Abstract
Linguistic uncertainty is prevalent in electronic health records (EHRs). The ability to handle and preserve uncertainty in natural language is an essential skill for clinicians, facilitating decidability and effective clinical reasoning processes despite incomplete knowledge in some situations. This has been addressed by previous research in clinical NLP by the development of algorithms that detect uncertainty expressions. However, existing rule-based algorithms have limited uncertainty detection capabilities. Therefore, we seek to reformulate uncertainty detection as a supervised machine learning problem by (i) reevaluating the concept of uncertainty, (ii) embedding this understanding in an improved linguistic uncertainty taxonomy and (iii) introducing a new dataset of EHRs annotated for nine types of uncertainty – the first publicly available dataset of its kind. Many of our classes are novel and emphasise implicit uncertainties – a form of uncertainty that is ignored by existing algorithms, yet has crucial functions in clinical settings. Through an evaluation of our dataset, we demonstrate the scalability of our approach and its utility in relation to research on clinical information extraction.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
All examples hereinafter are from MIMIC and are paraphrased.
- 2.
References
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. Inform. 34, 301–310 (2001). https://doi.org/10.1006/jbin.2001.1029
Goldberger, A.L., et al.: PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101, e215–e220 (2000). https://doi.org/10.1161/01.cir.101.23.e215
Irvin, J., et al.: CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI Conference on Artificial Intelligence (2019). https://doi.org/10.1609/aaai.v33i01.3301590
Johnson, A.E., Pollard, T.J., Mark, R.G.: MIMIC-III clinical database (version 1.4). PhysioNet (2016)
Johnson, A.E., Pollard, T.J., Mark, R.G., Seth, B., Horng, S.: MIMIC-CXR Database (version 2.0.0). PhysioNet (2019)
Johnson, A.E., et al.: MIMIC-III, a freely accessible critical care database. Sci. Data 3, 1–9 (2016). https://doi.org/10.1038/sdata.2016.35
Kim, Y.: Convolutional neural networks for sentence classification. In: EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (2014). https://doi.org/10.3115/v1/d14-1181
Mowery, D.L., Ave, M., Chapman, W.W.: Medical diagnosis lost in translation – analysis of uncertainty and negation expressions in English and Swedish clinical texts. In: Proceedings of the 2012 Workshop on Biomedical Natural Language Processing (BioNLP 2012) (2012)
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
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. In: AMIA Joint Summits on Translational Science Proceedings. AMIA Joint Summits on Translational Science (2018)
Velupillai, S.: Shades of certainty: annotation and classification of Swedish medical records (2012). http://su.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:512263
Vincze, V., Szarvas, G., Farkas, R., Móra, G., Csirik, J.: The BioScope corpus: biomedical texts annotated for uncertainty, negation and their scopes. BMC Bioinformatics 9, 1–9 (2008). https://doi.org/10.1186/1471-2105-9-S11-S9
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Ethics
This study has been carried out in accordance with all relevant guidelines and regulations for the use of MIMIC-III data. Assisting human medical experts to make better decisions in complex environments is the sole aim of this paper and the way we handle data in our dataset. Further, all annotators involved in the construction of our dataset were volunteers. Before deployment in an actual clinical setting, we plan to systematically evaluate our methodology under the supervision of expert clinicians.
A Model Implementation
A Model Implementation
Following the work of Kim [7], a state-of-the-art single channel Convolutional Neural Network (CNN) for sentence classification was used as a binary classifier.
For our experiments (see Sect. 5.2 and 5.3), the majority of hyperparameters were kept constant: the learning rate was set at 0.3; the dropout probability in the dropout layer was 0.1; BioWordVec embeddings were scaled by a factor of 0.65. The window sizes for our two convolutional layers were either 1 and 3 or 3 and 5. The number of training epochs ranged from 30 to 70. These hyperparameters were determined by monitoring the training loss. Random classifiers used as a baseline were drawn from the Scikitlearn library [9].
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Turner, M., Ive, J., Velupillai, S. (2021). Linguistic Uncertainty in Clinical NLP: A Taxonomy, Dataset and Approach. In: Candan, K.S., et al. Experimental IR Meets Multilinguality, Multimodality, and Interaction. CLEF 2021. Lecture Notes in Computer Science(), vol 12880. Springer, Cham. https://doi.org/10.1007/978-3-030-85251-1_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-85251-1_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-85250-4
Online ISBN: 978-3-030-85251-1
eBook Packages: Computer ScienceComputer Science (R0)