Abstract
Deep learning process trace classification is proving powerful in several application domains, including medical ones; however, classification results are typically not explainable, an issue which is particularly relevant in medicine.
In our recent work we tackled this problem, by proposing trace saliency maps, a novel tool able to highlight what trace activities are particularly significant for the classification task. A trace saliency map is built by generating artificial perturbations of the trace at hand that are classified in the same class as the original one, called examples.
In this paper, we investigate the role of counterexamples (i.e., artificial perturbations that are classified in a different class with respect to the original trace) in refining trace saliency map information, thus improving explainability. We test the approach in the domain of stroke.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alom, M.Z., et al.: A state-of-the-art survey on deep learning theory and architectures. Electronics 8(3), 292 (2019)
Breuker, D., Matzner, M., Delfmann, P., Becker, J.: Comprehensible predictive models for business processes. MIS Q. 40, 1009–1034 (2016)
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. 51(5), 1–4 (2019)
LeCun, Y., Bengio, Y., Hinton, G.E.: Deep learning. Nature 521(7553), 436–444 (2015)
Leonardi, G., Montani, S., Striani, M.: Explainable process trace classification: An application to stroke. J. Biomed. Informatics 126, 103981 (2022)
Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., Frey, B.: Adversarial autoencoders (2016)
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
Leonardi, G., Montani, S., Striani, M. (2023). Improving Stroke Trace Classification Explainability Through Counterexamples. 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_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-34344-5_16
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)