Early diagnosis of cervical cancer using Machine Learning approaches: Comparative Analysis

The disease that has the greatest effect on people is cancer. The analysis of previous cancer cases aided in determining the progressions that should be made with high-risk patients to lower the risk they face. Cervical cancer might potentially develop from these cells. The dataset gathered from Kaggle for predicting the likelihood of cervical cancer was used in the proposed study. No values for data were missing within the assessment of the collected data. A model for prediction that was developed as a result of this research can help determine if an individual has cervical cancer or not. Utilizing classification accuracy, F1-measure, recall, and precision, the predictive system's effectiveness is evaluated. An analysis comparison has been carried out based on the outcom8es of different algorithms used for machine learning. The proposed approach uses a variety of machine learning classification algorithms, with the Random Forest (RF) showing the highest accuracy 96.8% in predicting cancer among patients.