An ovarian cancer prediction using an optimized Elman neural network based on elephant herding optimization

One of the leading causes of death for women is ovarian cancer (OC). More recently, deep learning has demonstrated improved accuracy in OC stage and subtype prediction. Nonetheless, the majority of cutting-edge deep learning models might lead to low performance due to inappropriate selection of hyperparameters. Furthermore, the optimization of the model construction—which necessitates a significant computational cost for training and deployment—remains absent from these deep learning models. This paper proposes a novel optimized technique using an optimized Elman recurrent neural network (ERNN) based on elephant herding optimization (EHO) called ERNN-EHO for predicting ovarian cancer. A variety of evaluation metrics were employed to contrast the suggested model with alternative prediction models. This was carried out utilizing an OC benchmark that was gathered from the Kaggle website. The experimental findings show that the suggested model can diagnose OC and other malignancies with greater precision and accuracy.