Skip to content

Research at St Andrews

Ontological attention ensembles for capturing semantic concepts in ICD code prediction from clinical text

Research output: Contribution to conferencePaperpeer-review

Open Access permissions

Open

Author(s)

Matúš Falis, Maciej Pajak, Aneta Lisowska, Patrick Schrempf, Lucas Deckers, Shadia Mikhael, Sotirios Tsaftaris, Alison O'Neil

School/Research organisations

Abstract

We present a semantically interpretable system for automated ICD coding of clinical text documents. Our contribution is an ontological attention mechanism which matches the structure of the ICD ontology, in which shared attention vectors are learned at each level of the hierarchy, and combined into label-dependent ensembles. Analysis of the attention heads shows that shared concepts are learned by the lowest common denominator node. This allows child nodes to focus on the differentiating concepts, leading to efficient learning and memory usage. Visualisation of the multi-level attention on the original text allows explanation of the code predictions according to the semantics of the ICD ontology. On the MIMIC-III dataset we achieve a 2.7% absolute (11% relative) improvement from 0.218 to 0.245 macro-F1 score compared to the previous state of the art across 3,912 codes. Finally, we analyse the labelling inconsistencies arising from different coding practices which limit performance on this task.
Close

Details

Original languageEnglish
Publication statusPublished - Nov 2019
EventTenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019) - , Hong Kong
Duration: 3 Nov 2019 → …
https://louhi2019.fbk.eu/

Workshop

WorkshopTenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)
CountryHong Kong
Period3/11/19 → …
Internet address

Discover related content
Find related publications, people, projects and more using interactive charts.

View graph of relations

Related by author

  1. Templated text synthesis for expert-guided multi-label extraction from radiology reports

    Schrempf, P., Watson, H., Park, E., Pajak, M., MacKinnon, H., Muir, K. W., Harris-Birtill, D. & O’Neil, A. Q., 24 Mar 2021, In: Machine Learning and Knowledge Extraction. 3, 2, p. 299-317 19 p.

    Research output: Contribution to journalArticlepeer-review

  2. Paying per-label attention for multi-label extraction from radiology reports

    Schrempf, P., Watson, H., Mikhael, S., Pajak, M., Falis, M., Lisowska, A., Muir, K. W., Harris-Birtill, D. & O'Neil, A. Q., 2020, Interpretable and Annotation-Efficient Learning for Medical Image Computing: Third International Workshop, iMIMIC 2020, Second International Workshop, MIL3iD 2020, and 5th International Workshop, LABELS 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4–8, 2020, Proceedings. Cardoso, J., Van Nguyen, H., Heller, N., Henriques Abreu, P., Isgum, I., Silva, W., Cruz, R., Pereira Amorim, J., Patel, V., Roysam, B., Zhou, K., Jiang, S., Le, N., Luu, K., Sznitman, R., Cheplygina, V., Mateus, D., Trucco, E. & Abbasi, S. (eds.). Cham: Springer, p. 277-289 13 p. (Lecture Notes in Computer Science (including subseries Image Processing, Computer Vision, Pattern Recognition, and Graphics); vol. 12446 LNCS).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  3. Language transfer for early warning of epidemics from social media

    Appelgren, M., Schrempf, P., Falis, M., Ikeda, S. & O'Neil, A. Q., 13 Dec 2019. 6 p.

    Research output: Contribution to conferencePaperpeer-review

  4. RadarCat : Radar Categorization for input & interaction

    Yeo, H. S., Flamich, G., Schrempf, P. M., Harris-Birtill, D. C. C. & Quigley, A. J., 16 Oct 2016, Proceedings of the 29th Annual Symposium on User Interface Software and Technology (UIST '16). ACM, p. 833-841 9 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

ID: 264578567

Top