New Ensemble Deep Learning Model for Gynaecological Cancer Risk Prediction

Abstract Gynaecological cancer is a prevalent type of cancer affecting women worldwide, and early detection is critical for successful treatment and prevention of cancer recurrence. In our study, we introduce an innovative method to predict cervical cancer risk using a combination of deep learning models. Our approach employs a nested ensemble technique, where multiple deep learning base models are individually trained and then integrated to create a more precise ensemble model. In the initial phase of our nested ensemble method, we leverage sophisticated stacking deep learning techniques, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Support Vector Machines (SVMs). The subsequent MetaClassifier section introduces a voting mechanism, seamlessly integrating methods such as j48 and SGD. Our experimental findings reveal that our method surpasses expectations, demonstrating superior performance compared to existing state-of-the-art approaches in analyzing cervical cancer data.