Using neural attention networks to detect adverse medical events from electronic health records

The detection of Adverse Medical Events (AMEs) plays an important role in disease management in ensuring efficient treatment delivery and quality improvement of health services. Recently, with the rapid development of hospital information systems, a large volume of Electronic Health Records (EHRs) have been produced, in which AMEs are regularly documented in a free-text manner. In this study, we are concerned with the problem of AME detection by utilizing a large volume of unstructured EHR data. To address this challenge, we propose a neural attention network-based model to incorporate the contextual information of words into AME detection. Specifically, we develop a context-aware attention mechanism to locate salient words with respect to the target AMEs in patient medical records. And then we combine the proposed context attention mechanism with the deep learning tactic to boost the performance of AME detection. We validate our proposed model on a real clinical dataset that consists of 8845 medical records of patients with cardiovascular diseases. The experimental results show that our proposed model advances state-of-the-art models and achieves competitive performance in terms of AME detection.

[1]  J. Fleiss.  Measuring nominal scale agreement among many raters. , 1971 .

[2]  Koldo Gojenola,et al.  Learning to extract adverse drug reaction events from electronic health records in Spanish , 2016, Expert Syst. Appl..

[3]  A. Sharaf Eldin,et al.  Mining association patterns of drug-interactions using post marketing FDA's spontaneous reporting data , 2016, J. Biomed. Informatics.

[4]  Eric R. LaRose,et al.  Adverse Drug Event Discovery Using Biomedical Literature: A Big Data Neural Network Adventure , 2017, JMIR medical informatics.

[5]  W. Youden,et al.  Index for rating diagnostic tests , 1950, Cancer.

[6]  Susumu Horiguchi,et al.  Learning to classify short and sparse text & web with hidden topics from large-scale data collections , 2008, WWW.

[7]  Heng Ji,et al.  Visual Attention Model for Name Tagging in Multimodal Social Media , 2018, ACL.

[8]  Anne Cocos,et al.  Deep learning for pharmacovigilance: recurrent neural network architectures for labeling adverse drug reactions in Twitter posts , 2017, J. Am. Medical Informatics Assoc..

[9]  Carol Friedman,et al.  Combing signals from spontaneous reports and electronic health records for detection of adverse drug reactions , 2013, J. Am. Medical Informatics Assoc..

[10]  Alex Graves,et al.  Long Short-Term Memory , 2020, Computer Vision.

[11]  Ryan A. Rossi,et al.  Graph Classification using Structural Attention , 2018, KDD.

[12]  S. Holm.  A Simple Sequentially Rejective Multiple Test Procedure , 1979 .

[13]  Ramón Fernández Astudillo,et al.  From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification , 2016, ICML.

[14]  Hua Xu,et al.  Identifying Plausible Adverse Drug Reactions Using Knowledge Extracted from the Literature , 2014, AMIA.

[15]  Halil Kilicoglu,et al.  The role of fine-grained annotations in supervised recognition of risk factors for heart disease from EHRs , 2015, J. Biomed. Informatics.

[16]  M. Q. G. Torner,et al.  Detección de acontecimientos adversos producidos por medicamentos durante la estancia hospitalaria , 2009 .

[17]  Bart Baesens,et al.  A Process Mining-Based Investigation of Adverse Events in Care Processes , 2014, Health information management : journal of the Health Information Management Association of Australia.

[18]  Régis Beuscart,et al.  Data Mining to Generate Adverse Drug Events Detection Rules , 2011, IEEE Transactions on Information Technology in Biomedicine.

[19]  Zhiyuan Liu,et al.  Neural Sentiment Classification with User and Product Attention , 2016, EMNLP.

[20]  Jun-Jie Zhang,et al.  Cutoff Value and Long-Term Prediction of Clinical Events by FFR Measured Immediately After Implantation of a Drug-Eluting Stent in Patients With Coronary Artery Disease: 1- to 3-Year Results From the DKCRUSH VII Registry Study. , 2017, JACC. Cardiovascular interventions.

[21]  Gediminas Adomavicius,et al.  Data mining for censored time-to-event data: a Bayesian network model for predicting cardiovascular risk from electronic health record data , 2014, Data Mining and Knowledge Discovery.

[22]  M. Farrero,et al.  Detecting adverse drug events during the hospital stay , 2009 .

[23]  Xiaolong Wang,et al.  Drug-Drug Interaction Extraction via Convolutional Neural Networks , 2016, Comput. Math. Methods Medicine.

[24]  Zhenchao Jiang,et al.  Drug-drug interaction extraction from biomedical literature using support vector machine and long short term memory networks , 2017, Inf. Sci..

[25]  Pushpraj Shukla,et al.  Early identification of adverse drug reactions from search log data , 2016, J. Biomed. Informatics.

[26]  Yidong Chen,et al.  Lattice-to-sequence attentional Neural Machine Translation models , 2018, Neurocomputing.

[27]  Marianthi Markatou,et al.  Text mining for the Vaccine Adverse Event Reporting System: medical text classification using informative feature selection , 2011, J. Am. Medical Informatics Assoc..

[28]  H. A. David,et al.  The Paired t Test Under Artificial Pairing , 1997 .

[29]  A. Coats,et al.  Adverse cardiovascular outcomes in atrial fibrillation: Validation of the new 2MACE risk score. , 2017, International journal of cardiology.

[30]  Jimeng Sun,et al.  RAIM: Recurrent Attentive and Intensive Model of Multimodal Patient Monitoring Data , 2018, KDD.

[31]  Hua Xu,et al.  Identifying risk factors for heart disease over time: Overview of 2014 i2b2/UTHealth shared task Track 2 , 2015, J. Biomed. Informatics.

[32]  C Helma,et al.  Prediction of Adverse Drug Reactions Using Decision Tree Modeling , 2010, Clinical pharmacology and therapeutics.

[33]  Diyi Yang,et al.  Hierarchical Attention Networks for Document Classification , 2016, NAACL.

[34]  Angus Roberts,et al.  Building a semantically annotated corpus of clinical texts , 2009, J. Biomed. Informatics.

[35]  Zhengxing Huang,et al.  MACE prediction of acute coronary syndrome via boosted resampling classification using electronic medical records , 2017, J. Biomed. Informatics.

[36]  Yanchun Zhang,et al.  Refining Adverse Drug Reactions Using Association Rule Mining for Electronic Healthcare Data , 2014, 2014 IEEE International Conference on Data Mining Workshop.

[37]  Le Song,et al.  GRAM: Graph-based Attention Model for Healthcare Representation Learning , 2016, KDD.

[38]  Yoshua Bengio,et al.  Fine-grained attention mechanism for neural machine translation , 2018, Neurocomputing.

[39]  Mário J. Silva,et al.  Deep neural models for ICD-10 coding of death certificates and autopsy reports in free-text , 2018, J. Biomed. Informatics.

[40]  John Mullooly,et al.  Detecting possible vaccine adverse events in clinical notes of the electronic medical record. , 2009, Vaccine.

[41]  Xin Liu,et al.  An automatic system to identify heart disease risk factors in clinical texts over time , 2015, J. Biomed. Informatics.

[42]  Uwe Aickelin,et al.  A Supervised Adverse Drug Reaction Signalling Framework Imitating Bradford Hill's Causality Considerations , 2015, J. Biomed. Informatics.

[43]  Özlem Uzuner,et al.  Annotating risk factors for heart disease in clinical narratives for diabetic patients , 2015, J. Biomed. Informatics.

[44]  Jie Chen,et al.  Mining Unexpected Temporal Associations: Applications in Detecting Adverse Drug Reactions , 2008, IEEE Transactions on Information Technology in Biomedicine.

[45]  Donald E. Brown,et al.  HDLTex: Hierarchical Deep Learning for Text Classification , 2017, 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA).

[46]  Li Zhao,et al.  Attention-based LSTM for Aspect-level Sentiment Classification , 2016, EMNLP.

[47]  Juliane Fluck,et al.  Development of a benchmark corpus to support the automatic extraction of drug-related adverse effects from medical case reports , 2012, J. Biomed. Informatics.

[48]  Deepak L. Bhatt,et al.  ACCF/ACG/AHA 2008 expert consensus document on reducing the gastrointestinal risks of antiplatelet therapy and NSAID use: a report of the American College of Cardiology Foundation Task Force on Clinical Expert Consensus Documents. , 2008, Circulation.

[49]  Alex Graves,et al.  Recurrent Models of Visual Attention , 2014, NIPS.

[50]  D. Angiolillo,et al.  Platelet function testing and risk of bleeding complications , 2010, Thrombosis and Haemostasis.

[51]  Yu-Sheng Lin,et al.  Major adverse cardiovascular events in adult congenital heart disease: a population-based follow-up study from Taiwan , 2014, BMC Cardiovascular Disorders.

[52]  N. Guilera,et al.  Management of antiplatelet therapy in patients with coronary stents undergoing noncardiac surgery: association with adverse events , 2018, British journal of anaesthesia.

[53]  Daniel Dajun Zeng,et al.  Mining e-cigarette adverse events in social media using Bi-LSTM recurrent neural network with word embedding representation , 2018, J. Am. Medical Informatics Assoc..

[54]  Jeong Hoon Yang,et al.  Long-term survival benefit of revascularization compared with medical therapy in patients with coronary chronic total occlusion and well-developed collateral circulation. , 2015, JACC. Cardiovascular interventions.

[55]  Tung Tran,et al.  Predicting mental conditions based on "history of present illness" in psychiatric notes with deep neural networks. , 2017, Journal of biomedical informatics.

[56]  Kevin E. Kip,et al.  The problem with composite end points in cardiovascular studies: the story of major adverse cardiac events and percutaneous coronary intervention. , 2008, Journal of the American College of Cardiology.