Abstract
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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chalapathy, R., Borzeshi, E.Z., Piccardi, M.: Bidirectional LSTM-CRF for clinical concept extraction. arXiv:1611.08373 (2016)
Chapman, W.W., Bridewell, W., Hanbury, P., Cooper, G.F., Buchanan, B.G.: A simple algorithm for identifying negated findings and diseases in discharge summaries. J. Biomed. Inf. 34(5), 301–310 (2001)
Cheng, K., Baldwin, T., Verspoor, K.: Automatic negation and speculation detection in veterinary clinical text. In: Proceedings of the Australasian Language Technology Association Workshop 2017, pp. 70–78 (2017)
de Bruijn, B., Cherry, C., Kiritchenko, S., Martin, J., Zhu, X.: Machine-learned solutions for three stages of clinical information extraction: the state of the art at i2b2 2010. J. Am. Med. Inf. Assoc. 18(5), 557–562 (2011)
Fancellu, F., Lopez, A., Webber, B.: Neural networks for negation scope detection. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), vol. 1, pp. 495–504 (2016)
Gkotsis, G., Velupillai, S., Oellrich, A., Dean, H., Liakata, M., Dutta, R.: Don’t let notes be misunderstood: a negation detection method for assessing risk of suicide in mental health records. In: Proceedings of the Third Workshop on Computational Lingusitics and Clinical Psychology, pp. 95–105 (2016)
Harkema, H., Dowling, J.N., Thornblade, T., Chapman, W.W.: Context: an algorithm for determining negation, experiencer, and temporal status from clinical reports. J. Biomed. Inf. 42(5), 839–851 (2009)
Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K., Dyer, C.: Neural architectures for named entity recognition. In: Proceedings of NAACL-HLT, pp. 260–270 (2016)
Peng, N., Dredze, M.: Multi-task domain adaptation for sequence tagging. In: Proceedings of the 2nd Workshop on Representation Learning for NLP, pp. 91–100 (2017)
Peng, Y., Wang, X., Lu, L., Bagheri, M., Summers, R., Lu, Z.: NegBio: a high-performance tool for negation and uncertainty detection in radiology reports. AMIA Jt. Summits Transl. Sci. Proc. 2017, 188 (2018)
Rumeng, L., Jagannatha Abhyuday, N., Hong, Y.: A hybrid neural network model for joint prediction of presence and period assertions of medical events in clinical notes. In: AMIA Annual Symposium Proceedings, vol. 2017, p. 1149. American Medical Informatics Association (2017)
Shivade, C., de Marneffe, M.-C., Fosler-Lussier, E., Lai, A.M.: Extending NegEx with kernel methods for negation detection in clinical text. In: Proceedings of the Second Workshop on Extra-Propositional Aspects of Meaning in Computational Semantics (ExProM 2015), pp. 41–46 (2015)
Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. Advances in Neural Information Processing Systems, pp. 2951–2959 (2012)
Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Comput. 1(2), 270–280 (1989)
Wu, S., Miller, T., Masanz, J., Coarr, M., Halgrim, S., Carrell, D., Clark, C.: Negation’s not solved: generalizability versus optimizability in clinical natural language processing. PloS One 9(11), e112774 (2014)
Yang, Z., Salakhutdinov, R., Cohen, W.: Multi-task cross-lingual sequence tagging from scratch. arXiv:1603.06270 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
1.1 Experiments
Dataset We evaluated our model on two datasets. First is the 2010 i2b2/VA challenge dataset for “test, treatment, problem” (TTP) entity extraction and assertion detection (i2b2 dataset). Unfortunately, only part of this dataset was made public after the challenge, therefore we cannot directly compare with NegEx and ABoW results. We followed the original data split from [1] of 170 notes for training and 256 for testing. The second dataset is proprietary and consists of 4,200 de-identified annotated clinical notes with medical conditions (proprietary dataset). Below is a summary of the datasets (Table 3).
Model settings Word, character and tag embeddings are 100, 25, and 50 dimensions, respectively. Word embeddings are initialized using GloVe, while character and tag embeddings are learned. Character and word encoders have 50, and 100 hidden units, respectively, while the decoder LSTM has a hidden size of 50. Dropout is used after every LSTM, as well as for word embedding input. We use Adam as an optimizer. Our model is built using MXNet. Hyperparameters are tuned using Bayesian Optimization [13].
Training details Our models are trained until convergence, and we use the development set for both tasks to evaluate performance for early stopping. We performed two sets of experiments. The first set evaluates the performance of NER and negation assertion of the baseline, two decoder, shared decoder and conditional softmax decoder models on i2b2 and the medical condition datasets. The second set uses low resource settings, where we evaluate the performance of negation assertion of the conditional softmax decoder model on 5, 10 and 20% of the proprietary medical condition training data. Development and test sets are kept at the original size.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Bhatia, P., Busra Celikkaya, E., Khalilia, M. (2020). End-to-End Joint Entity Extraction and Negation Detection for Clinical Text. In: Shaban-Nejad, A., Michalowski, M. (eds) Precision Health and Medicine. W3PHAI 2019. Studies in Computational Intelligence, vol 843. Springer, Cham. https://doi.org/10.1007/978-3-030-24409-5_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-24409-5_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-24408-8
Online ISBN: 978-3-030-24409-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)