ABSTRACT
In this paper a new method of data retrieval from free text documents in medical domain is proposed. Presented approach gives the document summary and highlights important keywords in the text to support further analysis of multiple medical documents. The document is processed with natural language processing techniques to find medical keywords and assign them to concepts in the medical ontology. These concepts contribute to higher levels in the hierarchy and build the document descriptor as a graph with concepts in the nodes and corresponding relevance points. The descriptor is used to generate the summary in a form of tree. Finally, we highlight the most important keywords in the original text. Presented experiments demonstrate the proposed approach, which successfully summarizes and highlights meaningful medical information.
- Xiaojun Wan, Jianmin Zhang. CTSUM: extracting more certain summaries for news articles. In Proc. of the 37th International ACM SIGIR conference on Research & Development in Information Retrieval, Queensland, Australia, July 6--11, 2014. Google ScholarDigital Library
- Pengjie Ren, Zhumin Chen, Zhaochun Ren, Furu Wei, Jun Ma, Maarten de Rijke. Leveraging Contextual Sentence Relations for Extractive Summarization Using a Neural Attention Model. In Proc. of the 40th International ACM SIGIR, Tokyo, Japan, August 7--11, 2017. Google ScholarDigital Library
- Andreas Doms and Michael Schroeder. GoPubMed: exploring PubMed with the Gene Ontology. Nucleic Acids Research, Vol.33, pp. 783--786, 2005.Google ScholarCross Ref
- Jenssen, Tor-Kristian; Leegreid, Astrid; Komorowski, Jan; Hovig, Eivind. A literature network of human genes for high-throughput analysis of gene expression. Nature Genetics. Vol.28 (1), pp. 21--8, 2001.Google ScholarCross Ref
- Rada Mihalcea and Paul Tarau. TextRank: Bringing Order into Text. In Proc. of International Conference on Empirical Methods on Natural Language Processing (EMNLP), Barcelona, Spain, 2004.Google Scholar
- Yatsko, V. et al. Automatic genre recognition and adaptive text summarization. Automatic Documentation and Mathematical Linguistics, Vol.44 (3), pp.111--120, 2010. Google ScholarDigital Library
- Sparsh Mittal and Ankush Mittal. Versatile question answering systems: seeing in synthesis. Intelligent Information and Database Systems. Vol.5 (2), pp. 119--142, 2011. Google ScholarDigital Library
- Jaime Carbonell and Jade Goldstein. The use of MMR, diversity-based reranking for reordering documents and producing summaries. In Proc. of ACM SIGIR, Melbourne, Australia, August 24--28, 1998. Google ScholarDigital Library
- Hui Lin and Jeff Bilmes. Learning mixtures of submodular shells with application to document summarization. In Proc. of the conference on Uncertainty in Artificial Intelligence, Catalina Island, US, Aug 14--18, 2012. Google ScholarDigital Library
- "Simplish Simplification and Summarization Tool". The Goodwill Consortium. Retrieved February 8, 2017.Google Scholar
- Apache cTAKES: clinical Text Analysis and Knowledge Extraction System, http://ctakes.apache.org/Google Scholar
- SNOMED CT, http://www.snomed.org/Google Scholar
- Medical Subject Headings, https://www.nlm.nih.gov/mesh/Google Scholar
- History and Physical Examination Examples, http://www.clinicaladvisor.comGoogle Scholar
Index Terms
Medical documents processing for summary generation and keywords highlighting based on natural language processing and ontology graph descriptor approach
Recommendations
Ontology-based integration of clinical documents
IIWAS '12: Proceedings of the 14th International Conference on Information Integration and Web-based Applications & ServicesExisting health information systems gather and organize patients' health documents into hierarchical structures, and support a variety of ways for organizing the documents, e.g., grouping together the documents by episode, clinical specialty or time ...
Toward a taxonomy of concepts using web documents structure
IIWAS '12: Proceedings of the 14th International Conference on Information Integration and Web-based Applications & ServicesDue to the rise of the Web and the need to have structured knowledge, an interesting line for research is the formalization of ontologies and the creation of conceptual taxonomies from Web documents. The traditional methods for ontology learning and ...
Comments