Bidirectional RNN for Medical Event Detection in Electronic Health Records

By Abhyuday N. Jagannatha, Hong Yu. 2016

294 citations recorded by the source corpus.

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 recurrent neural network frameworks1 and show that they significantly out-performed the CRF models.

Subfields: Artificial Intelligence, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

Natural Language Processing for EHR-Based Computational Phenotyping (2018, background): “[161], [162] experimented with recurrent neural networks (RNNs), long shortterm memory (LSTM), gated recurrent units (GRUs), bidirectional LSTMs, combinations of LSTMs with CRF, and CRF to”
Recurrent Neural Networks for Classifying Relations in Clinical Notes (2017, positive): “[45] applied bidirectional RNNs using Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) to recognize named entities or concepts such as medications, diseases and their associated attributes (e.”
Deep Learning for Anomaly Detection: A Survey (2019, background): “A survey of traditional anomaly detection techniques and its challenges to detect anomalies in social networks is a well studied topic in literature (Liu and Chawla [2017], Savage et al. [2014], Anand et al. [2017], Yu et al. [2016], Cao et al. [2018b], Yu et al. [2016]).”
Assessment of DistilBERT performance on Named Entity Recognition task for the detection of Protected Health Information and medical concepts (2020, background): “Clinical records play an important role in the discovery of disease treatment and the advancement of medical research (Jagannatha and Yu, 2016).”
Unsupervised ensemble ranking of terms in electronic health record notes based on their importance to patients (2017, background): “recognition [45,46], adverse drug event detection [47,48], ranking biomedical synonyms [49], and disambiguating clinical abbreviations [50,51].”
Graph Convolutional Networks With Argument-Aware Pooling for Event Detection (2018, methodology): “2016c), recurrent neural networks (Nguyen, Cho, and Grishman 2016a; Jagannatha and Yu 2016) and attention-based networks (Liu et al.”
Doctor XAI: an ontology-based approach to black-box sequential data classification explanations (2020, background): “Deep Learning techniques have been proven useful for information extraction from clinical notes [21], patients and medical concept representation learning [35], outcome prediction [9, 12, 29, 38, 42] and new phenotype discovery [8, 25].”
Clinical Text Data in Machine Learning: Systematic Review (2020, methodology): “Unspecified type of clinical notes [102] were used mostly for classification [9,12,31,61,86,95,103,113], WSD [33], and disambiguation and IE [36,51,99].”
Deep Learning for Medical Anomaly Detection – A Survey (2020, methodology): “For instance, RNNs have been utilised in [48] and [49] for text based abnormality detection in electronic health records; and in [50] to detect abnormal heart beats in Phonocardiographic recordings.”