A machine learning-based Approach to predict cervical cancer

Abstract

Recently, there has been a significant increase in the prevalence of physical illnesses, including cervical cancer disease, drawing considerable attention due to its impact on a large population. The severity of the illness can be better understood by analyzing differences between normal and affected diagnostic reports. With numerous studies focused on understanding cervical cancer disease, there are promising opportunities for advancing diagnostic techniques. In this study, I propose the utilization of algorithmic models for early identification and raising awareness of potential threats. My straightforward approach is suitable for predicting simple cases of cervical cancer disease illness in real-world scenarios. We have collected the dataset from Kaggle dataset. We employed various classifiers, including Random Forest (RF), Logistic Regression (LR), Gradient Boosting (GB), K-Nearest Classifier (KNN), Adaboost Classifier (ABC), Decision Tree (DT), Support Vector Machine (SVM) and Gaussian Naïve Bayes (GNB). Notable results were achieved, with the K-Nearest Classifier (KNN), Adaboost Classifier (ABC) standing out as the most accurate, achieving an impressive accuracy rate of 97.33%. Through an experimental investigation and a review of recent findings, I confirmed that the K-Nearest Classifier (KNN), Adaboost Classifier (ABC) performed exceptionally well, accurately predicting cervical cancer disease with an accuracy rate of 97.33%