ABSTRACT
This paper reports on a shared task involving the assignment of ICD-9-CM codes to radiology reports. Two features distinguished this task from previous shared tasks in the biomedical domain. One is that it resulted in the first freely distributable corpus of fully anonymized clinical text. This resource is permanently available and will (we hope) facilitate future research. The other key feature of the task is that it required categorization with respect to a large and commercially significant set of labels. The number of participants was larger than in any previous biomedical challenge task. We describe the data production process and the evaluation measures, and give a preliminary analysis of the results. Many systems performed at levels approaching the inter-coder agreement, suggesting that human-like performance on this task is within the reach of currently available technologies.
- {Boutell et al., 2003} Boutell M., Shen X., Luo J. and Brown C. 2003. Multi-label Semantic Scene Classification, Technical Report 813. Department of Computer Science, University of Rochester September.Google Scholar
- {Cho et al., 2002} Cho P. S., Taira R. K., and Kangarloo H. 2002 Text boundary detection of medical reports. Proceedings of the Annual Symposium of the American Medical Informatics Association, 998.Google Scholar
- {Friedman et al., 2002} Friedman C., Kra P., and Rzhetsky A. 2002. Two biomedical sublanguages: a description based on the theories of Zellig Harris. Journal of Biomedical Informatics, 35:222--235. Google ScholarDigital Library
- {Gower and Legendre, 1986} Gower J. C. and Legendre P. 1986. Metric and euclidean properties of dissimilarity coefficient. Journal of Classification, 3:5--48.Google ScholarCross Ref
- {Hersh et al., 2004} Hersh W., Bhupatiraju R. T., Ross L., Roberts P., Cohen A. M., and Kraemer D. F. 2004. TREC 2004 Genomics track overview. Proceedings of the 13th Annual Text Retrieval Conference. National Institute of Standards and Technology.Google Scholar
- {Hersh et al., 2006} Hersh W., Cohen A. M., Roberts P., and Rekapalli H. K. 2006. TREC 2006 Genomics track overview. Proceedings of the 15th Annual Text Retrieval Conference National Institute of Standards and Technology.Google Scholar
- {Hersh et al., 2005} Hersh W., Cohen A. M., Yang J., Bhupatiraju R. T., Roberts P., and Hearst M. 2005. TREC 2005 Genomics track overview. Proceedings of the 14th Annual Text Retrieval Conference. National Institute of Standards and Technology.Google Scholar
- {Hirschman and Blaschke, 2006} Hirschman L. and Blaschke C. 2006. Evaluation of text mining in biology. Text mining for biology and biomedicine, Chapter 9. Ananiadou S. and McNaught J., editors. Artech House.Google Scholar
- {Hirschman and Sager, 1982} Hirschman L. and Sager S. 1982. Automatic information formatting of a medical sublanguage. Sublanguage: studies of language in restricted semantic domains, Chapter 2. Kittredge R. and Lehrberger J., editors. Walter de Gruyter.Google Scholar
- {Hurtado et al., 2001} Hurtado M. P, Swift E. K., and Corrigan J. M. 2001. Crossing the Quality Chasm: A New Health System for the 21st Century. Institute of Medicine, National Academy of Sciences.Google Scholar
- {Jackson and Moulinier, 2002} Jackson P. and Moulinier I. 2002. Natural language processing for online applications: text retrieval, extraction, and categorization. John Benjamins Publishing Co.Google Scholar
- {Lang, 2007} Lang, D. 2007. CONSULTANT REPORT - Natural Language Processing in the Health Care Industry. Cincinnati Children's Hospital Medical Center, Winter 2007.Google Scholar
- {Moisio, 2000} Moisio M. 2000. A Guide to Health Care Insurance Billing. Thomson Delmar Learning, Clifton Park.Google Scholar
- {Pestian et al., 2005} Pestian J. P., Itert L., Andersen C. L., and Duch W. 2005. Preparing Clinical Text for Use in Biomedical Research. Journal of Database Management, 17(2):1--12.Google ScholarCross Ref
- {Pestian et al., 2004} Pestian J. P., Itert L., and Duch W. 2004. Development of a Pediatric Text-Corpus for Part-of-Speech Tagging. Intelligent Information Processing and Web Mining, Advances in Soft Computing, 219--226 New York, Springer Verlag.Google Scholar
- {Sammuelsson and Wiren, 2000} Sammuelsson C. and Wiren M. 2000. Parsing Techniques. Handbook of Natural Language Processing, 59--93. Dale R., Moisl H., Somers H., editors. New York, Marcel Deker.Google Scholar
- {Sibanda and Uzuner, 2006} Sibanda T. and Uzuner O. 2006. Role of local context in automatic deidentification of ungrammatical, fragmented text. Proceedings of the Human Language Technology conference of the North American chapter of the Association for Computational Linguistics, 65--73. Google ScholarDigital Library
- {Stetson et al., 2002} Stetson P. D., Johnson S. B., Scotch M., and Hripcsak G. 2002. The sublanguage of cross-coverage. Proceedings of the Annual Symposium of the American Medical Informatics Association, 742--746.Google Scholar
- {U.S. Health, 2002} U.S. Heath&Human Services. 2002. 45 CFR Parts 160 and 164 Standards for Privacy of Individually Identifiable Health Information Final Rule Federal Register, 67(157):53181--53273.Google Scholar
- {Uzuner et al., 2006} Uzuner O., Szolovits P., and Kohane I. 2006. i2b2 workshop on natural language processing challenges for clinical records. Proceedings of the Fall Symposium of the American Medical Informatics Association.Google Scholar
- {Walters, 2004} Walters S. J. 2004. Sample size and power estimation for studies with health related quality of life outcomes: a comparison of four methods using the SF-36 Health and Quality of Life Outcomes, 2:26.Google Scholar
- A shared task involving multi-label classification of clinical free text
Recommendations
Adversarial Multi-task Label Embedding for Text Classification
CIIS '19: Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent SystemsMulti-task learning makes use of the potential correlation among related tasks to perform well in text classification. However, in the most multi-task works, labels are converted to meaningless one-hot vectors, which cause the loss of label semantics ...
Label-sensitive task grouping by Bayesian nonparametric approach for multi-task multi-label learning
IJCAI'18: Proceedings of the 27th International Joint Conference on Artificial IntelligenceMulti-label learning is widely applied in many real-world applications, such as image and gene annotation. While most of the existing multilabel learning models focus on the single-task learning problem, there are always some tasks that share some ...
Semi-supervised multi-label classification using incomplete label information
Highlights- An inductive semi-supervised method called Smile is proposed for multi-label classification using incomplete label information.
AbstractClassifying multi-label instances using incompletely labeled instances is one of the fundamental tasks in multi-label learning. Most existing methods regard this task as supervised weak-label learning problem and assume sufficient ...
Comments