Interpretation of Intracardiac Electrograms Through Textual Representations

William Han, Diana Guadalupe Gomez, Avi Alok, Chaojing Duan, Michael A Rosenberg, Douglas J Weber, Emerson Liu, Ding Zhao
Proceedings of the fifth Conference on Health, Inference, and Learning, PMLR 248:7-23, 2024.

Abstract

Understanding the irregular electrical activity of atrial fibrillation (AFib) has been a key challenge in electrocardiography. For serious cases of AFib, catheter ablations are performed to collect intracardiac electrograms (EGMs). EGMs offer intricately detailed and localized electrical activity of the heart and are an ideal modality for interpretable cardiac studies. Recent advancements in artificial intelligence (AI) has allowed some works to utilize deep learning frameworks to interpret EGMs during AFib. Additionally, language models (LMs) have shown exceptional performance in being able to generalize to unseen domains, especially in healthcare. In this study, we are the first to leverage pretrained LMs for finetuning of EGM interpolation and AFib classification via masked language modeling. We formulate the EGM as a textual sequence and present competitive performances on AFib classification compared against other representations. Lastly, we provide a comprehensive interpretability study to provide a multi-perspective intuition of the model’s behavior, which could greatly benefit the clinical use.

Cite this Paper

BibTeX
@InProceedings{pmlr-v248-han24a, title = {Interpretation of Intracardiac Electrograms Through Textual Representations}, author = {Han, William and Guadalupe Gomez, Diana and Alok, Avi and Duan, Chaojing and Rosenberg, Michael A and Weber, Douglas J and Liu, Emerson and Zhao, Ding}, booktitle = {Proceedings of the fifth Conference on Health, Inference, and Learning}, pages = {7--23}, year = {2024}, editor = {Pollard, Tom and Choi, Edward and Singhal, Pankhuri and Hughes, Michael and Sizikova, Elena and Mortazavi, Bobak and Chen, Irene and Wang, Fei and Sarker, Tasmie and McDermott, Matthew and Ghassemi, Marzyeh}, volume = {248}, series = {Proceedings of Machine Learning Research}, month = {27--28 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v248/main/assets/han24a/han24a.pdf}, url = {https://proceedings.mlr.press/v248/han24a.html}, abstract = {Understanding the irregular electrical activity of atrial fibrillation (AFib) has been a key challenge in electrocardiography. For serious cases of AFib, catheter ablations are performed to collect intracardiac electrograms (EGMs). EGMs offer intricately detailed and localized electrical activity of the heart and are an ideal modality for interpretable cardiac studies. Recent advancements in artificial intelligence (AI) has allowed some works to utilize deep learning frameworks to interpret EGMs during AFib. Additionally, language models (LMs) have shown exceptional performance in being able to generalize to unseen domains, especially in healthcare. In this study, we are the first to leverage pretrained LMs for finetuning of EGM interpolation and AFib classification via masked language modeling. We formulate the EGM as a textual sequence and present competitive performances on AFib classification compared against other representations. Lastly, we provide a comprehensive interpretability study to provide a multi-perspective intuition of the model’s behavior, which could greatly benefit the clinical use.} }
Endnote
%0 Conference Paper %T Interpretation of Intracardiac Electrograms Through Textual Representations %A William Han %A Diana Guadalupe Gomez %A Avi Alok %A Chaojing Duan %A Michael A Rosenberg %A Douglas J Weber %A Emerson Liu %A Ding Zhao %B Proceedings of the fifth Conference on Health, Inference, and Learning %C Proceedings of Machine Learning Research %D 2024 %E Tom Pollard %E Edward Choi %E Pankhuri Singhal %E Michael Hughes %E Elena Sizikova %E Bobak Mortazavi %E Irene Chen %E Fei Wang %E Tasmie Sarker %E Matthew McDermott %E Marzyeh Ghassemi %F pmlr-v248-han24a %I PMLR %P 7--23 %U https://proceedings.mlr.press/v248/han24a.html %V 248 %X Understanding the irregular electrical activity of atrial fibrillation (AFib) has been a key challenge in electrocardiography. For serious cases of AFib, catheter ablations are performed to collect intracardiac electrograms (EGMs). EGMs offer intricately detailed and localized electrical activity of the heart and are an ideal modality for interpretable cardiac studies. Recent advancements in artificial intelligence (AI) has allowed some works to utilize deep learning frameworks to interpret EGMs during AFib. Additionally, language models (LMs) have shown exceptional performance in being able to generalize to unseen domains, especially in healthcare. In this study, we are the first to leverage pretrained LMs for finetuning of EGM interpolation and AFib classification via masked language modeling. We formulate the EGM as a textual sequence and present competitive performances on AFib classification compared against other representations. Lastly, we provide a comprehensive interpretability study to provide a multi-perspective intuition of the model’s behavior, which could greatly benefit the clinical use.
APA
Han, W., Guadalupe Gomez, D., Alok, A., Duan, C., Rosenberg, M.A., Weber, D.J., Liu, E. & Zhao, D.. (2024). Interpretation of Intracardiac Electrograms Through Textual Representations. Proceedings of the fifth Conference on Health, Inference, and Learning, in Proceedings of Machine Learning Research 248:7-23 Available from https://proceedings.mlr.press/v248/han24a.html.

Related Material