Forecasting Breast Cancer Development using Deep Learning

The awareness of health systems is not decreasing the concern of breast cancer in the globe especially concerning results between patients. Making use of historical data from patients makes it possible to enhance, not just the sensitivity of predictive modeling of these diseases but also in the intervention approaches of this disease. The present work describes a novel application of recurrent neural network, namely Long Short-Term Memory (LSTM) neural network, for breast cancer prediction. They are mainly utilized for the analysis and understanding of sequence-based data. The model learns about an enormous database made of all areas of a patient containing information about the tumor makers, hormone, and even where they were born. Since LSTM networks take such a structure, they can actually represent a class of complex dynamic patterns in time. Moreover, the accurate predictions also made it through by the aid of even pre-processing and feature engineering data along with mending the model. The result depicted that the model based on LSTM is available source for developing early detection and micro-treatment approaches for breast cancer to enhance patient outcomes and control the disease