Best Treatment Identification for Disease Using Machine Learning Approach in Relation to Short Text

The goal of Machine Learning is to construct a computer system that can adapt and learn from their experience. Machine Learning approach helps to integrate the computer based system into the healthcare field in order to obtain best and accurate results for the system. Here the system deals with automatic identification of informative sentences from medical published by medical journals. Our main aim is to integrate machine learning in medical field and build an application that is capable of automatically identifying and disseminating disease and treatment related information, further it also identifies semantic relations that exists between diseases and treatments. In the proposed work user will search for the disease summary (disease and treatment related information) by giving symptoms as a query in the search engine. Initially when a pdf is downloaded and saved in the system it first performs per processing on the data in the document and the extracted relevant data is stored in the database. The symptoms entered by the user are further classified using SVM classifier to make the further process easier to find the semantic keyword which helps to identify the disease easily and quickly. Then the semantic keyword found is matched with the stored medical input database to identify the exact disease related to that keyword present. Once the disease related to the symptom is identified, it is sent to medical database to extract the articles pertaining to that disease. The preprocessing process involves tokenization, removal of stop words and stemming. Followed by that, relevant information is extracted using the keyword searching algorithm. The combination of BOW, NLP and biomedical concepts are put together toe identifying semantic relations that exist between diseases and treatments in biomedical sentences. Till now the best result obtain is 98.51% F-measure by OanaFrunza, for the extraction of cure and prevents relations. In our implementation of our proposed system we have used SVM classifier which gives us an improved result. The problem statement of the existing system was, it didn’t identify the best disease treatment. So the proposed solution used data mining concepts using voting algorithm to resolve the problem and find the best treatment for disease out of the treatment identified by the system.

[1]  C. Deisy,et al.  Extraction of Semantic Biomedical Relations from Medline Abstracts using Machine Learning Approach , 2012 .

[2]  Padmini Srinivasan,et al.  Exploring text mining from MEDLINE , 2002, AMIA.

[3]  Jiexun Li,et al.  Kernel-based learning for biomedical relation extraction , 2008 .

[4]  E. Madhusudhana Reddy,et al.  Efficient Machine Learning Approach for identifying Disease-Treatment Semantic Relations from Bio-Medical Sentences , 2012 .

[5]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[6]  Das Amrita,et al.  Mining Association Rules between Sets of Items in Large Databases , 2013 .

[7]  Yongyi Yang,et al.  Machine Learning in Medical Imaging , 2010, IEEE Signal Processing Magazine.

[8]  Thomas Tran,et al.  A Machine Learning Approach for Identifying Disease-Treatment Relations in Short Texts , 2011, IEEE Transactions on Knowledge and Data Engineering.

[10]  Anil K. Jain,et al.  Classification of text documents , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[11]  Lior Rokach,et al.  Context-Sensitive Medical Information Retrieval , 2004, MedInfo.

[12]  Barbara Rosario,et al.  Classifying Semantic Relations in Bioscience Texts , 2004, ACL.

[13]  AgrawalRakesh,et al.  Mining association rules between sets of items in large databases , 1993 .

[14]  Claudio Giuliano,et al.  Exploiting Shallow Linguistic Information for Relation Extraction from Biomedical Literature , 2006, EACL.

[15]  Mehmet S. Aktas,et al.  BlogMiner: Web Blog Mining Application for Classification of Movie Reviews , 2010, 2010 Fifth International Conference on Internet and Web Applications and Services.

[16]  Mark Craven,et al.  Representing Sentence Structure in Hidden Markov Models for Information Extraction , 2001, IJCAI.

[17]  Diana Inkpen,et al.  Extraction of Disease-Treatment Semantic Relations from Biomedical Sentences , 2010, BioNLP@ACL.

[18]  Diana Inkpen,et al.  Extracting Relations between Diseases, Treatments, and Tests from Clinical Data , 2011, Canadian Conference on AI.

[19]  Razvan C. Bunescu,et al.  Subsequence Kernels for Relation Extraction , 2005, NIPS.

[20]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[21]  Razvan C. Bunescu,et al.  A Shortest Path Dependency Kernel for Relation Extraction , 2005, HLT.

[22]  Tomasz Imielinski,et al.  Mining association rules between sets of items in large databases , 1993, SIGMOD Conference.