Bidirectional Recurrent Neural Networks for Medical Event Detection in Electronic Health Records
This work addresses a key step in health informatics for applications like pharmacovigilance, but it is incremental as it applies existing RNN methods to a specific domain.
The paper tackled the problem of medical event detection in electronic health records by comparing recurrent neural networks to conditional random fields, showing that RNNs significantly outperformed CRF models.
Sequence labeling for extraction of medical events and their attributes from unstructured text in Electronic Health Record (EHR) notes is a key step towards semantic understanding of EHRs. It has important applications in health informatics including pharmacovigilance and drug surveillance. The state of the art supervised machine learning models in this domain are based on Conditional Random Fields (CRFs) with features calculated from fixed context windows. In this application, we explored various recurrent neural network frameworks and show that they significantly outperformed the CRF models.