INTRODUCTION: Adverse drug event (ADE) detection is a vital step towards effective pharmacovigilance and prevention of future incidents caused by potentially harmful ADEs. The electronic health records (EHRs) of patients in hospitals contain valuable information regarding ADEs and hence are an important source for detecting ADE signals. However, EHR texts tend to be noisy. Yet applying off-the-shelf tools for EHR text preprocessing jeopardizes the subsequent ADE detection performance, which depends on a well tokenized text input. OBJECTIVE: In this paper, we report our experience with the NLP Challenges for Detecting Medication and Adverse Drug Events from Electronic Health Records (MADE1.0), which aims to promote deep innovations on this subject. In particular, we have developed rule-based sentence and word tokenization techniques to deal with the noise in the EHR text. METHODS: We propose a detection methodology by adapting a three-layered, deep learning architecture of (1) recurrent neural network [bi-directional long short-term memory (Bi-LSTM)] for character-level word representation to encode the morphological features of the medical terminology, (2) Bi-LSTM for capturing the contextual information of each word within a sentence, and (3) conditional random fields for the final label prediction by also considering the surrounding words. We experiment with different word embedding methods commonly used in word-level classification tasks and demonstrate the impact of an integrated usage of both domain-specific and general-purpose pre-trained word embedding for detecting ADEs from EHRs. RESULTS: Our system was ranked first for the named entity recognition task in the MADE1.0 challenge, with a micro-averaged F1-score of 0.8290 (official score). CONCLUSION: Our results indicate that the integration of two widely used sequence labeling techniques that complement each other along with dual-level embedding (character level and word level) to represent words in the input layer results in a deep learning architecture that achieves excellent information extraction accuracy for EHR notes.
INTRODUCTION: Adverse drug event (ADE) detection is a vital step towards effective pharmacovigilance and prevention of future incidents caused by potentially harmful ADEs. The electronic health records (EHRs) of patients in hospitals contain valuable information regarding ADEs and hence are an important source for detecting ADE signals. However, EHR texts tend to be noisy. Yet applying off-the-shelf tools for EHR text preprocessing jeopardizes the subsequent ADE detection performance, which depends on a well tokenized text input. OBJECTIVE: In this paper, we report our experience with the NLP Challenges for Detecting Medication and Adverse Drug Events from Electronic Health Records (MADE1.0), which aims to promote deep innovations on this subject. In particular, we have developed rule-based sentence and word tokenization techniques to deal with the noise in the EHR text. METHODS: We propose a detection methodology by adapting a three-layered, deep learning architecture of (1) recurrent neural network [bi-directional long short-term memory (Bi-LSTM)] for character-level word representation to encode the morphological features of the medical terminology, (2) Bi-LSTM for capturing the contextual information of each word within a sentence, and (3) conditional random fields for the final label prediction by also considering the surrounding words. We experiment with different word embedding methods commonly used in word-level classification tasks and demonstrate the impact of an integrated usage of both domain-specific and general-purpose pre-trained word embedding for detecting ADEs from EHRs. RESULTS: Our system was ranked first for the named entity recognition task in the MADE1.0 challenge, with a micro-averaged F1-score of 0.8290 (official score). CONCLUSION: Our results indicate that the integration of two widely used sequence labeling techniques that complement each other along with dual-level embedding (character level and word level) to represent words in the input layer results in a deep learning architecture that achieves excellent information extraction accuracy for EHR notes.
Authors: Guergana K Savova; James J Masanz; Philip V Ogren; Jiaping Zheng; Sunghwan Sohn; Karin C Kipper-Schuler; Christopher G Chute Journal: J Am Med Inform Assoc Date: 2010 Sep-Oct Impact factor: 4.497
Authors: Donald C Comeau; Rezarta Islamaj Doğan; Paolo Ciccarese; Kevin Bretonnel Cohen; Martin Krallinger; Florian Leitner; Zhiyong Lu; Yifan Peng; Fabio Rinaldi; Manabu Torii; Alfonso Valencia; Karin Verspoor; Thomas C Wiegers; Cathy H Wu; W John Wilbur Journal: Database (Oxford) Date: 2013-09-18 Impact factor: 3.451
Authors: Likeng Liang; Jifa Hu; Gang Sun; Na Hong; Ge Wu; Yuejun He; Yong Li; Tianyong Hao; Li Liu; Mengchun Gong Journal: Drug Saf Date: 2022-05-17 Impact factor: 5.228
Authors: Xi Yang; Jiang Bian; Ruogu Fang; Ragnhildur I Bjarnadottir; William R Hogan; Yonghui Wu Journal: J Am Med Inform Assoc Date: 2020-01-01 Impact factor: 4.497