Disease Identification using Concept and Feature Relationship Analysis for Remote Health Services

Abstract

Internet provides various resources for Remote health services. Web based communication models are adapted to manage the interaction between the remote people with medical experts. Remote health services are provided in two ways. They are reputable portals and community based health services. Reputable portal provides information related to the health care domains. Community based health services are built to support in a particular way based on health care solutions for the patients. Community based health service models are applied to support disease identification process. Vocabulary and medical terminology are provided for the Patient and Doctor Communication. Medical concepts and diagnosis samples are required for the health services. Disease diagnosis is carried out with the question and answer communication data values. Disease identification is achieved using the sparse deep learning method. Local learning and global learning methods are adapted to analyse the raw features for signature identification process. Disease inferences are discovered using the sparse learning method. Sparse learning method is enhanced to identify the discriminatory features. Medical term relationships are discovered with the medical domain based Ontology. Decision making is carried out with the concept relationship measurements. Symptoms and their importance are also considered in the decision support process.