Concept Node 분석을 이용한 방사선 판독문서로부터의 정보추출
Information Extraction Using Concept Node Analysis of Brain Radiology Reports Summarization
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Objective: Electronic Medical Record contains the majority of clinical data in unstructured text. The information in the textual document can be stored in conceptual format and used to support clinical care by text summarization technique. In this study, we present Information Extraction(IE) using Concept Node(CN) which is extraction rule in case frame from brain radiology reports in SNUH(Seoul National University Hospital) for summarization. Method: Following steps are performed: design conceptual model to define semantic entities as extraction templates of brain radiology report, build CN dictionary based on statistical syntactic pattern and development of parser to extract relevant information based on defined templates. Results: The three evaluation results shows that 19% precision improvement after post processing supplemental specified complex verb construction and 19.24~21.25% accurate semantic effectiveness with extracting additional Korean noun. The average of precision is 85.18%, average of recall is 93.71% and F-measure is 0.89. Conclusion: Our approach has advantageous elements for different language at the same sentence. We expect this IE technology can summarize vast amount radiology texts material for clinical decision support system effectively and hope this study helps the evolution of clinical data representation in Korean medical records and its integration into the EMR in the future.
Abstract
Objective: Electronic Medical Record contains the majority of clinical data in unstructured text. The information in the textual document can be stored in conceptual format and used to support clinical care by text summarization technique. In this study, we present Information Extraction(IE) using Concept Node(CN) which is extraction rule in case frame from brain radiology reports in SNUH(Seoul National University Hospital) for summarization. Method: Following steps are performed: design conceptual model to define semantic entities as extraction templates of brain radiology report, build CN dictionary based on statistical syntactic pattern and development of parser to extract relevant information based on defined templates. Results: The three evaluation results shows that 19% precision improvement after post processing supplemental specified complex verb construction and 19.24~21.25% accurate semantic effectiveness with extracting additional Korean noun. The average of precision is 85.18%, average of recall is 93.71% and F-measure is 0.89. Conclusion: Our approach has advantageous elements for different language at the same sentence. We expect this IE technology can summarize vast amount radiology texts material for clinical decision support system effectively and hope this study helps the evolution of clinical data representation in Korean medical records and its integration into the EMR in the future.
참고문헌 (32)
- "Information extraction as a core language technology A multidisciplinary approach to and emerging information technology", pp.1~9 (1997)
- "Conceptual information extraction and retrieval from natural language input Readings in information retrieval", pp.527~533 (1997), Morgan Kaufmann Publishers
- "A logical foundation for representation of clinical data", 1(3), pp.218~232 (1994)
- "In Proceedings of the Fourth Message Understanding Conference", pp.~4 (1992), Morgan Kaufmann Publishers
- "Proceedings of the Fifth Message Understanding Conference", pp.~5 (1994), Morgan Kaufmann Publishers
- "Proceedings of the Sixth Message Understanding Conference", pp.~6, Morgan Kaufmann Publishers
- "Proceeding of the Seventh Message Understanding Conference", pp.~7 (1998), Morgan Kaufmann Publishers
- "an information extraction approach to analysis of free-form text in life insurance applications Proceedings of the ninth Innovative Applications of Artificial Intelligence Conference", pp.27~31, AAAI Press
- "Information extraction as a basis for high-precision text classification", 12(3), pp.296~333 (1994)
- "Domain- specific knowledge acquisition from text Proceedings of the Sixth Conference on Applied Natural Language Processing" (2000), Morgan Kaufmann Publishers
- "Natural language generation in health care", 4(6), pp.473~482 (1997)
- "A reliability study for evaluating information extraction from radiology reports", 6(2), pp.143~150 (1999)
- "The analysis of mass physical screening using the concept of data warehousing short subject:Data warehousing and mass screening", 4(2), pp.111~114 (1998)
- "Automatically constructing a dictionary for information extraction tasks Proceedings of the Eleventh National Conference on Artificial Intelligence" (1993), AAAI Press
- "A general natural language text processor for clinical radiology", 1(2), pp.161~174 (1994)
- "Automated encoding of clinical documents based on natural language processing", 11(5), pp.392~402 (2004)
- "Building and evaluation of a structured representation of pharmacokinetics information presented in SPCs:From existing conceptual views of pharmacokinetics associated with natural language processing to object-oriented design", 10(3), pp.271~280 (2003)
- "Automatic detection of acute bacterial pneumonia from chest X-ray reports", 7, pp.593~604 (2000)
- "A schema for representing medical language applied to clinical radiology", 1(3), pp.248~ (1994)
- "Creating a text classifier to detect radiology reports describing mediastinal findings associated with inhalational anthrax and other disorders", 10(5), pp.494~503 (2003)
- "Computerized extraction of coded findings from free-text radiologic reports", 174(2), pp.543~548 (1990)
- "A free-text processing system to capture physical findings", ca(nical phrase identification system), pp.843~847 (1991)
- "Analysis of Korean morphology and information retrieval", pp.491~503 (2002)
- "Description of the CIRCUS system as used for MUC-3 Proceedings of the 3rd Message Understanding Conference" (1991), Morgan Kaufmann Publishers
- "Automatically acquiring conceptual patterns without and annotated corpus Proceedings of The Third Workshop on Very Large corpors" (1995)
- "An empirical study of automated dictionary construction for information extraction in three domain", 85, pp.101~134 (1996)
- "A pilot study of contextual UMLS indexing to improve the precision of concept-based representation in XML-structured clinical radiology reports", 10(6), pp.580~587 (2003)
- "A comparative study on the 'sign or symptom' concepts of the UMLS and clinical terms in Korean Medical Records Journal of Korean Society of Medical Informatics 2001", 7(4), pp.1~10 (2001)
- "Effective query expansion using condensed UMLS metathesaurus for medical information retrieval", 10(1), pp.43~53 (2004)
- "A study of effective Unified Medical Language System concept indexing in radiology reports", 10(3), pp.295~302 (2004)
- "Standardization of main concept in chief complaint based on SNOMED CT for utilization in electronic medical record", 9(3), pp.235~247 (2003)
- "Use of general-purpose negation detection to augment concept indexing of medical documents", pp.598~609