A Deep Learning Model for Predicting Cervical Cancer
Sakshi Bhelkar, Samidha S. Nikhate, Sumedha Tambulkar, Nekita Chavhan Morris, Rahul Agrawal, Chetan Dhule · 2024
The leading cause of death for women is cervical cancer, especially in underprivileged areas where early identification is essential. This study presents a hybrid deep learning and machine learning method that combines Feedforward Neural Networks (FNN), Recurrent Neural Networks (RNN), Deep Belief Networks (DBN), and Support Vector Machines (SVM) to improve the prediction of cervical cancer. The suggested approach makes use of each algorithm's advantages to provide predictions that are more accurate and dependable, paying special attention to DBN-like features for training accuracy. Our method shows notable gains in prediction accuracy and efficiency, with considerable promise for improved clinical outcomes and early identification. The Feedforward Neural Network (FNN) demonstrated its efficacy in this crucial area of health by achieving the highest accuracy in cervical cancer prediction among the models tested.