Abstract
The International Classification of Diseases (ICD) has been adopted worldwide in the healthcare domain, e.g. to summarize the key information in clinical documents. Since manual ICD coding is very expensive, time-consuming, and error-prone, deep learning algorithms have been proposed to automate this task. However, the final goal of ICD coding often lays not in determining the codes associated with individual documents, but instead in quantifying the prevalence of each code within sets of documents. In this work, we experimentally assess different quantification methods in connection to ICD coding, including a simple learning-based approach that leverages associations between the codes, in order to predict their relative frequencies more accurately. Experiments show that the proposed approach can effectively explore existing associations between ICD codes, improving the quantification performance over baseline methods that deal with each code independently.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bella, A., Ferri, C., Hernández-Orallo, J., Ramirez-Quintana, M.J.: Quantification via probability estimators. In: Proceedings of the IEEE International Conference on Data Mining (2010)
Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer. arXiv preprint arXiv:2004.05150 (2020)
Coutinho, I., Martins, B.: Transformer-based models for ICD-10 coding of death certificates with Portuguese text. J. Biomed. Inform. 136, 104232 (2022)
Dai, X., Chalkidis, I., Darkner, S., Elliott, D.: Revisiting transformer-based models for long document classification. arXiv preprint arXiv:2204.06683 (2022)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (2019)
Edin, J., et al.: Automated medical coding on MIMIC-III and MIMIC-IV: a critical review and replicability study. arXiv preprint arXiv:2304.10909 (2023)
Esuli, A., Moreo Fernández, A., Sebastiani, F.: A recurrent neural network for sentiment quantification. In: Proceedings of the ACM International Conference on Information and Knowledge Management (2018)
Forman, G.: Counting positives accurately despite inaccurate classification. In: Proceedings of the European Conference on Machine Learning (2005)
Forman, G.: Quantifying counts and costs via classification. Data Min. Knowl. Disc. 17, 164–206 (2008)
González, P., Castaño, A., Chawla, N.V., Coz, J.J.D.: A review on quantification learning. ACM Comput. Surv. 50(5), 1–40 (2017)
Heydarian, M., Doyle, T.E., Samavi, R.: MLCM: multi-label confusion matrix. IEEE Access 10, 19083–19095 (2022)
Ji, S., Hölttä, M., Marttinen, P.: Does the magic of BERT apply to medical code assignment? A quantitative study. Comput. Biol. Med. 139, 104998 (2021)
Ji, S., Pan, S., Marttinen, P.: Medical code assignment with gated convolution and note-code interaction. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP (2021)
Ji, S., Sun, W., Dong, H., Wu, H., Marttinen, P.: A unified review of deep learning for automated medical coding. arXiv preprint arXiv:2201.02797 (2022)
Johnson, A.E., et al.: MIMIC-III, a freely accessible critical care database. Sci. Data 3(1), 1–9 (2016)
Kaur, R., Ginige, J.A., Obst, O.: A systematic literature review of automated ICD coding and classification systems using discharge summaries. arXiv preprint arXiv:2107.10652 (2021)
Levin, R., Roitman, H.: Enhanced probabilistic classify and count methods for multi-label text quantification. In: Proceedings of the ACM SIGIR International Conference on the Theory of Information Retrieval (2017)
Li, Y., Wehbe, R.M., Ahmad, F.S., Wang, H., Luo, Y.: Clinical-longformer and clinical-BigBird: transformers for long clinical sequences. arXiv preprint arXiv:2201.11838 (2022)
Maletzke, A.G., Hassan, W., dos Reis, D.M., Batista, G.E.: The importance of the test set size in quantification assessment. In: Proceedings of the International Joint Conferences on Artificial Intelligence Organization (2020)
Michalopoulos, G., Malyska, M., Sahar, N., Wong, A., Chen, H.: ICDBigBird: a contextual embedding model for ICD code classification. In: Proceedings of the ACL Workshop on Biomedical Language Processing (2022)
Moreo, A., Francisco, M., Sebastiani, F.: Multi-label quantification. arXiv preprint arXiv:2211.08063 (2022)
Moreo, A., Sebastiani, F.: Re-assessing the “classify and count” quantification method. In: Proceedings of the European Conference on Information Retrieval (2021)
Mullenbach, J., Wiegreffe, S., Duke, J., Sun, J., Eisenstein, J.: Explainable prediction of medical codes from clinical text. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (2018)
Nawrot, P., et al.: Hierarchical transformers are more efficient language models. arXiv preprint arXiv:2110.13711 (2021)
Sebastiani, F.: Text quantification. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts (2014)
Sebastiani, F.: Evaluation measures for quantification: an axiomatic approach. Inf. Retr. J. 23(3), 255–288 (2020)
Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)
Vaswani, A., et al.: Attention is all you need. In: Proceedings of the Annual Conference on Advances in Neural Information Processing Systems (2017)
Vu, T., Nguyen, D.Q., Nguyen, A.: A label attention model for ICD coding from clinical text. In: Proceedings of the International Joint Conference on Artificial Intelligence (2021)
Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing: System Demonstrations (2020)
Xun, G., Jha, K., Sun, J., Zhang, A.: Correlation networks for extreme multi-label text classification. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2020)
Yuan, Z., Tan, C., Huang, S.: Code synonyms do matter: multiple synonyms matching network for automatic ICD coding. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (2022)
Zaheer, M., et al.: Big bird: transformers for longer sequences. In: Proceedings of the Annual Conference on Advances in Neural Information Processing Systems (2020)
Zhang, N., Jankowski, M.: Hierarchical BERT for medical document understanding. arXiv preprint arXiv:2204.09600 (2022)
Acknowledgements
This research was supported by Fundação para a Ciência e Tecnologia (FCT), through the project with reference DSAIPA/DS/0133/2020 (DETECT) and the PhD scholarship with reference 2022.09649.BD, as well as the INESC-ID multi-annual funding from the PIDDAC programme with reference UIDB/50021/2020. We also gratefully acknowledge the support of NVIDIA Corporation, with the donation of the two Titan Xp GPUs used in our experiments.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Coutinho, I., Martins, B. (2023). Exploring Label Correlations for Quantification of ICD Codes. In: Bifet, A., Lorena, A.C., Ribeiro, R.P., Gama, J., Abreu, P.H. (eds) Discovery Science. DS 2023. Lecture Notes in Computer Science(), vol 14276. Springer, Cham. https://doi.org/10.1007/978-3-031-45275-8_41
Download citation
DOI: https://doi.org/10.1007/978-3-031-45275-8_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45274-1
Online ISBN: 978-3-031-45275-8
eBook Packages: Computer ScienceComputer Science (R0)