Framework for Headache Disease using Novel Deep Learning

Disease tracing is an important in everyone life. Everyone care about himself/herself. Lots of people spend their time in online searching internet. Normally people use google to search their health related problem but they get information in scattered format. User do not get exact answer for their query. So we are going to implement this paper, we first report a user study on the information needs of health seekers in terms of questions and then select those that ask for possible diseases. We next propose novel deep learning algorithm to finding the possible headache diseases given the questions of health seekers. There are 26 types of headache. System ask various types of question and user have to give answer of that question. According to users answer system find the disease that user suffer from. The proposed scheme comprises of two key components. The first globally mines the discriminant medical signatures from raw features. The second deems the raw features and their signatures as input nodes in one layer and hidden nodes in the subsequent layer, respectively. Meanwhile, it learns the inter-relations between these two layers via pre-training. Following that, the hidden nodes serve as raw features for the more abstract signature mining. This is help to know possible headache disease with information about that disease.