MEDI-Q&A: AN ONLINE MEDICAL SYSTEM BASED ON BOOTSTRAP APPROACH.

Abstract

Online healthcare is a web based system which satisfies health seeker needs by providing inference of the
related disease this reduces communication gap between health seeker and health advisor. In healthcare accurately and
efficiently inferring diseases is nontrivial especially for community-based health services due to vocabulary gap,
incomplete information, correlated medical concepts, and limited high quality training samples. It is also very important
to identify the discriminant features. Suppose more than one disease having some symptoms then to give the correct
inference of which possible disease the health seeker may suffer from finding discriminant features is done using
signature mining. Liqiang Nie, Bo Zhang, were proposed user study report on the information needs of health seekers in
terms of questions and then select those that ask for possible diseases of their manifested symptoms for further analytic.
Next step proposed is a novel deep learning scheme to infer the possible diseases given the questions of health seekers.
The proposed scheme is comprised of two key components. The first globally mines the discriminate 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
with pseudo-labelled data. Following that, the hidden nodes serve as raw features for the more abstract semantic
bootstrap approach. With incremental and alternative repeating of these two components. Our contribution is a
proposed a question answer system for automatic disease inference. Tag have been generated from the user query to be
matched with the dataset .System provides inference of having a particular disease based on tags. The proposed system
identifies discriminant features for correct diagnosis of disease.