Abstract
eXplainable Artifical Intelligence (XAI) is integral for the usability of black-box models in high-risk domains. Many problems in such domains are concerned with analysing temporal data. Namely, we must consider a sequence of instances that occur in time, and explain why the prediction transitions from one time point to the next. Currently, XAI techniques do not leverage the temporal nature of data and instead treat each instance independently. Therefore, we introduce a new approach advancing the Integrated Gradients method developed in the literature, namely the Batch-Integrated Gradients (Batch-IG) technique that (1) produces explanations over a temporal batch for instance-to-instance state transitions and (2) takes into account features that change over time. In Electronic Health Records (EHRs), we see patient records can be stored in temporal sequences. Thus, we demonstrate Batch-Integrated Gradients in producing explanations over a temporal sequence that satisfy proposed properties corresponding to XAI for EHR data.
Jamie Duell is supported by the UKRI AIMLAC CDT, funded by grant EP/S023992/1.
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
Similar content being viewed by others
Notes
- 1.
https://simulacrum.healthdatainsight.org.uk/ - The Simulacrum is a synthetic dataset developed by Health Data Insight CiC derived from anonymous cancer data provided by the National Cancer Registration and Analysis Service, which is part of Public Health England.
References
Amann, J., Blasimme, A., Vayena, E., Frey, D., Madai, V.I.: Explainability for artificial intelligence in healthcare: a multidisciplinary perspective. BMC Med. Inf. Decis. Making 20(1), 310 (2020)
Batal, I., Valizadegan, H., Cooper, G.F., Hauskrecht, M.: A temporal pattern mining approach for classifying electronic health record data. ACM Trans. Intell. Syst. Technol. 4(4), 2508044 (2013). https://doi.org/10.1145/2508037.2508044
Loh, H.W., Ooi, C.P., Seoni, S., Barua, P.D., Molinari, F., Acharya, U.R.: Application of explainable artificial intelligence for healthcare: A systematic review of the last decade (2011–2022). Comput. Methods Programs Biomed. 226, 107161 (2022)
Lundberg, S.M., Lee, S.: A unified approach to interpreting model predictions. In: Advances in NeurIPS 30: Annual Conference on NeurIPS, pp. 4765–4774 (2017)
Ribeiro, M.T., Singh, S., Guestrin, C.: “Why should I trust you?”: Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144. KDD 2016, Association for Computing Machinery, New York, NY, USA (2016)
Schlegel, U., Arnout, H., El-Assady, M., Oelke, D., Keim, D.A.: Towards a rigorous evaluation of XAI methods on time series. In: 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 4197–4201 (2019). https://doi.org/10.1109/ICCVW.2019.00516
Selbst, A.D., Powles, J.: Meaningful information and the right to explanation. Int. Data Priv. Law 7(4), 233–242 (2017)
Simic, I., Sabol, V., Veas, E.E.: XAI methods for neural time series classification: a brief review. CoRR abs/2108.08009 (2021). https://arxiv.org/abs/2108.08009
Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: ICML2017: Proceedings of the 34th International Conference on Machine Learning, pp. 3319–3328. JMLR.org (2017)
Veerappa, M., Anneken, M., Burkart, N., Huber, M.F.: Validation of XAI explanations for multivariate time series classification in the maritime domain. J. Comput. Sci. 58, 101539 (2022). https://doi.org/10.1016/j.jocs.2021.101539
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
Duell, J., Fan, X., Fu, H., Seisenberger, M. (2023). Batch Integrated Gradients: Explanations for Temporal Electronic Health Records. In: Juarez, J.M., Marcos, M., Stiglic, G., Tucker, A. (eds) Artificial Intelligence in Medicine. AIME 2023. Lecture Notes in Computer Science(), vol 13897. Springer, Cham. https://doi.org/10.1007/978-3-031-34344-5_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-34344-5_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34343-8
Online ISBN: 978-3-031-34344-5
eBook Packages: Computer ScienceComputer Science (R0)