HTNSystem: Hypertension Information Extraction System for Unstructured Clinical Notes
Hypertension (HTN) relevant information has great application potential in cohort discovery and building predictive models for prevention and surveillance. Unfortunately most of this valuable patient information is buried in the form of unstructured clinical notes. In this study we present HTN information extraction system called HTNSystem which is capable of extracting mentions of HTN and inferring HTN from BP lab values. HTNSystem is a rule based system which implements MetaMap as a core component together with custom built BP value extractor and post processing components. It is evaluated on a corpus of 514 clinical notes (82.92% F-measure). HTNSystem is distributed as an open source command line tool available at https://github.com/TCRNBioinformatics/HTNSystem .
KeywordsHypertension Blood pressure Information extraction Rule based Apache UIMA Apache Ruta Text mining
Unable to display preview. Download preview PDF.
- 2.Organization, W.H., I.S.O.H.W Group: World Health Organization (WHO)/International Society of Hypertension (ISH) statement on management of hypertension. Journal of hypertension 21(11), 1983–1992 (2003)Google Scholar
- 6.Turchin, A., Pendergrass, M.L., Kohane, I.S.: DITTO–a Tool for Identification of Patient Cohorts from the Text of Physician Notes in the Electronic Medical Record. In: AMIA Annual Symposium Proceedings. American Medical Informatics Association (2005)Google Scholar
- 8.Chang, N.-W., et al.: TMUNSW System for Risk Factor Recognition and Progression Tracking. In: Proceedings of the 2014 i2b2/UTHealth Shared-Tasks and Workshop on Challenges in Natural Language Processing for Clinical Data (2014)Google Scholar
- 9.Jonnagaddala, J., et al.: Coronary heart disease risk assessment from unstructured clinical notes using Framingham risk score. In: Proceedings of the 2014 i2b2/UTHealth Shared-Tasks and Workshop on Challenges in Natural Language Processing for Clinical Data (2014)Google Scholar
- 10.Stubbs, A., et al.: Practical applications for NLP in Clinical Research: the 2014 i2b2/UTHealth shared tasks (2014)Google Scholar
- 11.Jonnagaddala, J., et al.: TMUNSW: Disorder Concept Recognition and Normalization in Clinical Notes for SemEval-2014 Task 7. In: 8th International Workshop on Semantic Evaluation (SemEval 2014), Dublin, Ireland, August 23-24. ACL Anthology (2014)Google Scholar
- 12.Greenberg, J.O., et al.: Meaningful measurement: developing a measurement system to improve blood pressure control in patients with chronic kidney disease. Journal of the American Medical Informatics Association, p. amiajnl-2012-001308 (2013)Google Scholar
- 14.Gooch, P., Roudsari, A.: A tool for enhancing MetaMap performance when annotating clinical guideline documents with UMLS concepts (2011)Google Scholar
- 15.Osborne, R.M., Aronson, A.R., Cohen, K.B.: A repository of semantic types in the MIMIC II database clinical notes. In: ACL 2014, p. 93 (2014)Google Scholar
- 16.Jonquet, C., Shah, N.H., Musen, M.A.: The open biomedical annotator. Summit on Translational Bioinformatics, 56 (2009)Google Scholar