Extracting Drug-Drug Interactions with Word and Character-Level Recurrent Neural Networks

Ramakanth Kavuluru, Anthony Rios, Tung Tran

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

44 Scopus citations

Abstract

Drug-drug interactions (DDIs) are known to be responsible for nearly a third of all adverse drug reactions. Hence several current efforts focus on extracting signal from EMRs to prioritize DDIs that need further exploration. To this end, being able to extract explicit mentions of DDIs in free text narratives is an important task. In this paper, we explore recurrent neural network (RNN) architectures to detect and classify DDIs from unstructured text using the DDIExtraction dataset from the SemEval 2013 (task 9) shared task. Our methods are in line with those used in other recent deep learning efforts for relation extraction including DDI extraction. However, to our knowledge, we are the first to investigate the potential of character-level RNNs (Char-RNNs) for DDI extraction (and relation extraction in general). Furthermore, we explore a simple but effective model bootstrapping method to (a). build model averaging ensembles, (b). derive confidence intervals around mean micro-F scores (MMF), and (c). assess the average behavior of our methods. Without any rule based filtering of negative examples, a popular heuristic used by most earlier efforts, we achieve an MMF of 69.13. By adding simple replicable heuristics to filter negative instances we are able to achieve an MMF of 70.38. Furthermore, our best ensembles produce micro F-scores of 70.81 (without filtering) and 72.13 (with filtering), which are superior to metrics reported in published results. Although Char-RNNs turnout to be inferior to regular word based RNN models in overall comparisons, we find that ensembling models from both architectures results in nontrivial gains over simply using either alone, indicating that they complement each other.

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017
EditorsMollie Cummins, Julio Facelli, Gerrit Meixner, Christophe Giraud-Carrier, Hiroshi Nakajima
Pages5-12
Number of pages8
ISBN (Electronic)9781509048816
DOIs
StatePublished - Sep 8 2017
Event5th IEEE International Conference on Healthcare Informatics, ICHI 2017 - Park City, United States
Duration: Aug 23 2017Aug 26 2017

Publication series

NameProceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017

Conference

Conference5th IEEE International Conference on Healthcare Informatics, ICHI 2017
Country/TerritoryUnited States
CityPark City
Period8/23/178/26/17

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

Keywords

  • Drug-drug interactions
  • Recurrent neural networks
  • Relation classification

ASJC Scopus subject areas

  • Health Informatics

Fingerprint

Dive into the research topics of 'Extracting Drug-Drug Interactions with Word and Character-Level Recurrent Neural Networks'. Together they form a unique fingerprint.

Cite this