Interpretability of Machine Learning Models for Cardiac Arrhythmia Classification
Resumo
Context: Cardiovascular diseases, particularly cardiac arrhythmias, cause global mortality. Electrocardiograms (ECG) are essential for diagnoses. However, the automated analysis of ECG signals using machine learning faces interpretability challenges, which are crucial for accepting these models in medical practice. Problem: The classification of cardiac arrhythmias using machine learning faces resistance in the medical field due to the black-box nature of these models, which hinders the understanding of decisions and reduces professional trust. There is a need for interpretable models that reveal the critical factors in diagnosis, fostering the reliable use of artificial intelligence in healthcare. Solution: This work proposes an interpretable model for classifying cardiac arrhythmias, using machine learning to identify and visually explain the ECG features contributing to the diagnosis, with explanations at the model, class, and specific signal levels. IS Theory: This work is based on the Technology Acceptance Model (TAM), which suggests that "perceived usefulness" and "perceived ease of use" influence the intention to use a system. In healthcare, these perceptions relate to the model’s ability to provide clear and helpful explanations, facilitating medical professionals’ adoption of artificial intelligence (AI). Method: Instead of using raw biosignals, extracted ECG features are employed to enhance interpretability. This approach provides model-agnostic explanations at both local and global levels. Interpretability techniques are applied to clarify the contribution of each feature to the diagnosis. Summary of Results: Features such as the variability and median of RR and PR intervals and the signal-to-noise ratio of ECG signals are crucial for accurate arrhythmia classification. Contributions and Impact on IS: The approach allows for understanding the influence of specific ECG features on diagnosis, helping to identify patterns that support classification decisions and promoting the adoption of AI with trust and responsibility in medical practice.
Referências
Philine Lou Bommer, Marlene Kretschmer, Anna Hedström, Dilyara Bareeva, and Marina M.-C. Höhne. 2024. Finding the Right XAI Method—A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science. Artificial Intelligence for the Earth Systems 3, 3 (2024), e230074. DOI: 10.1175/ AIES-D-23-0074.1
Federico Cabitza, Andrea Campagner, and Clara Balsano. 2020. Bridging the “last mile” gap between AI implementation and operation: “data awareness” that matters. Annals of translational medicine 8, 7 (April 2020), 501.
Federico Cabitza, Andrea Campagner, and Luca Maria Sconfienza. 2020. As if sand were stone. New concepts and metrics to probe the ground on which to build trustable AI. BMC Medical Informatics and Decision Making 20, 1 (11 Sep 2020), 219. DOI: 10.1186/s12911-020-01224-9
Federico Cabitza, Davide Ciucci, and Raffaele Rasoini. 2019. A Giant with Feet of Clay: On the Validity of the Data that Feed Machine Learning in Medicine. In Organizing for the Digital World, Federico Cabitza, Carlo Batini, and Massimo Magni (Eds.). Springer International Publishing, Cham, 121–136.
Davide Chicco, Anna Karaiskou, and Maarten De Vos. 2024. Ten quick tips for electrocardiogram (ECG) signal processing. PeerJ Computer Science 10 (2024), e2295. DOI: 10.7717/peerj-cs.2295
Gari D Clifford, Chengyu Liu, Benjamin Moody, Li-Wei H Lehman, Ikaro Silva, Qiao Li, A E Johnson, and Roger G Mark. 2018. AF Classification from a Short Single Lead ECG Recording: the PhysioNet/Computing in Cardiology Challenge 2017.
Nick Erickson, Jonas Mueller, Alexander Shirkov, Hang Zhang, Pedro Larroy, Mu Li, and Alexander Smola. 2020. AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data. arXiv:2003.06505 [stat.ML] [link]
A. Goldberger, L. Amaral, L. Glass, J. Hausdorff, P. C. Ivanov, R. Mark, ..., and H. E. Stanley. 2000. PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation 101, 23 (2000), e215–e220. [link]
Yola Jones, Fani Deligianni, and Jeff Dalton. 2020. Improving ECG Classification Interpretability using Saliency Maps. , 675-682 pages. DOI: 10.1109/BIBE50027.2020.00114
Eunchan Kim, Jaehyuk Kim, Juyoung Park, Haneul Ko, and Yeunwoong Kyung. 2023. TinyML-Based Classification in an ECG Monitoring Embedded System. Computers, Materials & Continua 75, 1 (2023), 1751–1764. DOI: 10.32604/cmc.2023.031663
Zachary C. Lipton. 2018. The Mythos of Model Interpretability: In machine learning, the concept of interpretability is both important and slippery. Queue 16, 3 (jun 2018), 31–57. DOI: 10.1145/3236386.3241340
Scott M. Lundberg, Gabriel Erion, Hugh Chen, Alex DeGrave, Jordan M. Prutkin, Bala Nair, Ronit Katz, Jonathan Himmelfarb, Nisha Bansal, and Su-In Lee. 2020. From local explanations to global understanding with explainable AI for trees. Nature Machine Intelligence 2, 1 (01 Jan 2020), 56–67. DOI: 10.1038/s42256-019-0138-9
Scott M. Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems (Long Beach, California, USA) (NIPS’17). Curran Associates Inc., Red Hook, NY, USA, 4768–4777.
George B. Moody and Roger G. Mark. 2001. The impact of the MIT-BIH Arrhythmia Database. IEEE Engineering in Medicine and Biology Magazine 20 (2001), 45–50. [link]
Inês Neves, Duarte Folgado, Sara Santos, Marília Barandas, Andrea Campagner, Luca Ronzio, Federico Cabitza, and Hugo Gamboa. 2021. Interpretable heartbeat classification using local model-agnostic explanations on ECGs. Computers in Biology and Medicine 133 (2021), 104393. DOI: 10.1016/j.compbiomed.2021.104393
Jaya Ojha, Hårek Haugerud, Anis Yazidi, and Pedro G. Lind. 2024. Exploring Interpretable AI Methods for ECG Data Classification. In Proceedings of the 5th ACM Workshop on Intelligent Cross-Data Analysis and Retrieval (ICDAR ’24). Association for Computing Machinery, New York, NY, USA, 11–18. DOI: 10.1145/3643488.3660294
M. Ramkumar, C. Ganesh Babu, K Vinoth Kumar, D Hepsiba, A. Manjunathan, and R. Sarath Kumar. 2021. ECG Cardiac arrhythmias Classification using DWT, ICA and MLP Neural Networks. Journal of Physics: Conference Series 1831, 1 (mar 2021), 012015. DOI: 10.1088/1742-6596/1831/1/012015
Amit Sangroya, Suparshva Jain, Lovekesh Vig, C. Anantaram, Arijit Ukil, and Sundeep Khandelwal. 2022. Generating Conceptual Explanations for DL based ECG Classification Model. DOI: 10.32473/flairs.v35i.130681
Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. 2017. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. , 618-626 pages. DOI: 10.1109/ICCV.2017.74
T Sullivan. 2024. Half of Hospitals to Adopt Artificial Intelligence Within 5 Years. Healthcare IT News. [link] Accessed: 2024-11-14.
Mudrakola Swapna, Uma Maheswari Viswanadhula, Rajanikanth Aluvalu, Vijayakumar Vardharajan, and Ketan Kotecha. 2022. Bio-Signals in Medical Applications and Challenges Using Artificial Intelligence. DOI: 10.3390/jsan11010017
Jia Wu, Xiu-Yun Chen, Hao Zhang, Li-Dong Xiong, Hang Lei, and Si-Hao Deng. 2019. Hyperparameter Optimization for Machine Learning Models Based on Bayesian Optimizationb. Journal of Electronic Science and Technology 17, 1 (2019), 26–40. DOI: 10.11989/JEST.1674-862X.80904120
