Joint Entity Extraction and Assertion Detection for Clinical Text

Negative medical findings are prevalent in clinical reports, yet discriminating them from positive findings remains a challenging task for information extraction. Most of the existing systems treat this task as a pipeline of two separate tasks, i.e., named entity recognition (NER) and rule-based negation detection. We consider this as a multi-task problem and present a novel end-to-end neural model to jointly extract entities and negations. We extend a standard hierarchical encoder-decoder NER model and first adopt a shared encoder followed by separate decoders for the two tasks. This architecture performs considerably better than the previous rule-based and machine learning-based systems. To overcome the problem of increased parameter size especially for low-resource settings, we propose the Conditional Softmax Shared Decoder architecture which achieves state-of-art results for NER and negation detection on the 2010 i2b2/VA challenge dataset and a proprietary de-identified clinical dataset.

[1]  Ruslan Salakhutdinov,et al.  Multi-Task Cross-Lingual Sequence Tagging from Scratch , 2016, ArXiv.

[2]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[3]  Parminder Bhatia,et al.  Relation Extraction using Explicit Context Conditioning , 2019, NAACL.

[4]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[5]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

[6]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[7]  Eric Nichols,et al.  Named Entity Recognition with Bidirectional LSTM-CNNs , 2015, TACL.

[8]  Busra Celikkaya,et al.  Improving Hospital Mortality Prediction with Medical Named Entities and Multimodal Learning , 2018, ArXiv.

[9]  Ronald M. Summers,et al.  NegBio: a high-performance tool for negation and uncertainty detection in radiology reports , 2017, AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science.

[10]  Maria Liakata,et al.  Don’t Let Notes Be Misunderstood: A Negation Detection Method for Assessing Risk of Suicide in Mental Health Records , 2016, CLPsych@HLT-NAACL.

[11]  Busra Celikkaya,et al.  Dynamic Transfer Learning for Named Entity Recognition , 2018, Precision Health and Medicine.

[12]  Massimo Piccardi,et al.  Bidirectional LSTM-CRF for Clinical Concept Extraction , 2016, ClinicalNLP@COLING 2016.

[13]  Li Rumeng,et al.  A hybrid Neural Network Model for Joint Prediction of Presence and Period Assertions of Medical Events in Clinical Notes. , 2017, AMIA ... Annual Symposium proceedings. AMIA Symposium.

[14]  Wendy W. Chapman,et al.  A Simple Algorithm for Identifying Negated Findings and Diseases in Discharge Summaries , 2001, J. Biomed. Informatics.

[15]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[16]  Nanyun Peng,et al.  Multi-task Domain Adaptation for Sequence Tagging , 2016, Rep4NLP@ACL.

[17]  Parminder Bhatia,et al.  Morphological Priors for Probabilistic Neural Word Embeddings , 2016, EMNLP.

[18]  James J. Masanz,et al.  Negation’s Not Solved: Generalizability Versus Optimizability in Clinical Natural Language Processing , 2014, PloS one.

[19]  Busra Celikkaya,et al.  Comprehend Medical: A Named Entity Recognition and Relationship Extraction Web Service , 2019, 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA).

[20]  Wendy W. Chapman,et al.  ConText: An algorithm for determining negation, experiencer, and temporal status from clinical reports , 2009, J. Biomed. Informatics.

[21]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[22]  Timothy Baldwin,et al.  Automatic Negation and Speculation Detection in Veterinary Clinical Text , 2017, ALTA.

[23]  Guillaume Lample,et al.  Neural Architectures for Named Entity Recognition , 2016, NAACL.

[24]  Bonnie L. Webber,et al.  Neural Networks For Negation Scope Detection , 2016, ACL.

[25]  Eric Fosler-Lussier,et al.  Extending NegEx with Kernel Methods for Negation Detection in Clinical Text , 2015 .

[26]  Joel D. Martin,et al.  Machine-learned solutions for three stages of clinical information extraction: the state of the art at i2b2 2010 , 2011, J. Am. Medical Informatics Assoc..

[27]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.