An explainable machine learning system for left bundle branch block detection and classification

  1. Macas, Beatriz 23
  2. Garrigós, Javier 1
  3. Martínez, José Javier 1
  4. Ferrández, José Manuel 1
  5. Bonomini, María Paula 12
  1. 1 Departamento de Electrónica, Tecnología de Computadoras y Proyectos, Universidad Politécnica de Cartagena, Cartagena, Spain
  2. 2 Instituto Argentino de Matemática Alberto P. Calderṕn (IAM, CONICET), Argentina
  3. 3 Instituto de Ingeniería Biomédica, Fac. de Ingeniería, Universidad de Buenos Aires (FIUBA), Argentina
Mostrar afiliaciones +
Revista:
Integrated Computer-Aided Engineering

ISSN: 1069-2509,  1875-8835

Año de publicación: 2023

Páginas: 1-16

Tipo: Artículo

DOI: 10.3233/ICA-230719 GOOGLE SCHOLAR lock_openAcceso abierto editor

Otras publicaciones en: Integrated Computer-Aided Engineering

Resumen

Left bundle branch block is a cardiac conduction disorder that occurs when the electrical impulses that control the heartbeat are blocked or delayed as they travel through the left bundle branch of the cardiac conduction system providing a characteristic electrocardiogram (ECG) pattern. We use a reduced set of biologically inspired features extracted from ECG data is proposed and used to train a variety of machine learning models for the LBBB classification task. Then, different methods are used to evaluate the importance of the features in the classification process of each model and to further reduce the feature set while maintaining the classification performance of the models. The performances obtained by the models using different metrics improve those obtained by other authors in the literature on the same dataset. Finally, XAI techniques are used to verify that the predictions made by the models are consistent with the existing relationships between the data. This increases the reliability of the models and their usefulness in the diagnostic support process. Thes

Referencias bibliográficas

  • Sankari, (2011), Computers in Biology and Medicine, 41, pp. 211, 10.1016/j.compbiomed.2011.02.002
  • Martis, (2014), Computers in Biology and Medicine, 48, pp. 133, 10.1016/j.compbiomed.2014.02.012
  • Martis, (2014), Biomedical Signal Processing and Control, 13, pp. 295, 10.1016/j.bspc.2014.04.001
  • Strauss, (2011), American Journal of Cardiology, 107, pp. 927, 10.1016/j.amjcard.2010.11.010
  • Galeotti, (2014), EP Europace, 15, pp. 1816, 10.1093/europace/eut132
  • Emerek, (2015), Journal of Electrocardiology, 48, pp. 758, 10.1016/j.jelectrocard.2015.07.008
  • Hadjis, (2019), Pacing Clin Electrophysiol, 42, pp. 431, 10.1111/pace.13638
  • Zusterzeel, (2018), J Electrocardiol, 51, pp. 25, 10.1016/j.jelectrocard.2018.08.001
  • Gunning, (2017), Defense advanced research projects agency (DARPA), nd Web, 2, pp. 1
  • Adadi, (2018), IEEE Access, 6, pp. 52138, 10.1109/ACCESS.2018.2870052
  • Došilović, (2018), 2018 41st International convention on information and communication technology, electronics and microelectronics (MIPRO), pp. 210, 10.23919/MIPRO.2018.8400040
  • Arrieta, (2020), Information fusion, 58, pp. 82, 10.1016/j.inffus.2019.12.012
  • Shapley, (1953), Contributions to the Theory of Games II, pp. 307
  • Lundberg, (2017), Advances in Neural Information Processing Systems 30, pp. 4765
  • Lundberg S. Be Careful When Interpreting Predictive Models in Search of Causal Insights. Available from: https://towardsdatascience.com/be-careful-when-interpreting-predictive-models-in-search-of-causal-insights-e68626e664b6.
  • sktime: a unified framework for machine learning with time series. Available from: https://github.com/sktime/sktime.
  • Ding, (2008), Proceedings of the VLDB Endowment, 1, pp. 1542, 10.14778/1454159.1454226
  • Moss, (2009), New England Journal of Medicine, 361, pp. 1329, 10.1056/NEJMoa0906431
  • Edenbrandt, (1988), Journal of Electrocardiology, 21, pp. 361, 10.1016/0022-0736(88)90113-6
  • Ledezma CA. WTdelineator. 2021. Available from: https://github.com/caledezma/WTdelineator.
  • Bonomini, (2017), Medicina (B Aires), 77, pp. 7
  • Daniel, (2020), Journal of Electrocardiology, 63, pp. 35, 10.1016/j.jelectrocard.2020.09.008
  • Dempster, (2020), Data Mining and Knowledge Discovery, 34, pp. 1454, 10.1007/s10618-020-00701-z
  • Tan CW, Dempster A, Bergmeir C, Webb GI. MultiRocket: Multiple pooling operators and transformations for fast and effective time series classification. arXiv preprint arXiv: 210200457. 2022.
  • Middlehurst M, Large J, Flynn M, Lines J, Bostrom A, Bagnall A. HIVE-COTE 2.0: A New Meta Ensemble for Time Series Classification. Machine Learning. 2021.
  • Rodriguez, (2006), IEEE transactions on pattern analysis and machine intelligence, 28, pp. 1619, 10.1109/TPAMI.2006.211
  • Middlehurst, (2020), 2020 IEEE International Conference on Big Data (Big Data), pp. 1774
  • Middlehurst, (2020), European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, pp. 345
  • Geler, (2020), 2020 International Conference on INnovations in Intelligent SysTems and Applications (INISTA), pp. 1
  • Chan JYL, Leow SMH, Bea KT, Cheng WK, Phoong SW, Hong ZW, et al. Mitigating the Multicollinearity Problem and Its Machine Learning Approach: A Review. Mathematics. 2022; 10(8). Available from: https://www.mdpi.com/2227-7390/10/8/1283.
  • Zuur, (2010), Methods in Ecology and Evolution, 1, pp. 3, 10.1111/j.2041-210X.2009.00001.x
  • Menze, (2009), BMC Bioinformatics, 10, pp. 213, 10.1186/1471-2105-10-213
  • Jović, (2015), 2015 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), pp. 1200, 10.1109/MIPRO.2015.7160458
  • Guyon, (2002), Machine Learning, 46, pp. 389, 10.1023/A:1012487302797
  • Breiman, (2001), Machine Learning, 45, pp. 5, 10.1023/A:1010933404324
  • Adeli, (1990), Engineering Applications of Artificial Intelligence, 3, pp. 127, 10.1016/0952-1976(90)90006-8
  • Adeli H, Balasubramanyam KV. Expert Systems for Structural Design – A New Generation. Englewood Cliffs, New Jersey: Prentice-Hall; 1988.
  • Luo, (2023), Computer-Aided Civil and Infrastructure Engineering, 38, pp. 26, 10.1111/mice.12823
  • Dau, (2018), Data mining and knowledge discovery, 32, pp. 1074, 10.1007/s10618-018-0565-y
  • Kruskal, (1952), Journal of the American Statistical Association, 47, pp. 583, 10.1080/01621459.1952.10483441
  • Lundberg, (2020), Nature Machine Intelligence, 2, pp. 2522, 10.1038/s42256-019-0138-9
  • Lundberg, (2018), Nature Biomedical Engineering, 2, pp. 749, 10.1038/s41551-018-0304-0
  • Smisek, (2018), J Electrocardiol, 51, pp. S31, 10.1016/j.jelectrocard.2018.06.013
  • Yang, (2020), Physiol Meas, 41, pp. 025005, 10.1088/1361-6579/ab6e55
  • Bonomini, (2019), Biomedical Signal Processing and Control, 49, pp. 540, 10.1016/j.bspc.2018.12.009
  • Bonomini, (2021), J Interv Card Electrophysiol, 62, pp. 479, 10.1007/s10840-021-00999-9
  • Pérez-Riera A, Barbosa-Barros R, Daminello-Raimundo R, et al. Re-evaluating the electro-vectorcardiographic criteria for left bundle branch block. Ann Noninvasive Electrocardiol. 2019; 24.
  • Halamek, (2019), PLoS One, 14, pp. 1, 10.1371/journal.pone.0217097
  • Emerek, (2019), Heart Rhythm, 16, pp. 213, 10.1016/j.hrthm.2018.08.028
  • Bonomini, (2018), Journal of Electrocardiology, 51, pp. 844, 10.1016/j.jelectrocard.2018.06.011
  • Rafiei, (2017), IEEE Transactions on Neural Networks and Learning Systems, 28, pp. 3074, 10.1109/TNNLS.2017.2682102
  • Pereira, (2020), Neural Computing and Applications, 32, pp. 6393, 10.1007/s00521-019-04146-4
  • Alam, (2020), Neural Computing with Applications, 32, pp. 8675, 10.1007/s00521-019-04359-7
  • Rafiei MH, Gauthier L, Adeli H, Takabi D. Self-Supervised Learning for Electroencephalography. IEEE Transactions on Neural Networks and Learning Systems. 2023.