Xiaohua Zhou
ABSTRACT
Clinical medical records contain a wealth of information, largely in free-text form. Means to extract structured information from free-text records is an important research endeavor. In this paper, we describe a MEDical Information Extraction (MedIE) system that extracts and mines a variety of patient information with breast complaints from free-text clinical records. MedIE is a part of medical text mining project being conducted in Drexel University. Three approaches are proposed to solve different IE tasks and very good performance (precision and recall) was achieved. A graph-based approach which uses the parsing result of link-grammar parser was invented for relation extraction; high accuracy was achieved. A simple but efficient ontology-based approach was adopted to extract medical terms of interest. Finally, an NLP-based feature extraction method coupled with an ID3-based decision tree was used to perform text classification.
- Cunningham, H., "GATE, A General Architecture for Text Engineering", Computers and the Humanities, 2002, Vol. 36, pp. 223--254Google Scholar
Cross Ref
- Cunningham, H., Maynard, D., and Tablan., V., "JAPE: a Java Annotation Patterns Engine (Second Edition)", Technical report CS-00-10, University of Sheffield, Department of Computer Science, 2000.Google Scholar
- Dimitrov, M., Bontcheva, K., Cunningham, H., and Maynard, D., "A Light-weight Approach to Coreference Resolution for Named Entities in Text", Proceedings of the Fourth Discourse Anaphora and Anaphor Resolution Colloquium (DAARC), Lisbon, 2002.Google Scholar
- Ding, J., Berleant, D., Xu, J., and Fulmer, A. W., "Extracting Biochemical Interactions from MEDLINE Using a Link Grammar Parser", In the 15th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'03), 2003. Google ScholarDigital Library
- Gaizauskas, R., Hepple, M., Davis, N., Guo, Y., Harkema, H, Roberts, A., and Roberts, I., "AMBIT: Acquiring Medical and Biological Information from Text", ISMB/ECCB, Poster, 2004.Google Scholar
- Kim, J. T. and Moldovan, D. I., "Acquisition of Linguistic Patterns for Knowledge-Based Information Extraction", IEEE Transactions on Knowledge and Data Engineering, Volume 7, Issue 5, 1995, pp. 713--724. Google ScholarDigital Library
- Kuhn, R. and Mori, R., "Application of Semantic Classification Trees to Natural Language Understanding", IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, Vol. 17, No. 5. Google ScholarDigital Library
- Lehnert, W., Soderland, S., Aronow, D., Feng, F., and Shmueli, A., "Inductive Text Classification for Medical Applications", Journal for Experimental and Theoretical Artificial Intelligence, 1994, 7(1), pp. 49--80.Google ScholarCross Ref
- Madhyastha, H. V., Balakrishnan, N., and Ramakrishnan, K. R., "Event Information Extraction Using Link Grammar", 13th International Workshop on Research Issues in Data Engineering: Multi-lingual Information Management (RIDE'03), 2003.Google ScholarCross Ref
- Miller, G. et al, "WordNet: an On-line Lexical Database", International Journal of Lexicography, 1990, pp. 235--245.Google ScholarCross Ref
- Quinlan, J. R., "Induction of Decision Trees", Machine Learning, 1986, No.1, pp. 81--106. Google ScholarCross Ref
- Riloff, E., "Automatically Constructing a Dictionary for Information Extraction Tasks", Proceedings of the Eleventh National Conference on Artificial Intelligence, AAAI Press/the MIT Press, 1993, pp. 811--816Google Scholar
- Riloff, E. and Lehnert, W., "Information Extraction as a Basis for High-Precision Text Classification", ACM Transactions on Information Systems, 1994, Vol. 12, No. 3, pp. 296--333. Google ScholarDigital Library
- Sleator, D. and Temperley D., "Parsing English with a Link Grammar", Third International Workshop on Parsing Technologies, 1993.Google Scholar
- Soderland, S., Aronow, D., Fisher, D., Aseltine, J., and Lehnert, W., "Machine Learning of Text Analysis Rules for Clinical Records", CIIR Technical Report, University of Massachusetts Amherst, 1995.Google Scholar
- Soderland, S., Fisher, D., Aseltine, J., and Lehnert, W., "CRYSTAL: Inducing a Conceptual Dictionary", Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, 1995, pp. 1314--1319. Google ScholarDigital Library
- Soderland, S., "Learning Information Extraction rules for Semi-structured and free text", Machine Learning, Vol. 34, 1998, pp. 233--272. Google ScholarDigital Library
- Szolovits, P., "Adding a Medical Lexicon to an English Parser", Proc. AMIA 2003 Annual Symposium, 2003.Google Scholar
- Zhou, X., Han, H., Chankai, I., Prestrud, A. A., and Brooks, A. D., "Converting Semi-structured Clinical Medical Records into Information and Knowledge", In the International Workshop on Biomedical Data Engineering in conjunction with the 21st International Conference on Data Engineering (ICDE), Tokyo, Japan, April 3-4, 2005. Google ScholarDigital Library
Index Terms
- Approaches to text mining for clinical medical records
Recommendations
Semantic-based exchanger of electronic medical records
MoMM '08: Proceedings of the 6th International Conference on Advances in Mobile Computing and MultimediaConsidering the importance of the patient's medical information for the caregivers to ensure that patients receive appropriate and safe treatment, especially the emergency room (ER) patients, thus, sharing distributed medical information among ...
Anonymizing and Sharing Medical Text Records
Health information technology has increased accessibility of health and medical data and benefited medical research and healthcare management. However, there are rising concerns about patient privacy in sharing medical and healthcare data. A large ...
Fever detection from free-text clinical records for biosurveillance
Automatic detection of cases of febrile illness may have potential for early detection of outbreaks of infectious disease either by identification of anomalous numbers of febrile illness or in concert with other information in diagnosing specific ...
Reviews
Andrew Brooks
Text mining works. Precision and recall rates for classification (for example, smoking status), attribute extraction (for example, blood pressure), and medical term extraction (for example, past surgical history) for the Java-based MedIE system on 125 free-text clinical records were at least 86 percent and often better. MedIE comprises three main techniques. Classification tasks make use of the ID3 decision tree algorithm. Attribute extraction makes use of a graph-based approach from output produced by the link grammar parser. Medical term extraction makes use of the unified medical language system (UMLS) as the domain ontology. Although it is impossible to convey every detail of a complex system or experiment, the explanations of the three main techniques and experimental results are too brief. The reader is left with many questions unanswered: How much did using part-of-speech patterns reduce the computational complexity of medical term extraction__?__ How were negating words or phrases dealt with__?__ How often was a pattern approach taken when the link grammar parser failed to parse a sentence__?__ How long did MedIE take compared to the human coder that was employed as the oracle__?__ Why are precision and recall clearly distinguished in Table 3 but not in Tables 1 and 2__?__ Surprisingly missing is the final step: that of data mining on the text-mined data itself. Despite this, and the brevity of the explanations, this paper represents a key milestone in text mining and as such is strongly recommended to anyone working in data or text mining. Online Computing Reviews Service
Access critical reviews of Computing literature here
Become a reviewer for Computing Reviews.
Comments