Detection of Bleeding Events in Electronic Health Record Notes Using Convolutional Neural Network Models Enhanced With Recurrent Neural Network Autoencoders: Deep Learning Approach (Preprint)
Preprint
- 15 April 2018
- preprint
- Published by JMIR Publications Inc. in JMIR Preprints
Abstract
BACKGROUND Bleeding events are common and critical and may cause significant morbidity and mortality. High incidences of bleeding events are associated with cardiovascular disease in patients on anticoagulant therapy. Prompt and accurate detection of bleeding events is essential to prevent serious consequences. As bleeding events are often described in clinical notes, automatic detection of bleeding events from electronic health record (EHR) notes may improve drug-safety surveillance and pharmacovigilance. OBJECTIVE We aimed to develop a natural language processing (NLP) system to automatically classify whether an EHR note sentence contains a bleeding event. METHODS We expert annotated 878 EHR notes (76,577 sentences and 562,630 word-tokens) to identify bleeding events at the sentence level. This annotated corpus was used to train and validate our NLP systems. We developed an innovative hybrid convolutional neural network (CNN) and long short-term memory (LSTM) autoencoder (HCLA) model that integrates a CNN architecture with a bidirectional LSTM (BiLSTM) autoencoder model to leverage large unlabeled EHR data. RESULTS HCLA achieved the best area under the receiver operating characteristic curve (0.957) and F1 score (0.938) to identify whether a sentence contains a bleeding event, thereby surpassing the strong baseline support vector machines and other CNN and autoencoder models. CONCLUSIONS By incorporating a supervised CNN model and a pretrained unsupervised BiLSTM autoencoder, the HCLA achieved high performance in detecting bleeding events.Keywords
All Related Versions
- Published version: JMIR Medical Informatics, 7 (1), e10788.
This publication has 10 references indexed in Scilit:
- Comparing deep learning and concept extraction based methods for patient phenotyping from clinical narrativesPLOS ONE, 2018
- Artificial Intelligence Learning Semantics via External Resources for Classifying Diagnosis Codes in Discharge NotesJournal of Medical Internet Research, 2017
- Predicting mental conditions based on “history of present illness” in psychiatric notes with deep neural networksJournal of Biomedical Informatics, 2017
- Challenges in adapting existing clinical natural language processing systems to multiple, diverse health care settingsJournal of the American Medical Informatics Association, 2017
- Usefulness of Health Registers for detection of bleeding events in outcome studiesThrombosis and Haemostasis, 2016
- Risk stratification, perioperative and periprocedural management of the patient receiving anticoagulant therapyJournal of Clinical Anesthesia, 2016
- The impact of bleeding complications in patients receiving target-specific oral anticoagulants: a systematic review and meta-analysisBlood, 2014
- Bleeding Complications With Warfarin UseArchives of internal medicine (1960), 2007
- Hematoma growth is a determinant of mortality and poor outcome after intracerebral hemorrhageNeurology, 2006
- Building text classifiers using positive and unlabeled examples2004