International Journal of Computational Engineering Research||Vol, 03||Issue, 6|| www.ijceronline.com ||June ||2013|| Page 23 Medical Diagnosis by Using Relation Extraction M.Syed Rabiya, 1, Asst professor, M.E ComputerScience and engineering, Sethu Institute of Technology . I. INTRODUCTION Datamining is the process of analyzing the data from different perspectives and summarizing it into useful information.The main aim of the project is Kernel-Based Learning for Biomedical Relation Extraction for helping health care and clinical data repositories. The designing and representation techniques in combination with various learning methods to identify and extract biomedical relations. Electronic Health Records (hereafter,EHR) are becoming the standard in the healthcare domain.Researches and studies show that the potential benefits of having an EHR system are Health information recording and clinical data repositories : immediate access to patient diagnoses, allergies,and lab test results that enable better and time-efficient medical decisions; Decision support: the ability to capture and use quality medical data for decisions in the workflow of healthcare. Obtain treatments that are tailored to specific health needs: rapid access to information.In order to embrace the views that the EHR system has,we need better, faster, and more reliable access to information. Medline(medical literature analysis and retrieval system online) a database of extensive life science published articles. identifying sentences published in medical abstracts (Medline) as containing or not information about diseases and treatments, and automatically identifying semantic relations that exist between diseases and treatments, as expressed in texts. The second task is focused on three semanticrelations: Cure, Prevent, and Side Effect.Our objective for this work is to show what Natural Language Processing (NLP) and Machine Learning (ML)techniques—what representation of information and what classification algorithms—are suitable to use for identifying and classifying relevant medical information in short texts.We acknowledge the fact that tools capable of identifying reliable information in the medical as stand as building blocks for a healthcare system that is up-to-date with the latest discoveries. II. RELATED WORK Prior work is based on entity recognition for diseases and treatments. The data set consists of sentences from Medline abstracts annotated with disease and treatment entities and with eight semantic relations between diseases and treatments. prior representation techniques are based on words in context, part of speech information, phrases, and a medical lexical ontology—Mesh6 terms. Compared to this work, my work is focused on different representation techniques,different classification models, and most importantly generates improved results with less annotated data.The task addressed is information extraction and relation extraction.Information extraction is the process of extracting the information from the database..Relation extraction is the process of detecting and classifying semantic relations by given text. Various learning algorithms have been used for the statistical learning approach with kernel based learning is the popular ones applied to Medline abstracts. ABSTRACT The healthcare information system extracts the sentences from published medical papers that mention group of diseases and treatments, and identifies semantic relations that exist between diseases and treatments.The extracted information is less accurate. My proposed methodology obtains reliable outcomes that could be integrated in an application to be used in the medical care main. The potential value of my paper stands in the ML settings that I propose and in the fact that would outperform previous results on the same data set. The same data set to provide the fact. INDEX TERMS: Healthcare, machine learning, natural language processing