Abstract
In recent years, machine learning methods have been rapidly implemented in the medical domain. However, current state-of-the-art methods usually produce opaque, black-box models. To address the lack of model transparency, substantial attention has been given to develop interpretable machine learning methods. In the medical domain, counterfactuals can provide example-based explanations for predictions, and show practitioners the modifications required to change a prediction from an undesired to a desired state. In this paper, we propose a counterfactual explanation solution for predicting the survival of cardiovascular ICU patients, by representing their electronic health record as a sequence of medical events, and generating counterfactuals by adopting and employing a text style-transfer technique. Experimental results on the MIMIC-III dataset strongly suggest that text style-transfer methods can be effectively adapted for the problem of counterfactual explanations in healthcare applications and can achieve competitive performance in terms of counterfactual validity, BLEU-4 and local outlier metrics.
Keywords
- Counterfactual explanations
- Survival prediction
- Explainable models
- Deep learning
This is a preview of subscription content, access via your institution.
Buying options
References
Ahmad, F.S., et al.: A hybrid machine learning framework to predict mortality in paralytic ileus patients using electronic health records (EHRs). J. Ambient Intell. Hum. Comput. 30, 1 (2020)
Bagattini, F., Karlsson, I., Rebane, J., Papapetrou, P.: A classification framework for exploiting sparse multi-variate temporal features with application to adverse drug event detection in medical records. BMC Med. Inform. Decis. Mak. 19(1), 7:1–7:20 (2019)
Breunig, M.M., Kriegel, H.P., Ng, R.T., Sander, J.: LOF: identifying density-based local outliers. In: Proceedings of SIGMOD international conference on Management of data, pp. 93–104. New York (2000)
Caicedo-Torres, W., Gutierrez, J.: ISeeU: visually interpretable deep learning for mortality prediction inside the ICU. Biomed. Inform. 98, 103269 (2019)
Cao, Y., Shui, R., Pan, L., Kan, M.Y., Liu, Z., Chua, T.S.: Expertise style transfer: a new task towards better communication between experts and laymen. In: ACL, pp. 1061–1071 (2020)
Esteban, C., Schmidt, D., Krompaß, D., Tresp, V.: Predicting sequences of clinical events by using a personalized temporal latent embedding model. In: International Conference on Healthcare Informatics, pp. 130–139 (2015)
Hsieh, Y.Z., Su, M.C., Wang, C.H., Wang, P.C.: Prediction of survival of ICU patients using computational intelligence. Comput. Biol. Med. 47, 13–19 (2014)
Huang, J., Osorio, C., Sy, L.W.: An empirical evaluation of deep learning for ICD-9 code assignment using MIMIC-III clinical notes. Comput. Meth. Prog. Biomed. 177, 141-153 (2019)
Johnson, A.E.W.: MIMIC-III, a freely accessible critical care database. Sci. Data 3(1), 160035 (2016)
Lee, J.W.: Fluid and Electrolyte Disturbances in Critically Ill Patients. Electrolyte Blood Press (2010)
Kaji, D.A.: An attention based deep learning model of clinical events in the intensive care unit. PLOS ONE 14(2), e0211057 (2019)
Karlsson, I., Rebane, J., Papapetrou, P., Gionis, A.: Explainable time series tweaking via irreversible and reversible temporal transformations. In: 2018 IEEE International Conference on Data Mining (ICDM), pp. 207–216 (2018)
Li, J., Jia, R., He, H., Liang, P.: Delete, retrieve, generate: a simple approach to sentiment and style transfer. In: NAACL-HLT (2018)
Molnar, C.: Interpretable Machine Learning - A Guide for Making Black Box Models Explainable (2019)
Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z.B., Swami, A.: Practical Black-Box Attacks against Machine Learning (2017). arXiv:1602.02697
Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of ACL, pp. 311–318. Philadelphia, Pennsylvania, USA (2002)
Pryzant, R., Richard, D.M., Dass, N., Kurohashi, S., Jurafsky, D., Yang, D.: Automatically neutralizing subjective bias in text. In: Association for the Advancement of Artificial Intelligence (AAAI) (2020)
Rebane, J., Samsten, I., Papapetrou, P.: Exploiting complex medical data with interpretable deep learning for adverse drug event prediction. Artif. Intell. Med. 109, 101942 (2020)
Sudhakar, A., Upadhyay, B., Maheswaran, A.: “Transforming” delete, retrieve, generate approach for controlled text style transfer. In: Proceedings of EMNLP-IJCNLP, pp. 3269–3279. Hong Kong, China (2019)
Tonekaboni, S., Joshi, S., McCradden, M.D., Goldenberg, A.: What clinicians want: contextualizing explainable machine learning for clinical end use. In: Machine Learning for Healthcare Conference, pp. 359–380 (2019)
Van Looveren, A., Klaise, J.: Interpretable Counterfactual Explanations Guided by Prototypes (2020). arXiv:1907.02584
Verma, S., Dickerson, J., Hines, K.: Counterfactual Explanations for Machine Learning: A Review (2020). arXiv:2010.10596
Wachter, S., Mittelstadt, B., Russell, C.: Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR. Technical report, Social Science Research Network (2017)
Acknowledgments
This work was supported in part the EXTREMUM collaborative project of the Digital Futures framework.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, Z., Samsten, I., Papapetrou, P. (2021). Counterfactual Explanations for Survival Prediction of Cardiovascular ICU Patients. In: Tucker, A., Henriques Abreu, P., Cardoso, J., Pereira Rodrigues, P., Riaño, D. (eds) Artificial Intelligence in Medicine. AIME 2021. Lecture Notes in Computer Science(), vol 12721. Springer, Cham. https://doi.org/10.1007/978-3-030-77211-6_38
Download citation
DOI: https://doi.org/10.1007/978-3-030-77211-6_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-77210-9
Online ISBN: 978-3-030-77211-6
eBook Packages: Computer ScienceComputer Science (R0)