Email updates

Keep up to date with the latest news and content from BMC Medical Informatics and Decision Making and BioMed Central.

Open Access Research article

Mining FDA drug labels for medical conditions

Qi Li1, Louise Deleger1, Todd Lingren1, Haijun Zhai1, Megan Kaiser1, Laura Stoutenborough1, Anil G Jegga1, Kevin Bretonnel Cohen2 and Imre Solti13*

Author Affiliations

1 Division of Biomedical Informatics, Department of Pediatrics, University of Cincinnati, Cincinnati, OH, USA

2 Computational Bioscience Program, University of Colorado School of Medicine, Aurora, CO, USA

3 Anderson Center for Health Systems Excellence, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA

For all author emails, please log on.

BMC Medical Informatics and Decision Making 2013, 13:53  doi:10.1186/1472-6947-13-53

Published: 24 April 2013

Abstract

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.

Keywords:
Medical condition; Disease and disorders; Sign and symptoms; cTAKES; NLP; Natural language processing; IE; Information extraction; CRF; Conditional random fields; FDA drug labels