Arrhythmia detection based on heart rate from photoplethysmography
DOI:
https://doi.org/10.46502/issn.2710-995X/2021.5.05Keywords:
arrhythmias, classification, systolic peak detection, heart rate, photoplethysmographic wave.Abstract
Cardiovascular diseases (CVD) kill about 18 million people each year which constitute the leading cause of death and disability worldwide. Among cardiovascular diseases, cardiac arrhythmias are the most common. For several years, new studies have highlighted the potential of the photoplethysmographic wave to detect arrhythmias, surpassing in simplicity and cost reduction to electrocardiography (ECG). This study proposes a method of detecting systolic peaks of the photoplethysmographic wave to determine the heart rate and establish the presence of tachycardia, bradycardia, or asystole. The systolic peak detection method calculates the first derivative of the previously filtered signal. It then applies a thresholding process. Finally, in a clustering stage, the DBSCAN algorithm is used. The peak detection algorithm was evaluated on 42 signals from an international multiparametric database for RR estimation. The evaluation of the method showed high accuracy and precision (0 ± 2 ms). The sensitivity and positive predictive value were 99%. These results allow determining the heart rate with accuracy and precision of 0 ± 1 beats per minute. The algorithm was evaluated in arrhythmia classification using 155 signals from the PhysioNet/Computing in Cardiology Challenge 2015 database. For this evaluation, the algorithm showed acceptable results for detecting asystole, bradycardia, and tachycardia. The sensitivity and positive predictive values were 79% and 88% for asystole, 74% and 64% for bradycardia, and 80% and 99% for tachycardia, respectively. The method's effectiveness may be affected in signals with significant variations in amplitude or low signal-to-noise ratios (SNR). However, the results under these conditions are still acceptable and are very good at high SNR signals.
Downloads
References
Asensi, J. O., de Francisco, M. T. I., Pérez, Ó. C., de Carranza, M. J. S. T., Rubio, J. A., Palop, C. P., ... & Dolz, L. M. (2021). Estudio RITHMI, capacidad diagnóstica de un monitor de ritmo cardiaco para la detección automática de fibrilación auricular. Revista Española de Cardiología, 74(7), 602-607.
Bonomi, A. G., Schipper, F., Eerikäinen, L. M., Margarito, J., Van Dinther, R., Muesch, G., ... & Dekker, L. R. (2018). Atrial fibrillation detection using a novel cardiac ambulatory monitor based on photo?plethysmography at the wrist. Journal of the American Heart Association, 7(15), e009351.
Castaneda, D., Esparza, A., Ghamari, M., Soltanpur, C., & Nazeran, H. (2018). A review on wearable photoplethysmography sensors and their potential future applications in health care. International Journal of Biosensors & Bioelectronics, 4, 195-202. doi: DOI: 10.15406/ijbsbe.2018.04.00125
Clifford, G. D., Silva, I., Moody, B., Li, Q., Kella, D., Shahin, A., ... & Mark, R. G. (2015). The PhysioNet/computing in cardiology challenge 2015: reducing false arrhythmia alarms in the ICU. Paper presented at the 2015 Computing in Cardiology Conference (CinC).
Constantén, S.B., Pepe, D.S and Mona, P. (2020). Anuario Estadístico de Salud 2020. Ministerio de Salud Pública de Cuba.
Coviello, J. S. (2020). ECG interpretation made incredibly easy!: Lippincott Williams & Wilkins.
Eerikäinen, L. M., Vanschoren, J., Rooijakkers, M. J., Vullings, R., & Aarts, R. M. (2015, September). Decreasing the false alarm rate of arrhythmias in intensive care using a machine learning approach. In 2015 Computing in Cardiology Conference (CinC) (pp. 293-296). IEEE.
Ester, M., Kriegel, H. P., Sander, J., & Xu, X. (1996, August). A density-based algorithm for discovering clusters in large spatial databases with noise. In kdd (Vol. 96, No. 34, pp. 226-231).
Fallet, S., Yazdani, S., & Vesin, J. M. (2015, September). A multimodal approach to reduce false arrhythmia alarms in the intensive care unit. In 2015 Computing in Cardiology Conference (CinC) (pp. 277-280). IEEE.
García, E. G., Gómez, F. G., Pion, M. G., & Alonso-Colmenares, M. G. (2015). Arritmias cardíacas en urgencias. Medicine-Programa de Formación Médica Continuada Acreditado, 11(87), 5175-5184.
Guyton, A.C. (2006). Tratado de fisiologia medica. Brasil: Elsevier
Jung, D. K., Kim, G. R., Kim, K. N., Choi, B. C., Suh, D. J., Jeon, G. R., & Ye, S. Y. (2007). Changes of pulse wave velocity in arm according to characteristic points of pulse wave. Paper presented at the 2007 International Conference on Convergence Information Technology (ICCIT 2007).
Kalidas, V. and Tamil, L. S. (2015). Enhancing accuracy of arrhythmia classification by combining logical and machine learning techniques. Paper presented at the 2015 Computing in Cardiology Conference (CinC).
Karlen, W., Raman, S., Ansermino, J. M., & Dumont, G. A. (2013). Multiparameter respiratory rate estimation from the photoplethysmogram. IEEE Transactions on Biomedical Engineering, 60(7), 1946-1953.
Paradkar, N., & Chowdhury, S. R. (2017). Cardiac arrhythmia detection using photoplethysmography. Paper presented at the 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).
Poh, M. Z., Poh, Y. C., Chan, P. H., Wong, C. K., Pun, L., Leung, W. W. C., ... & Siu, C. W. (2018). Diagnostic assessment of a deep learning system for detecting atrial fibrillation in pulse waveforms. Heart, 104(23), 1921-1928.
Polanía, L. F., Mestha, L. K., Huang, D. T., & Couderc, J. P. (2015). Method for classifying cardiac arrhythmias using photoplethysmography. Paper presented at the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).
Rezaei Yousefi, Z. (2018). Atrial Fibrillation Detection from Photoplethysmography Data Using Artificial Neural Networks. (Master), Tampere University of Tecnology.
Sadr, N., Huvanandana, J., Nguyen, D. T., Kalra, C., McEwan, A., & de Chazal, P. (2015, September). Reducing false arrhythmia alarms in the ICU by Hilbert QRS detection. In 2015 Computing in Cardiology Conference (CinC) (pp. 1173-1176). IEEE.
Saquib, N., Papon, M. T. I., Ahmad, I., & Rahman, A. (2015). Measurement of heart rate using photoplethysmography. In 2015 International Conference on Networking Systems and Security (NSysS) (pp. 1-6). IEEE.
Shashikumar, S. P., Shah, A. J., Li, Q., Clifford, G. D., & Nemati, S. (2017, February). A deep learning approach to monitoring and detecting atrial fibrillation using wearable technology. In 2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI) (pp. 141-144). IEEE.
Stankevi?ius, D., Petr?nas, A., Sološenko, A., Grigutis, M., Januškevi?ius, T., Rimševi?ius, L., & Marozas, V. (2016). Photoplethysmography-based system for atrial fibrillation detection during hemodialysis. In XIV Mediterranean Conference on Medical and Biological Engineering and Computing 2016 (pp. 79-82). Springer, Cham.
Vázquez Seisdedos, C.R. (2001). Análisis del ECG en monitorización ambulatoria para el diagnóstico cardíaco y la predicción de muerte cardíaca súbita. Universdtat Politécnica de Catalunya.
