Abstract
This paper discusses the concepts of interpretability and explainability and outlines desiderata for robust interpretability. It then describes a neural network model that meets all criteria, with the addition of global faithfulness.
This is achieved by efficient estimation of a General Additive Neural Network, seeded by a conventional Multilayer Perceptron (MLP) by distilling the dependence on individual variables and pairwise interactions, so that their effects can be represented within the structure of a General Additive Model. This makes the logic of the model clear and transparent to users, across the complete input space. The model is self-explaining.
The modelling approach used in this paper derives the partial responses from the MLP, resulting in the Partial Response Network (PRN). Its application is illustrated in a medical context using the CTU-UHB Cardiotacography intrapartum database (n = 552) to infer the features associated with caesarean deliveries. This is the first application of the PRN to this data set and it is shown that the self-explaining model achieves comparable discrimination performance to that of Random Forests previously applied to the same data set. The classes are highly imbalanced with a prevalence of caesarean sections of 8.33%. The resulting model uses 4 from 8 possible features and has an AUROC of 0.69 [CI 0.60, 0.77] estimated by 4-fold cross-validation. Its performance and features are compared also with those from a Sparse Additive Models (SAM) which has an AUROC of 0.72 [CI 0.64, 0.80]. This is not significantly different and requires all features.
For clinical utility by risk stratification, the odds-ratio for caesarian section vs. not at the prevalence threshold is 3.97 for the PRN, better 3.14 for the SAM. Compared for consistency, parsimony, stability and scalability the models have complementary properties.
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
References
Goodman, B., Flaxman, S.: European union regulations on algorithmic decision making and a ‘right to explanation’. AI Mag. 38, 50–57 (2017)
Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6 52138–52160 (2018)
Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1–38 (2019)
Biran, O., Cotton, C.: Explanation and justification in machine learning: a survey. In: IJCAI Workshop on Explainable AI (XAI) (2017)
Etchells, T.A., Lisboa, P.J.G.: Orthogonal Search-Based Rule Extraction (OSRE) for trained neural networks: a practical and efficient approach. IEEE Trans. Neural Netw. 17(2), 374–384 (2006)
Rögnvaldsson, T., Etchells, T.A., You, L., Garwicz, D., Jarman, I., Lisboa, P.J.G.: How to find simple and accurate rules for viral protease cleavage specificities. BMC Bioinf. 10(1), 149 (2009)
Montani, S., Striani, M.: Artificial intelligence in clinical decision support: a focused literature survey. Yearb. Med. Inform. 28(1), 120–127 (2019)
Ribeiro, M.T., Singh, S., Guestrin, C.: Why should I trust you? In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD 2016, pp. 1135–1144 (2016)
Lundberg, S., Lee, S.-I., A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, vol. 30, pp. 4765–4774 (2017)
Alvarez-Melis, D., Jaakkola, T.S.: Towards robust interpretability with self- explaining neural networks. In: NIPS, vol. 31 (2018)
Ravikumar, P., Lafferty, J., Liu, H., Wasserman, L.: Sparse additive models. J. Roy. Stat. Soc.: Ser. B (Stat. Methodol.) 71(5), 1009–1030 (2009)
Van Belle, V., Van Calster, B., Van Huffel, S., Suykens, J.A.K., Lisboa, P.: Explaining support vector machines: a color based nomogram. PLoS ONE 11(10), e0164568 (2016)
Goldberger, A.L., et al.: PhysioBank, PhysioToolkit, and PhysioNet. Circulation 101(23), e215–e220 (2000)
Chudáček, V., et al.: Open access intrapartum CTG database. BMC Pregnancy Childbirth 14(1), 16 (2014)
Spilka, J., Chudacek, V., Koucky, M., Lhotska, L.: Assessment of non-linear features for intrapartal fetal heart rate classification. In: 2009 9th International Conference on Information Technology and Applications in Biomedicine, pp. 1–4 (2009)
Fergus, P., Selvaraj, M., Chalmers, C.: Machine learning ensemble modelling to classify caesarean section and vaginal delivery types using Cardiotocography traces. Comput. Biol. Med. 93, 7–16 (2018)
Zhao, Z., Zhang, Y., Deng, Y.: A comprehensive feature analysis of the fetal heart rate signal for the intelligent assessment of fetal state. J. Clin. Med. 7(8), 223 (2018)
Georgoulas, G., Karvelis, P., Spilka, J., Chudáček, V., Stylios, C.D., Lhotská, L.: Investigating pH based evaluation of fetal heart rate (FHR) recordings. Health Technol. (Berl). 7(2–3), 241–254 (2017)
Lisboa, P.J.G., Ortega-Martorell, S., Cashman, S., Olier, I.: The partial response network arXiv, pp. 1–10 (2019)
Hooker, G.: Generalized functional ANOVA diagnostics for high-dimensional functions of dependent variables. J. Comput. Graph. Stat. 16(3), 709–732 (2007)
Meier, L., Van De Geer, S., Bühlmann, P.: The group lasso for logistic regression. J. R. Stat. Soc. Ser. B Stat. Methodol. (2008)
MacKay, D.J.C.: The evidence framework applied to classification networks. Neural Comput. 4(5), 720–736 (1992)
Kim, B., et al.: Interpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV). In: International Conference on Machine Learning (ICLR) (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Lisboa, P.J.G., Ortega-Martorell, S., Jayabalan, M., Olier, I. (2020). Efficient Estimation of General Additive Neural Networks: A Case Study for CTG Data. In: Koprinska, I., et al. ECML PKDD 2020 Workshops. ECML PKDD 2020. Communications in Computer and Information Science, vol 1323. Springer, Cham. https://doi.org/10.1007/978-3-030-65965-3_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-65965-3_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-65964-6
Online ISBN: 978-3-030-65965-3
eBook Packages: Computer ScienceComputer Science (R0)
