Automagically Encoding Adverse Drug Reactions in MedDRA

Pharmacovigilance is the field of science devoted to the collection, analysis, and prevention of Adverse Drug Reactions (ADRs). Efficient strategies for the extraction of information about ADRs from free text sources are essential to support the important task of detecting and classifying unexpected pathologies, possibly related to (therapy-related) drug use. Narrative ADR descriptions may be collected in different ways, e.g., Either by monitoring social networks or through the so called "spontaneous reporting, the main method pharmacovigilance adopts in order to identify ADRs. The encoding of free-text ADR descriptions according to MedDRA standard terminology is central for report analysis. It is a complex work, which has to be manually implemented by the pharmacovigilance experts. The manual encoding is expensive (in terms of time). Moreover, a problem about the accuracy of the encoding may occur, since the number of reports is growing up day by day. In this paper, we propose Magi Coder, an efficient Natural Language Processing algorithm able to automatically derive MedDRA terminologies from free text ADR descriptions. Magi Coder is part of Vigi Work, a web application for online ADR reporting and analysis. From a practical point of view, Magi Coder reduces the encoding time of ADR reports. Pharmacologists have simply to review and validate the MedDRA terms proposed by Magi Coder, instead of choosing the right terms among the 70K terms of MedDRA. Such improvement in the efficiency of pharmacologists' work has a relevant impact also on the quality of the following data analysis. Our proposal is based on a general approach, not depending on the considered language. Indeed, we developed Magi Coder for the Italian pharmacovigilance language, but preliminarily analyses show that it is robust to language and dictionary changes.

[1]  Xiaoyan Wang,et al.  Active computerized pharmacovigilance using natural language processing, statistics, and electronic health records: a feasibility study. , 2009, Journal of the American Medical Informatics Association : JAMIA.

[2]  Marcin Sydow,et al.  String Distance Metrics for Reference Matching and Search Query Correction , 2007, BIS.

[3]  Abeed Sarker,et al.  Portable automatic text classification for adverse drug reaction detection via multi-corpus training , 2015, J. Biomed. Informatics.

[4]  James H. Martin,et al.  Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition , 2000 .

[5]  Gunnar Dahlberg,et al.  Implementation and evaluation of a text extraction tool for adverse drug reaction information , 2010 .

[6]  A. Bate,et al.  Quantitative signal detection using spontaneous ADR reporting , 2009, Pharmacoepidemiology and drug safety.

[7]  Luca Toldo,et al.  Extraction of potential adverse drug events from medical case reports , 2012, Journal of biomedical semantics.

[8]  Laurie Bauer,et al.  Introducing Linguistic Morphology , 1988 .

[9]  Carol Friedman,et al.  Discovering Novel Adverse Drug Events Using Natural Language Processing and Mining of the Electronic Health Record , 2009, AIME.

[10]  Geoffrey Sampson,et al.  The Oxford Handbook of Computational Linguistics , 2003, Lit. Linguistic Comput..

[11]  Carol Friedman,et al.  Mining multi-item drug adverse effect associations in spontaneous reporting systems , 2010, BMC Bioinformatics.

[12]  Alberto Sabaini.  Temporal Data Analysis and Mining. A Multidimensional Approach and its Application in a Medical Domain , 2015 .

[13]  Stephen Mifsud,et al.  Strengthening and Rationalizing Pharmacovigilance in the EU: Where is Europe Heading to? , 2011, Drug safety.

[14]  Ruslan Mitkov,et al.  The Oxford handbook of computational linguistics , 2003 .

[15]  Chris Fox,et al.  The Handbook of Computational Linguistics and Natural Language Processing , 2010 .

[16]  Lise Aagaard,et al.  Global patterns of adverse drug reactions over a decade: analyses of spontaneous reports to VigiBase™. , 2012, Drug safety.

[17]  Yuval Shahar,et al.  An Active Learning Framework for Efficient Condition Severity Classification , 2015, AIME.

[18]  James H. Martin,et al.  Speech and language processing: an introduction to natural language processing , 2000 .

[19]  William R. Hersh,et al.  A Survey of Current Work in Biomedical Text Mining , 2005 .

[20]  Kazuhiko Ohe,et al.  Extraction of Adverse Drug Effects from Clinical Records , 2010, MedInfo.

[21]  Christopher C. Yang,et al.  Social media mining for drug safety signal detection , 2012, SHB '12.

[22]  Kazuaki Kishida,et al.  Technical issues of cross-language information retrieval: a review , 2005, Inf. Process. Manag..

[23]  Kevin M. Heard,et al.  Computerized surveillance for adverse drug events in a pediatric hospital. , 2008, AMIA ... Annual Symposium proceedings. AMIA Symposium.

[24]  P. Kilbridge,et al.  Natural language processing to identify adverse drug events. , 2008, AMIA ... Annual Symposium proceedings. AMIA Symposium.

[25]  Michael Collins.  Tutorial: Machine Learning Methods in Natural Language Processing , 2003, COLT.

[26]  Ebba Holme Hansen,et al.  Global Patterns of Adverse Drug Reactions Over a Decade , 2012, Drug Safety.