Medical Entity Recognition and Negation Extraction: Assessment of NegEx on Health Records in Spanish
This work focuses on biomedical text mining. The core of this work is to make a step ahead in the negation detection of biomedical entities on Electronic Health Records (EHRs), where the detection of non-negated entities is as important as the identification of negated entities. For instance, the identification of a negated entity as factual, can produce diagnostic errors in decision support systems.
Negated entity recognition tackles two tasks: (1) entity recognition; (2) entity classification as negated or not. To identify negations, in the literature rule-based and machine-learning techniques have been used. This paper presents an adaptation of the rule-based system NegEx, which uses exact-matching for the aforementioned tasks.
Our contribution consist in assessing the aforementioned two tasks and explored alternatives for each of them, in such a way that the negation detection improves when the entity recognition is able to detect more entities correctly.
The evaluation was carried out within a real domain of 75 EHRs written in Spanish obtaining an f-measure of 76.2 for entity recognition and 73.8 for negation detection.
KeywordsNegation detection Electronic health records Text mining Spanish
- 1.Blanco, E., Moldovan, D.I.: Some issues on detecting negation from text. In: FLAIRS (2011)Google Scholar
- 3.Ceusters, W., Elkin, P., Smith, B.: Negative findings in electronic health records and biomedical ontologies: a realist approach. Int. J. Med. Inform. 76, 326–333 (2017)Google Scholar
- 5.Costumero, R., Lopez, F., Gonzalo-Martín, C., Millan, M., Menasalvas, E.: An approach to detect negation on medical documents in Spanish. In: Ślȩzak, D., Tan, A.-H., Peters, J.F., Schwabe, L. (eds.) BIH 2014. LNCS (LNAI), vol. 8609, pp. 366–375. Springer, Heidelberg (2014). doi:10.1007/978-3-319-09891-3_34 Google Scholar
- 7.Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the Eighteenth International Conference on Machine Learning, ICML, vol. 1, pp. 282–289 (2001)Google Scholar
- 8.Nakov, P., Zesch, T. (eds.): Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014). Association for Computational Linguistics and Dublin City University, Dublin, Ireland (2014)Google Scholar
- 11.Skeppstedt, M.: Negation detection in swedish clinical text. In: Proceedings of the NAACL HLT 2010 Second Louhi Workshop on Text and Data Mining of Health Documents, pp. 15–21. Association for Computational Linguistics (2010)Google Scholar
- 12.Skeppstedt, M., Dalianis, H., Nilsson, G.H.: Retrieving disorders and findings: results using SNOMED CT and NegEx adapted for swedish. In: Third International Workshop on Health Document Text Mining and Information AnalysisBled, Slovenia, 6 July 2011, Bled Slovenia, Collocated with AIME 2011, pp. 11–17 (2011)Google Scholar
- 13.Weegar, R., Kvist, M., Sundström, K., Brunak, S., Dalianis, H.: Finding cervical cancer symptoms in swedish clinical text using a machine learning approach and NegEx. In: AMIA Annual Symposium Proceedings. vol. 2015, p. 1296. American Medical Informatics Association (2015)Google Scholar