Mining FDA drug labels for medical conditions.
Background: Cincinnati Children's Hospital Medical Center (CCHMC) has built the initial Natural Language Processing (NLP) component to extract medications with their corresponding medical conditions (Indications, Contraindications, Overdosage, and Adverse Reactions) as triples of medication-related...
| Publicado en: | BMC Medical Informatics & Decision Making Vol. 13; no. 1; pp. 53 - 54 |
|---|---|
| Autores principales: | , , , , , , , , |
| Formato: | Journal Article |
| Publicado: |
BioMed Central
2013
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=104283786&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 104283786 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 14726947 1CI0 jtl: BMC Medical Informatics & Decision Making issn: 14726947 maglogo: N pubinfo: dt: 2013 vid: 13 iid: 1 pid: 24147 pub: BioMed Central artinfo: ui: 104283786 NLM23617267 2012111962 10.1186/1472-6947-13-53 NLM23617267 PMC3646673 104283786 ppf: 53 ppct: 1 formats: tig: atl: Mining FDA drug labels for medical conditions. aug: au: Li, Qi Deleger, Louise Lingren, Todd Zhai, Haijun Kaiser, Megan Stoutenborough, Laura Jegga, Anil G Cohen, Kevin Bretonnel Solti, Imre affil: Division of Biomedical Informatics, Department of Pediatrics, University of Cincinnati, Cincinnati, OH, USA. Imre.Solti@cchmc.org. sug: subj: Adverse Drug Event Data Mining Methods Drug Labeling United States Food and Drug Administration Medication Systems Natural Language Processing Ohio United States ab: Background: Cincinnati Children's Hospital Medical Center (CCHMC) has built the initial Natural Language Processing (NLP) component to extract medications with their corresponding medical conditions (Indications, Contraindications, Overdosage, and Adverse Reactions) as triples of medication-related information ([(1) drug name]-[(2) medical condition]-[(3) LOINC section header]) for an intelligent database system, in order to improve patient safety and the quality of health care. The Food and Drug Administration's (FDA) drug labels are used to demonstrate the feasibility of building the triples as an intelligent database system task.Methods: This paper discusses a hybrid NLP system, called AutoMCExtractor, to collect medical conditions (including disease/disorder and sign/symptom) from drug labels published by the FDA. Altogether, 6,611 medical conditions in a manually-annotated gold standard were used for the system evaluation. The pre-processing step extracted the plain text from XML file and detected eight related LOINC sections (e.g. Adverse Reactions, Warnings and Precautions) for medical condition extraction. Conditional Random Fields (CRF) classifiers, trained on token, linguistic, and semantic features, were then used for medical condition extraction. Lastly, dictionary-based post-processing corrected boundary-detection errors of the CRF step. We evaluated the AutoMCExtractor on manually-annotated FDA drug labels and report the results on both token and span levels.Results: Precision, recall, and F-measure were 0.90, 0.81, and 0.85, respectively, for the span level exact match; for the token-level evaluation, precision, recall, and F-measure were 0.92, 0.73, and 0.82, respectively.Conclusions: The results demonstrate that (1) medical conditions can be extracted from FDA drug labels with high performance; and (2) it is feasible to develop a framework for an intelligent database system. pubtype: Academic Journal doctype: Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|