Section Heading Recognition in Electronic Health Records Using Conditional Random Fields
Electronic health records (EHRs) contain a wealth of information, such as discharge diagnoses, laboratory results, and pharmacy orders, which can be used to support clinical decision support systems and enable clinical and translational research. Unfortunately, the information is represented in a highly heterogeneous semi-structured or unstructured format with author- and domain-specific idiosyncrasies, acronyms and abbreviations. To take full advantage of health data, text-mining techniques have been applied by researchers to recognize named entities (NEs) mentioned in EHRs. However, the judgment of clinical data cannot be known solely from the NE level. For instance, a disease mention in the section of past medical history has different clinical significance when mentioned in the family medical history section. To obtain high-quality information and improve the understanding of clinical records, this work developed a machine learning-based section heading recognition system and evaluated its performance on a manually annotated corpus. The experiment results showed that the machine learning-based system achieved a satisfactory F-score of 0.939, which outperformed a dictionary-based system by 0.321.
KeywordsInformation Extraction Natural Language Processing Electronic Health Record Section Recognition
Unable to display preview. Download preview PDF.
- 1.Aronson, A.: Effective Mapping of Biomedical Text to the UMLS Metathesaurus: The MetaMap Program. Journal of Biomedical Informatic 35, 17–21 (2001)Google Scholar
- 2.Denny, J.C., Miller, R.A., Johnson, K.B., Spickard III, A.: Development and evaluation of a clinical note section header terminology. In: AMIA Annu. Symp. Proc., pp. 156–160 (2008)Google Scholar
- 4.Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proceedings of the 18th International Conference on Machine Learning (ICML), pp. 282–289 (2001)Google Scholar
- 5.Savova, G.K., Masanz, J.J., Ogren, P.V., Zheng, J., Sohn, S., Kipper-Schuler, K.C., Chute, C.G.: Mayo clinical Text Analysis and Knowledge Extraction System (cTAKES): architecture, component evaluation and applications. Journal of the American Medical Informatics Association 17(5), 507–513 (2010)CrossRefGoogle Scholar
- 7.Stubbs, A., Kotfila, C., Xu, H., Uzuner, O.: Practical applications for NLP in Clinical Research: the 2014 i2b2/UTHealth shared tasks. In: Proceedings of the i2b2 2014 Shared Task and Workshop Challenges in Natural Language Processing for Clinical Data (2014)Google Scholar
- 8.Tsai, R.T.-H., Sung, C.-L., Dai, H.-J., Hung, H.-C., Sung, T.-Y., Hsu, W.-L.: NERBio: using selected word conjunctions, term normalization, and global patterns to improve biomedical named entity recognition. BMC Bioinformatics7(suppl. 5), S11 (2006)Google Scholar