Papers
Topics
Authors
Recent
Search
2000 character limit reached

Using explainable AI to investigate electrocardiogram changes during healthy aging -- from expert features to raw signals

Published 11 Oct 2023 in eess.SP, cs.LG, and stat.ML | (2310.07463v2)

Abstract: Cardiovascular diseases remain the leading global cause of mortality. Age is an important covariate whose effect is most easily investigated in a healthy cohort to properly distinguish the former from disease-related changes. Traditionally, most of such insights have been drawn from the analysis of electrocardiogram (ECG) feature changes in individuals as they age. However, these features, while informative, may potentially obscure underlying data relationships. In this paper we present the following contributions: (1) We employ a deep-learning model and a tree-based model to analyze ECG data from a robust dataset of healthy individuals across varying ages in both raw signals and ECG feature format. (2) We use explainable AI methods to identify the most discriminative ECG features across age groups.(3) Our analysis with tree-based classifiers reveals age-related declines in inferred breathing rates and identifies notably high SDANN values as indicative of elderly individuals, distinguishing them from younger adults. (4) Furthermore, the deep-learning model underscores the pivotal role of the P-wave in age predictions across all age groups, suggesting potential changes in the distribution of different P-wave types with age. These findings shed new light on age-related ECG changes, offering insights that transcend traditional feature-based approaches.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. M. Vaduganathan, G. A. Mensah, J. V. Turco, V. Fuster, and G. A. Roth, “The global burden of cardiovascular diseases and risk,” Journal of the American College of Cardiology, vol. 80, no. 25, pp. 2361–2371, 2022.
  2. S. Pavanello, M. Campisi, A. Fabozzo, G. Cibin, V. Tarzia, G. Toscano, and G. Gerosa, “The biological age of the heart is consistently younger than chronological age,” Scientific Reports, vol. 10, no. 1, Jul. 2020.
  3. E. Zvuloni, J. Read, A. H. Ribeiro, A. L. P. Ribeiro, and J. A. Behar, “On merging feature engineering and deep learning for diagnosis, risk prediction and age estimation based on the 12-lead ECG,” IEEE Transactions on Biomedical Engineering, vol. 70, no. 7, pp. 2227–2236, Jul. 2023.
  4. Z. I. Attia, P. A. Friedman, P. A. Noseworthy, F. Lopez-Jimenez, D. J. Ladewig, G. Satam, P. A. Pellikka, T. M. Munger, S. J. Asirvatham, C. G. Scott, R. E. Carter, and S. Kapa, “Age and sex estimation using artificial intelligence from standard 12-lead ECGs,” Circulation: Arrhythmia and Electrophysiology, vol. 12, no. 9, Sep. 2019.
  5. N. Strodthoff, P. Wagner, T. Schaeffter, and W. Samek, “Deep learning for ecg analysis: Benchmarks and insights from ptb-xl,” IEEE Journal of Biomedical and Health Informatics, vol. 25, no. 5, pp. 1519–1528, 2020.
  6. K. H. Lee and S. Byun, “Age prediction in healthy subjects using RR intervals and heart rate variability: A pilot study based on deep learning,” Applied Sciences, vol. 13, no. 5, p. 2932, Feb. 2023.
  7. A. Schumann, C. Gaser, R. Sabeghi, P. C. Schulze, S. Festag, C. Spreckelsen, and K.-J. Bär, “Using machine learning to estimate the calendar age based on autonomic cardiovascular function,” Frontiers in Aging Neuroscience, vol. 14, Jan. 2023.
  8. L. Garavaglia, D. Gulich, M. M. Defeo, J. T. Mailland, and I. M. Irurzun, “The effect of age on the heart rate variability of healthy subjects,” PLOS ONE, vol. 16, no. 10, p. e0255894, Oct. 2021.
  9. S. M. Z. S. Bukhari and I. Akhtar, “HRV dynamical analysis of cardiac autonomic activity of healthy subjects with age,” in 2023 International Conference on Robotics and Automation in Industry (ICRAI).   IEEE, Mar. 2023.
  10. A. Schumann and K.-J. Bär, “Autonomic aging – a dataset to quantify changes of cardiovascular autonomic function during healthy aging,” Scientific Data, vol. 9, no. 1, Mar. 2022.
  11. A. L. Goldberger, L. A. N. Amaral, L. Glass, J. M. Hausdorff, P. C. Ivanov, R. G. Mark, J. E. Mietus, G. B. Moody, C.-K. Peng, and H. E. Stanley, “PhysioBank, PhysioToolkit, and PhysioNet,” Circulation, vol. 101, no. 23, pp. e215–e220, 2000.
  12. L. C. Brant, A. H. Ribeiro, M. M. Pinto-Filho, J. Kornej, S. R. Preis, J. L. Fetterman, O. B. Eromosele, J. W. Magnani, J. M. Murabito, M. G. Larson, E. J. Benjamin, A. L. Ribeiro, and H. Lin, “Association between electrocardiographic age and cardiovascular events in community settings: The framingham heart study,” Circulation: Cardiovascular Quality and Outcomes, Jun. 2023.
  13. E. Merdjanovska and A. Rashkovska, “Comprehensive survey of computational ECG analysis: Databases, methods and applications,” Expert Systems with Applications, vol. 203, p. 117206, Oct. 2022.
  14. A. Kalyakulina, I. Yusipov, M. G. Bacalini, A. Moskalev, C. Franceschi, and M. Ivanchenko, “explainable artificial intelligence (xai) in aging clock models,” 2023.
  15. Y. M. Ayano, F. Schwenker, B. D. Dufera, and T. G. Debelee, “Interpretable machine learning techniques in ECG-based heart disease classification: A systematic review,” Diagnostics, vol. 13, no. 1, p. 111, Dec. 2022.
  16. T. Bender, J. M. Beinecke, D. Krefting, C. Müller, H. Dathe, T. Seidler, N. Spicher, and A.-C. Hauschild, “Analysis of a deep learning model for 12-lead ECG classification reveals learned features similar to diagnostic criteria,” IEEE Journal of Biomedical and Health Informatics, pp. 1–12, 2023.
  17. P. Wagner, T. Mehari, W. Haverkamp, and N. Strodthoff, “Explaining deep learning for ecg analysis: Building blocks for auditing and knowledge discovery,” arXiv preprint arXiv:2305.17043, 2023.
  18. A. Schumann and K.-J. Bär, “Autonomic aging–a dataset to quantify changes of cardiovascular autonomic function during healthy aging,” Scientific Data, vol. 9, no. 1, p. 95, 2022.
  19. T. Mehari and N. Strodthoff, “Towards quantitative precision for ECG analysis: Leveraging state space models, self-supervision and patient metadata,” IEEE Journal of Biomedical and Health Informatics, pp. 1–9, 2023.
  20. G. Ott, Y. Schaubelt, J. M. Lopez Alcaraz, W. Haverkamp, and N. Strodthoff, “ECG-aging,” Oct. 2023. [Online]. Available: https://github.com/AI4HealthUOL/ECG-aging
  21. D. Makowski, T. Pham, Z. J. Lau, J. C. Brammer, F. Lespinasse, H. Pham, C. Schölzel, and S. H. A. Chen, “NeuroKit2: A python toolbox for neurophysiological signal processing,” Behavior Research Methods, vol. 53, no. 4, pp. 1689–1696, Feb. 2021.
  22. P. V. Gent, H. Farah, N. V. Nes, and B. V. Arem, “Analysing noisy driver physiology real-time using off-the-shelf sensors: Heart rate analysis software from the taking the fast lane project,” Journal of Open Research Software, vol. 7, no. 1, p. 32, Oct. 2019.
  23. S. M. Lundberg, G. Erion, H. Chen, A. DeGrave, J. M. Prutkin, B. Nair, R. Katz, J. Himmelfarb, N. Bansal, and S.-I. Lee, “From local explanations to global understanding with explainable ai for trees,” Nature machine intelligence, vol. 2, no. 1, pp. 56–67, 2020.
  24. T. Mehari, A. Sundar, A. Bosnjakovic, P. Harris, S. E. Williams, A. Loewe, O. Doessel, C. Nagel, N. Strodthoff, and P. J. Aston, “Ecg feature importance rankings: Cardiologists vs. algorithms,” arXiv preprint arXiv:2304.02577, 2023.
  25. T. Mehari and N. Strodthoff, “Self-supervised representation learning from 12-lead ECG data,” Computers in Biology and Medicine, vol. 141, p. 105114, Feb. 2022.
  26. T. He, Z. Zhang, H. Zhang, Z. Zhang, J. Xie, and M. Li, “Bag of tricks for image classification with convolutional neural networks,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 558–567.
  27. I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” in International Conference on Learning Representations, 2018.
  28. T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2980–2988.
  29. P. Wagner, T. Mehari, W. Haverkamp, and N. Strodthoff, “Explaining deep learning for ecg analysis: Building blocks for auditing and knowledge discovery,” 2023.
  30. J. E. Mietus, “The pNNx files: re-examining a widely used heart rate variability measure,” Heart, vol. 88, no. 4, pp. 378–380, Oct. 2002.
  31. O. Barquero-Perez, J. M. de Sa, J. L. Rojo-Alvarez, and R. Goya-Esteban, “Changes in detrended fluctuation indices with aging in healthy and congestive heart failure subjects,” in 2008 Computers in Cardiology.   IEEE, Sep. 2008.
  32. N. Iyengar, C. K. Peng, R. Morin, A. L. Goldberger, and L. A. Lipsitz, “Age-related alterations in the fractal scaling of cardiac interbeat interval dynamics,” American Journal of Physiology-Regulatory, Integrative and Comparative Physiology, vol. 271, no. 4, pp. R1078–R1084, Oct. 1996.
  33. M. D. Costa, R. B. Davis, and A. L. Goldberger, “Heart rate fragmentation: A new approach to the analysis of cardiac interbeat interval dynamics,” Frontiers in Physiology, vol. 8, May 2017.
  34. R. Havmoller, J. Carlson, F. Holmqvist, A. Herreros, C. J. Meurling, B. Olsson, and P. Platonov, “Age-related changes in p wave morphology in healthy subjects,” BMC Cardiovascular Disorders, vol. 7, no. 1, Jul. 2007.
  35. A. Takayama, T. Nagamine, and K. Kotani, “Aging is independently associated with an increasing normal respiratory rate among an older adult population in a clinical setting: A cross-sectional study,” Geriatrics and Gerontology International, vol. 19, no. 11, pp. 1179–1183, Oct. 2019.
  36. A. Rodríguez-Molinero, L. Narvaiza, J. Ruiz, and C. Gálvez-Barrón, “Normal respiratory rate and peripheral blood oxygen saturation in the elderly population,” Journal of the American Geriatrics Society, vol. 61, no. 12, pp. 2238–2240, Dec. 2013.
  37. K. M. Zareba, V. T. Truong, W. Mazur, S. M. Smart, X. Xia, J.-P. Couderc, and S. V. Raman, “T-wave and its association with myocardial fibrosis on cardiovascular magnetic resonance examination,” Annals of Noninvasive Electrocardiology, vol. 26, no. 2, Dec. 2020.
  38. F. Bocchi, P. Marques-Vidal, E. Pruvot, G. Waeber, P. Vollenweider, and D. Gachoud, “Clinical and biological determinants of p-wave duration: cross-sectional data from the population-based CoLaus||||PsyCoLaus study,” BMJ Open, vol. 10, no. 11, p. e038828, Nov. 2020.
  39. P. Giovanardi, C. Vernia, E. Tincani, C. Giberti, F. Silipo, and A. Fabbo, “Combined effects of age and comorbidities on electrocardiographic parameters in a large non-selected population,” Journal of Clinical Medicine, vol. 11, no. 13, 2022.
  40. H. Turhan, E. Yetkin, O. Sahin, A. S. Yasar, K. Senen, R. Atak, H. Sasmaz, and S. Cehreli, “Comparison of p-wave duration and dispersion in patients aged ≥\geq≥65 years with those aged ≤\leq≤45 years,” Journal of Electrocardiology, vol. 36, no. 4, pp. 321–326, Oct. 2003.
  41. T. Lindow, I. Palencia-Lamela, T. T. Schlegel, and M. Ugander, “Heart age estimated using explainable advanced electrocardiography,” Scientific Reports, vol. 12, no. 1, p. 9840, 2022.
  42. J. Vielhaben, S. Blücher, and N. Strodthoff, “Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees,” Transactions on Machine Learning Research, 2023. [Online]. Available: https://openreview.net/forum?id=KxBQPz7HKh
Citations (5)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up for Free