely used to analyze the risk of cervical cancer, one of which is Random Forest (RF). One of the main challenges in early detection of cervical cancer is the large amount of irrelevant and redundant data, which can reduce the accuracy of predictions, making feature selection imperative. SI is able to combine new algorithms to improve performance in feature selection. One of the SI-based optimization algorithms is the FOX-Inspired Optimization Algorithm. The results of research that has been carried out using the RF-FOX hybrid method, the Num of pregnancies feature has proven to be the most influential factor in detecting the risk of cervical cancer in patients. In addition, other features such as First sexual intercourse, Number of sexual partners, age, and Hormonal Contraceptives also occupy the top five most influential features. Therefore, the hybrid RF-FOX method allows the performance of the model to be more optimized, thus helping in the identification of patients at risk of cervical cancer more precisely.