Bidirectional LSTM-CRF for Adverse Drug Event Tagging in Electronic Health Records

Susmitha Wunnava, Xiao Qin, Tabassum Kakar, Elke A. Rundensteiner, Xiangnan Kong
Proceedings of the 1st International Workshop on Medication and Adverse Drug Event Detection, PMLR 90:48-56, 2018.

Abstract

Adverse drug event (ADE) detection is a vital step towards effective pharmacovigilance and prevention of future incidents caused by potentially harmful ADEs. Electronic health records (EHRs) of patients in hospitals contain valuable information regarding the ADEs and hence are an important source for detecting ADE signals. We have developed a deep learning based system that utilizes a three layered deep learning architecture of 1) RNN (bi-directional long short-term memory (bi-LSTM)) for character-level word representation 2) bi-LSTM for context representation and 3) Conditional Random Fields (CRF) for the final output prediction, by integrating them into one deep network architecture. Furthermore, we have developed customized rule-based tokenization techniques for preprocessing text to deal with the noise in the EHR text. In this paper, we share our system architecture and its performance w.r.t the MADE1.0 NLP challenge.

Cite this Paper

BibTeX
@InProceedings{pmlr-v90-wunnava18a, title = {Bidirectional LSTM-CRF for Adverse Drug Event Tagging in Electronic Health Records}, author = {Wunnava, Susmitha and Qin, Xiao and Kakar, Tabassum and Rundensteiner, Elke A. and Kong, Xiangnan}, booktitle = {Proceedings of the 1st International Workshop on Medication and Adverse Drug Event Detection}, pages = {48--56}, year = {2018}, editor = {Liu, Feifan and Jagannatha, Abhyuday and Yu, Hong}, volume = {90}, series = {Proceedings of Machine Learning Research}, month = {04 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v90/wunnava18a/wunnava18a.pdf}, url = {https://proceedings.mlr.press/v90/wunnava18a.html}, abstract = {Adverse drug event (ADE) detection is a vital step towards effective pharmacovigilance and prevention of future incidents caused by potentially harmful ADEs. Electronic health records (EHRs) of patients in hospitals contain valuable information regarding the ADEs and hence are an important source for detecting ADE signals. We have developed a deep learning based system that utilizes a three layered deep learning architecture of 1) RNN (bi-directional long short-term memory (bi-LSTM)) for character-level word representation 2) bi-LSTM for context representation and 3) Conditional Random Fields (CRF) for the final output prediction, by integrating them into one deep network architecture. Furthermore, we have developed customized rule-based tokenization techniques for preprocessing text to deal with the noise in the EHR text. In this paper, we share our system architecture and its performance w.r.t the MADE1.0 NLP challenge.} }
Endnote
%0 Conference Paper %T Bidirectional LSTM-CRF for Adverse Drug Event Tagging in Electronic Health Records %A Susmitha Wunnava %A Xiao Qin %A Tabassum Kakar %A Elke A. Rundensteiner %A Xiangnan Kong %B Proceedings of the 1st International Workshop on Medication and Adverse Drug Event Detection %C Proceedings of Machine Learning Research %D 2018 %E Feifan Liu %E Abhyuday Jagannatha %E Hong Yu %F pmlr-v90-wunnava18a %I PMLR %P 48--56 %U https://proceedings.mlr.press/v90/wunnava18a.html %V 90 %X Adverse drug event (ADE) detection is a vital step towards effective pharmacovigilance and prevention of future incidents caused by potentially harmful ADEs. Electronic health records (EHRs) of patients in hospitals contain valuable information regarding the ADEs and hence are an important source for detecting ADE signals. We have developed a deep learning based system that utilizes a three layered deep learning architecture of 1) RNN (bi-directional long short-term memory (bi-LSTM)) for character-level word representation 2) bi-LSTM for context representation and 3) Conditional Random Fields (CRF) for the final output prediction, by integrating them into one deep network architecture. Furthermore, we have developed customized rule-based tokenization techniques for preprocessing text to deal with the noise in the EHR text. In this paper, we share our system architecture and its performance w.r.t the MADE1.0 NLP challenge.
APA
Wunnava, S., Qin, X., Kakar, T., Rundensteiner, E.A. & Kong, X.. (2018). Bidirectional LSTM-CRF for Adverse Drug Event Tagging in Electronic Health Records. Proceedings of the 1st International Workshop on Medication and Adverse Drug Event Detection, in Proceedings of Machine Learning Research 90:48-56 Available from https://proceedings.mlr.press/v90/wunnava18a.html.

Related Material