Abstract
The past decade has witnessed significant progress in deploying AI in the medical field. However, most AI models are considered black-boxes, making predictions neither understandable nor interpretable by humans. This limitation is especially significant when they contradict clinicians’ expectations based on medical knowledge. This can lead to a lack of trust in the model. In this work, we propose a pipeline to explain AI models. We used a previously devised Neural Network model to present our approach. It predicts the daily risk for patients with heart failure and is a part of a Decision Support System. In our pipeline, we deployed DeepSHAP algorithm to receive global and local explanations. With a global explanation, we defined the most important features in the model and their influence on the prediction. With local explanation, we analyzed individual observations and explained why a specific prediction was made. To validate the clinical relevance of our results, we consulted them with medical experts and made a literature review. Moreover, we described how the proposed pipeline can be integrated into Decision Support Systems. With the above tools, medical personnel can analyze the root of decisions and have insights into how medical parameters should be changed to improve the patient’s health state.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adams, K.F., Fonarow, G.C., Emerman, C.L., et al.: Characteristics and outcomes of patients hospitalized for heart failure in the united states: Rationale, design, and preliminary observations from the first 100, 000 cases in the acute decompensated heart failure national registry (ADHERE). Am. Heart J. 149(2), 209–216 (2005). https://doi.org/10.1016/j.ahj.2004.08.005
Amann, J., Blasimme, A., Vayena, E., et al.: Explainability for artificial intelligence in healthcare. BMC Med. Inform. Decis. Mak. 20, 310 (2020)
Bundgaard, J.S., Thune, J.J., Torp-Pedersen, C., et al.: Self-reported health status and the associated risk of mortality in heart failure: the DANISH trial. J. Psychosom. Res. 137, 110220 (2020). https://doi.org/10.1016/j.jpsychores.2020.110220
Chen, Y., Qi, B.: Representation learning in intraoperative vital signs for heart failure risk prediction. BMC Med. Inform. Decis. Mak. 19, 260 (2019)
Costanzo, M.R., Guglin, M.E., Saltzberg, M.T., et al.: Ultrafiltration versus intravenous diuretics for patients hospitalized for acute decompensated heart failure. J. Am. Coll. Cardiol. 49(6), 675–683 (2007). https://doi.org/10.1016/j.jacc.2006.07.073
Dave, D., Naik, H., Singhal, S., Patel, P.: Explainable AI meets healthcare: a study on heart disease dataset. CoRR abs/2011.03195 (2020)
Gontarska, K., Wrazen, W., Beilharz, J., Schmid, R., Thamsen, L., Polze, A.: Predicting medical interventions from vital parameters: towards a decision support system for remote patient monitoring. In: Tucker, A., Henriques Abreu, P., Cardoso, J., Pereira Rodrigues, P., Riaño, D. (eds.) AIME 2021. LNCS (LNAI), vol. 12721, pp. 293–297. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-77211-6_33
Heinze, T., Wierschke, R., Schacht, A., von Löwis, M.: A hybrid artificial intelligence system for assistance in remote monitoring of heart patients. In: Corchado, E., Kurzyński, M., Woźniak, M. (eds.) HAIS 2011. LNCS (LNAI), vol. 6679, pp. 413–420. Springer, Cham (2011). https://doi.org/10.1007/978-3-642-21222-2_50
Jenkins, S.: Sports science handbook: V. 1. Multi Science Publishing (2005)
Jia, Y., McDermid, J., Habli, I.: Enhancing the value of counterfactual explanations for deep learning. In: Tucker, A., Henriques Abreu, P., Cardoso, J., Pereira Rodrigues, P., Riaño, D. (eds.) AIME 2021. LNCS (LNAI), vol. 12721, pp. 389–394. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-77211-6_46
Koehler, F., Koehler, K., Deckwart, O., et al.: Efficacy of telemedical interventional management in patients with heart failure (tim-hf2): a randomised, controlled, parallel-group, unmasked trial. Lancet (2018)
Kopitar, L., Cilar, L., Kocbek, P., Stiglic, G.: Local vs. global interpretability of machine learning models in type 2 diabetes mellitus screening. In: Marcos, M., Juarez, J.M., Lenz, R., Nalepa, G.J., Nowaczyk, S., Peleg, M., Stefanowski, J., Stiglic, G. (eds.) KR4HC/TEAAM -2019. LNCS (LNAI), vol. 11979, pp. 108–119. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-37446-4_9
Kumar, P.: Kumar & clark’s medical management and therapeutics. W B Saunders (2011)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Adv Neural Inf Process Systs 30, pp. 4765–4774. Curran Associates, Inc. (2017)
Miller, W.L.: Fluid volume overload and congestion in heart failure. Circ. Heart Fail 9(8) (2016). https://doi.org/10.1161/circheartfailure.115.002922
Moreno-Sanchez, P.A.: Development of an explainable prediction model of heart failure survival by using ensemble trees. In: 2020 IEEE International Conference on Big Data (Big Data), pp. 4902–4910 (2020)
Pawar, U., O’Shea, D., Rea, S., O’Reilly, R.: Explainable AI in healthcare. In: 2020 Int. Conf. Cyber Situational Aware. Data Anal. Assess. CyberSA, pp. 1–2 (2020)
Samek, W., Binder, A., Montavon, G., et al.: Evaluating the visualization of what a deep neural network has learned. IEEE Trans. Neural Netw. Learn. Syst. 28(11), 2660–2673 (2017). https://doi.org/10.1109/TNNLS.2016.2599820
Shen, L., Margolies, L.R., Rothstein, J.H., et al.: Deep learning to improve breast cancer detection on screening mammography. Sci. Rep. 9, 12495 (2019)
Stegmann, T., Koehler, K., Wachter, R., et al.: Heart failure patients with atrial fibrillation benefit from remote patient management: insights from the TIM-HF2 trial. ESC Heart Fail. 7(5), 2516–2526 (2020). https://doi.org/10.1002/ehf2.12819
Thom, T., Haase, N., Rosamond, W., et al.: Heart disease and stroke statistics—2006 update. Circulation 113(6) (2006). https://doi.org/10.1161/circulationaha.105.171600
Tian, J., Yuan, Y., Shen, M., et al.: Association of resting heart rate and its change with incident cardiovascular events in the middle-aged and older Chinese. Sci. Rep. 9 (2019). https://doi.org/10.1038/s41598-019-43045-5
Wang, D., Yang, Q., Abdul, A., Lim, B.Y.: Designing theory-driven user-centric explainable AI, p. 1–15. ACM (2019)
Zhang, D., Wang, W., Li, F.: Association between resting heart rate and coronary artery disease, stroke, sudden death and noncardiovascular diseases: a meta-analysis. CMAJ 188(15), E384–E392 (2016). https://doi.org/10.1503/cmaj.160050
Acknowledgment
We thank Prof. Dr. med. Friedrich Köhler and his team for the access to the database and valuable feedback regarding our evaluation. This research has been supported by the Federal Ministry for Economic Affairs and Energy of Germany as part of the program Smart Data (01MD19014C).
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
Wrazen, W., Gontarska, K., Grzelka, F., Polze, A. (2023). Explainable AI for Medical Event Prediction for Heart Failure Patients. 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_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-34344-5_12
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)