Robust and Efficient Atrial Fibrillation Detection from Intracardiac Electrograms Using Minirocket

Year 2024, Volume: 16 Issue: 1, 432 - 447, 31.01.2024

Celal Alagoz

https://doi.org/10.29137/umagd.1409437

Abstract

Atrial Fibrillation (AF) detection from intracardiac Electrogram (EGM) signals is a critical aspect of cardiovascular health monitoring. This study explores the application of Minirocket, a time series classification (TSC) algorithm, for robust and efficient AF detection. A comparative analysis is conducted against a deep learning approach using a subset of the dataset from Rodrigo et al. (2022). The study investigates the robustness of Minirocket in the face of shorter EGM sequences and varying training sizes, essential for real-world applications such as wearable and implanted devices. Empirical runtime analysis further assesses the efficiency of Minirocket in comparison to conventional machine learning (ML) algorithms. The results showcase Minirocket's notable performance, especially in scenarios with shorter signals and varying training sizes, making it a promising candidate for streamlined AF detection in emerging cardiovascular monitoring technologies. This research contributes to the optimization of AF detection algorithms for increased efficiency and adaptability to dynamic clinical scenarios.

Keywords

Atrial Fibrillation, Intracardiac Electrograms, Machine Learning, Time Series Classification

Thanks

The author expresses gratitude to Miguel Rodrigo for generously providing the dataset, as well as for valuable discussions and guidance regarding the data.

Minirocket Kullanarak Güçlendirilmiş ve Verimli Atriyal Fibrilasyon Tespiti

Abstract

Atriyal Fibrilasyon (AF) tespiti, intrakardiyak Elektrogram (EGM) sinyallerinin kritik bir yönüdür ve kardiyovasküler sağlık izlemesinin önemli bir parçasını oluşturur. Bu çalışma, güçlendirilmiş ve verimli AF tespiti için bir zaman serisi sınıflandırma (TSC) algoritması olan Minirocket'ın uygulanmasını keşfeder. Rodrigo et al. (2022) tarafından elde edilen veri setinin bir alt kümesi üzerinde karşılaştırmalı bir analiz gerçekleştirilir. Çalışma, Minirocket'ın kısa EGM dizileri ve değişen eğitim büyüklükleri karşısındaki direncini araştırır; bu, giyilebilir ve implante edilebilir cihazlar gibi gerçek dünya uygulamaları için önemlidir. Ampirik çalışma süresi analizi, Minirocket'ın geleneksel makine öğrenimi algoritmalarına kıyasla verimliliğini değerlendirir. Sonuçlar, özellikle kısa sinyaller ve değişen eğitim büyüklükleri senaryolarında Minirocket'ın dikkate değer performansını sergiler, böylece geleceğin kardiyovasküler izleme teknolojilerinde AF tespiti için umut vadeden bir aday olarak öne çıkar. Bu araştırma, AF tespit algoritmalarının verimliliğinin artırılması ve dinamik klinik senaryolara adapte edilmesi konusunda katkıda bulunur.

Keywords

Atrial Fibrilasyon, Elektrogramlar, Makine Öğrenme, Zaman Serisi Sınıflandırma

References

• Alhusseini, M. I., Abuzaid, F., Rogers, A. J., Zaman, J. A., Baykaner, T., Clopton, P., ... & Narayan, S. M. (2020). Machine learning to classify intracardiac electrical patterns during atrial fibrillation: machine learning of atrial fibrillation. Circulation: Arrhythmia and Electrophysiology, 13(8), e008160.
• Bayoumy, K., Gaber, M., Elshafeey, A., Mhaimeed, O., Dineen, E. H., Marvel, F. A., ... & Elshazly, M. B. (2021). Smart wearable devices in cardiovascular care: where we are and how to move forward. Nature Reviews Cardiology, 18(8), 581-599.
• Bentéjac, C., Csörgő, A., & Martínez-Muñoz, G. (2021). A comparative analysis of gradient boosting algorithms. Artificial Intelligence Review, 54, 1937-1967.
• Bottou, L., Curtis, F. E., & Nocedal, J. (2018). Optimization methods for large-scale machine learning. SIAM review, 60(2), 223-311.
• Dau, H., Bagnall, A., Kamgar, K., Yeh, M., Zhu, Y., Gharghabi, S., Ratanamahatana, C., Chotirat, A., & Keogh, E. (2019). The UCR time series archive. IEEE/CAA Journal of Automatica Sinica, 6(6), 1293–1305.
• Dempster, A., Petitjean, F., & Webb, G. I. (2020a). ROCKET: exceptionally fast and accurate time series classification using random convolutional kernels. Data Mining and Knowledge Discovery, 34(5), 1454-1495.
• Dempster, A. (2020b). A Very Fast (Almost) Deterministic Transform for Time Series Classification Angus Dempster, Daniel F. Schmidt, Geoffrey I. Webb. arXiv preprint arXiv:2012.08791.
• Fulcher, B. D., Little, M. A., & Jones, N. S. (2013). Highly comparative time-series analysis: the empirical structure of time series and their methods. Journal of the Royal Society Interface, 10(83), 20130048.
• Fulcher, B. D., & Jones, N. S. (2017). hctsa: A computational framework for automated time-series phenotyping using massive feature extraction. Cell systems, 5(5), 527-531.
• Haissaguerre, M., Marcus, F. I., Fischer, B., & Clementy, J. (1994). Radiofrequency catheter ablation in unusual mechanisms of atrial fibrillation: report of three cases. Journal of cardiovascular electrophysiology, 5(9), 743-751.
• Hannun, A. Y., Rajpurkar, P., Haghpanahi, M., Tison, G. H., Bourn, C., Turakhia, M. P., & Ng, A. Y. (2019). Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nature medicine, 25(1), 65-69.
• Honarbakhsh, S., Schilling, R. J., Providência, R., Dhillon, G., Sawhney, V., Martin, C. A., ... & Hunter, R. J. (2017). Panoramic atrial mapping with basket catheters: A quantitative analysis to optimize practice, patient selection, and catheter choice. Journal of cardiovascular electrophysiology, 28(12), 1423-1432.
• Hong, Y. J., Jeong, H., Cho, K. W., Lu, N., & Kim, D. H. (2019). Wearable and implantable devices for cardiovascular healthcare: from monitoring to therapy based on flexible and stretchable electronics. Advanced Functional Materials, 29(19), 1808247.
• Isa, R., Villacastín, J., Moreno, J., Pérez-Castellano, N., Salinas, J., Doblado, M., ... & Macaya, C. (2007). Differentiating between atrial flutter and atrial fibrillation using right atrial bipolar endocardial signals. Revista Española de Cardiología (English Edition), 60(2), 104-109.
• Jang, J. K., Park, J. S., Kim, Y. H., Choi, J. I., Lim, H. E., Pak, H. N., & Kim, Y. H. (2010). Coexisting sustained tachyarrthymia in patients with atrial fibrillation undergoing catheter ablation. Korean Circulation Journal, 40(5), 235-238.
• Katritsis, D., Iliodromitis, E., Fragakis, N., Adamopoulos, S., & Kremastinos, D. (1996). Ablation therapy of type I atrial flutter may eradicate paroxysmal atrial fibrillation. American Journal of Cardiology, 78(3), 345-347.
• LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. nature, 521(7553), 436-444.
• Lubba, C. H., Sethi, S. S., Knaute, P., Schultz, S. R., Fulcher, B. D., & Jones, N. S. (2019). catch22: CAnonical Time-series CHaracteristics: Selected through highly comparative time-series analysis. Data Mining and Knowledge Discovery, 33(6), 1821-1852.
• Middlehurst, M., Large, J., Flynn, M., Lines, J., Bostrom, A., & Bagnall, A. (2021). HIVE-COTE 2.0: a new meta ensemble for time series classification. Machine Learning, 110(11-12), 3211-3243.
• Mietus, J. E., Peng, C. K., Henry, I., Goldsmith, R. L., & Goldberger, A. L. (2002). The pNNx files: re-examining a widely used heart rate variability measure. Heart, 88(4), 378-380.
• Palma, E. C., Ferrick, K. J., Gross, J. N., Kim, S. G., & Fisher, J. D. (2000). Transition from atrioventricular node reentry tachycardia to atrial fibrillation begins in the pulmonary veins. Circulation, 102(8), 937-937.
• Rodrigo, M., Waddell, K., Magee, S., Rogers, A. J., Alhusseini, M., Hernandez-Romero, I., ... & Narayan, S. M. (2021). Non-invasive spatial mapping of frequencies in atrial fibrillation: Correlation with contact mapping. Frontiers in Physiology, 11, 611266.
• Rodrigo, M., Alhusseini, M. I., Rogers, A. J., Krittanawong, C., Thakur, S., Feng, R., ... & Narayan, S. M. (2022). Atrial fibrillation signatures on intracardiac electrograms identified by deep learning. Computers in biology and medicine, 145, 105451.
• Sana, F., Isselbacher, E. M., Singh, J. P., Heist, E. K., Pathik, B., & Armoundas, A. A. (2020). Wearable devices for ambulatory cardiac monitoring: JACC state-of-the-art review. Journal of the American College of Cardiology, 75(13), 1582-1592.
• Shifaz, A., Pelletier, C., Petitjean, F., & Webb, G. I. (2020). TS-CHIEF: a scalable and accurate forest algorithm for time series classification. Data Mining and Knowledge Discovery, 34(3), 742-775.
• Siddiqi, H. K., Vinayagamoorthy, M., Gencer, B., Ng, C., Pester, J., Cook, N. R., ... & Albert, C. M. (2022). Sex differences in atrial fibrillation risk: the VITAL Rhythm Study. JAMA cardiology, 7(10), 1027-1035.
• Smith, S. W., Rapin, J., Li, J., Fleureau, Y., Fennell, W., Walsh, B. M., ... & Gardella, C. (2019). A deep neural network for 12-lead electrocardiogram interpretation outperforms a conventional algorithm, and its physician overread, in the diagnosis of atrial fibrillation. IJC Heart & Vasculature, 25, 100423.
• Wang, X., Wirth, A., & Wang, L. (2007, October). Structure-based statistical features and multivariate time series clustering. In Seventh IEEE international conference on data mining (ICDM 2007) (pp. 351-360). IEEE.
• Weng, L. C., Preis, S. R., Hulme, O. L., Larson, M. G., Choi, S. H., Wang, B., ... & Lubitz, S. A. (2018). Genetic predisposition, clinical risk factor burden, and lifetime risk of atrial fibrillation. Circulation, 137(10), 1027-1038.