Detection of Arrhythmias Using Heart Rate Signals from Smartwatches
Source abstract
Abstract
According to the World Health Organization (WHO), cardiovascular illnesses, including arrhythmia, are the primary cause of mortality globally, responsible for over 31% of all fatalities each year. To reduce mortality, early and precise diagnosis is essential. Although the analysis of electrocardiograms (ECGs) is the primary means of detecting arrhythmias, it depends significantly on the expertise and subjectivity of the health professional reading and interpreting the ECG, and errors may occur in detection. Artificial intelligence provides tools, techniques, and models that can support health professionals in detecting arrhythmias. However, these tools are based only on ECG data, of which the process of obtaining is an invasive, high-cost method requiring specialized equipment and personnel. Smartwatches feature sensors that can record real-time signals indicating the heart’s behavior, such as ECG signals and heart rate. Using this approach, we propose a machine learning- and deep learning-based approach for detecting arrhythmias using heart rate data obtained with smartwatches. Heart rate data were collected from 252 patients with and without arrhythmias who attended a clinic in Arequipa, Peru. Heart rates were also collected from 25 patients who wore smartwatches. Ten machine learning algorithms were implemented to generate the most effective arrhythmia recognition model, with the decision tree algorithm being the most suitable. The results were analyzed using accuracy, sensitivity, and specificity metrics. Using Holter data yielded values of 93.2%, 91.89%, and 94.59%, respectively. Using smartwatch data yielded values of 70.83%, 91.67%, and 50%, respectively. These results indicate that our model can effectively recognize arrhythmias from heart rate data. The high sensitivity score suggests that our model adequately recognizes true positives; that is, patients with arrhythmia. Likewise, its specificity suggests an adequate recognition of false positives.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Non-Invasive Vital Sign Monitoring · ECG Monitoring and Analysis · EEG and Brain-Computer Interfaces
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Academic Department of Engineering and Information Technology, Professional School of Systems Engineering, Faculty of Engineering, Jose Maria Arguedas National University, Andahuaylas 03701, Peru
Vicerrectorado de Investigación, Universidad Católica de Santa María, Arequipa 04013, Peru
Agile Corporation, Arequipa 04013, Peru
Professional School of Systems Engineering, San Agustín of Arequipa National University, Arequipa 04013, Peru
Armonía Research Group, Hanami Psychosocial Care and Research Center, Bogotá 11001, Colombia
Funding
PROCIENCIA—CONCYTEC, Peru
References (49)
Show source-provided references
1. Machine learning of clinical variables and coronary artery calcium scoring for the prediction of obstructive coronary artery disease on coronary computed tomography angiography: Analysis from the CONFIRM registry10.1093/eurheartj/ehz565 ↗
2. Arrhythmias beyond atrial fibrillation detection using smartwatches: A systematic review10.14744/AnatolJCardiol.2023.2799 ↗
3. Tiernay, L., Papadakis, M., and Mcphee, S. (2012). Current Medical Diagnosis & Treatment, McGrawHill.
4. Detecting SARS-CoV-2 from chest X-Ray using artificial intelligence10.1109/ACCESS.2021.3061621 ↗
5. Overdiagnosis: How our compulsion for diagnosis may be harming children10.1542/peds.2014-1778 ↗
6. Computerized epileptiform transient detection in the scalp electroencephalogram: Obstacles to progress and the example of computerized ECG interpretation10.1016/j.clinph.2009.08.007 ↗
7. Ansari, Y., Mourad, O., Qaraqe, K., and Serpedin, E. (2023). Deep learning for ECG Arrhythmia detection and classification: An overview of progress for period 2017–2023. Front. Physiol., 14.10.3389/fphys.2023.1246746 ↗
8. Arrhythmia detection and classification using ECG and PPG techniques: A review10.1007/s13246-021-01072-5 ↗
9. Shan, S.M., Tang, S.C., Huang, P.W., Lin, Y.M., Huang, W.H., Lai, D.M., and Wu, A.Y.A. (2016, January 17–19). Reliable PPG-based algorithm in atrial fibrillation detection. Proceedings of the 2016 IEEE Biomedical Circuits and Systems Conference (BioCAS), Shanghai, China.10.1109/BioCAS.2016.7833801 ↗
10. Schäck, T., Harb, Y.S., Muma, M., and Zoubir, A.M. (2017, January 11–15). Computationally efficient algorithm for photoplethysmography-based atrial fibrillation detection using smartphones. Proceedings of the 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jeju Island, Republic of Korea.10.1109/EMBC.2017.8036773 ↗
11. Kanawade, R., Tewary, S., and Sardana, H. (2019, January 7–8). Photoplethysmography based arrhythmia detection and classification. Proceedings of the 2019 6th International Conference on Signal Processing and Integrated Networks (SPIN), Noida, India.
12. Sardana, H.K., Kanawade, R., and Dogra, N. (2023). Photoplethysmograph based arrhythmia detection using morphological features. Biomed. Signal Process. Control, 81.10.1016/j.bspc.2022.104422 ↗
13. Detecting atrial fibrillation and atrial flutter in daily life using photoplethysmography data
14. Han, D., Bashar, S.K., Zieneddin, F., Ding, E., Whitcomb, C., McManus, D.D., and Chon, K.H. (2020, January 20–24). Digital image processing features of smartwatch photoplethysmography for cardiac arrhythmia detection. Proceedings of the 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, QC, Canada.10.1109/EMBC44109.2020.9176142 ↗
15. Can one detect atrial fibrillation using a wrist-type photoplethysmographic device?10.1007/s11517-018-1886-0 ↗
16. Solosenko, A., and Marozas, V. (2014, January 22–24). Automatic premature ventricular contraction detection in photoplethysmographic signals. Proceedings of the 2014 IEEE Biomedical Circuits and Systems Conference (BioCAS) Proceedings, Lausanne, Switzerland.10.1109/BioCAS.2014.6981642 ↗
17. Photoplethysmography-based method for automatic detection of premature ventricular contractions10.1109/TBCAS.2015.2477437 ↗
18. Dynamic time warping based arrhythmia detection using photoplethysmography signals10.1007/s11760-022-02152-z ↗
19. Wang, J., Qiao, X., Liu, C., Wang, X., Liu, Y., Yao, L., and Zhang, H. (2021). Automated ECG classification using a non-local convolutional block attention module. Comput. Methods Programs Biomed., 203.10.1016/j.cmpb.2021.106006 ↗
20. Ji, C., Wang, L., Qin, J., Liu, L., Han, Y., and Wang, Z. (2024). MSGformer: A multi-scale grid transformer network for 12-lead ECG arrhythmia detection. Biomed. Signal Process. Control, 87.10.1016/j.bspc.2023.105499 ↗
21. Advances in diagnosis, therapy, and prognosis of coronary artery disease powered by deep learning algorithms10.1016/j.jacasi.2022.12.005 ↗
22. Chen, C., Hua, Z., Zhang, R., Liu, G., and Wen, W. (2020). Automated arrhythmia classification based on a combination network of CNN and LSTM. Biomed. Signal Process. Control, 57.10.1016/j.bspc.2019.101819 ↗
23. Electrocardiogram soft computing using hybrid deep learning CNN-ELM10.1016/j.asoc.2019.105778 ↗
24. A multitier deep learning model for arrhythmia detection10.1109/TIM.2020.3033072 ↗
25. Automatic cardiac arrhythmia classification using residual network combined with long short-term memory
26. Deep learning models for arrhythmia detection in IoT healthcare applications10.1016/j.compeleceng.2022.108011 ↗
27. Islam, M.R., Kabir, M.M., Mridha, M.F., Alfarhood, S., Safran, M., and Che, D. (2023). Deep learning-based IoT system for remote monitoring and early detection of health issues in real-time. Sensors, 23.10.3390/s23115204 ↗
28. Mousavi, S., and Afghah, F. (2019, January 12–17). Inter-and intra-patient ecg heartbeat classification for arrhythmia detection: A sequence to sequence deep learning approach. Proceedings of the ICASSP 2019–2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.10.1109/ICASSP.2019.8683140 ↗
29. The role of contemporary wearable and handheld devices in the diagnosis and management of cardiac arrhythmias10.1016/j.hlc.2022.08.001 ↗
30. Intelligent health management based on analysis of big data collected by wearable smart watch10.1016/j.cogr.2022.12.003 ↗
31. At the crossroads! Time to start taking smartwatches seriously10.1016/j.amjcard.2022.06.020 ↗
32. Accuracy of a smartwatch-derived ECG for diagnosing bradyarrhythmias, tachyarrhythmias, and cardiac ischemia10.1161/CIRCEP.120.009260 ↗
33. The impact of the MIT-BIH arrhythmia database10.1109/51.932724 ↗
34. Automated detection and classification of arrhythmia from ECG signals using feature-induced long short-term memory network10.1109/LSENS.2020.3006756 ↗
35. Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network10.1016/j.ins.2017.04.012 ↗
36. Akan, T., Alp, S., and Bhuiyan, M.A.N. (2024). ECGformer: Leveraging transformer for ECG heartbeat arrhythmia classification. arXiv.10.1109/CSCI62032.2023.00231 ↗
37. Chau, K.Y., Lam, M.H.S., Cheung, M.L., Tso, E.K.H., Flint, S.W., Broom, D.R., Tse, G., and Lee, K.Y. (2019). Smart technology for healthcare: Exploring the antecedents of adoption intention of healthcare wearable technology. Health Psychol. Res., 7.10.4081/hpr.2019.8099 ↗
38. Rationale and design of a large-scale, app-based study to identify cardiac arrhythmias using a smartwatch: The Apple Heart Study10.1016/j.ahj.2018.09.002 ↗
39. Bogár, B., Pető, D., Sipos, D., Füredi, G., Keszthelyi, A., Betlehem, J., and Pandur, A.A. (2024). Detection of Arrhythmias Using Smartwatches—A Systematic Literature Review. Healthcare, 12.10.3390/healthcare12090892 ↗
40. Neri, L., Oberdier, M.T., van Abeelen, K.C., Menghini, L., Tumarkin, E., Tripathi, H., Jaipalli, S., Orro, A., Paolocci, N., and Gallelli, I. (2023). Electrocardiogram monitoring wearable devices and artificial-intelligence-enabled diagnostic capabilities: A review. Sensors, 23.10.3390/s23104805 ↗
41. Beyond the wrist: Using a smartwatch electrocardiogram to detect electrocardiographic abnormalities10.1016/j.acvd.2021.11.003 ↗
42. Feasibility and diagnostic value of recording Smartwatch electrocardiograms in neonates and children10.1016/j.jpeds.2022.09.010 ↗
43. Abu-Alrub, S., Strik, M., Ramirez, F.D., Moussaoui, N., Racine, H.P., Marchand, H., Buliard, S., Haïssaguerre, M., Ploux, S., and Bordachar, P. (2022). Smartwatch electrocardiograms for automated and manual diagnosis of atrial fibrillation: A comparative analysis of three models. Front. Cardiovasc. Med., 9.10.3389/fcvm.2022.836375 ↗
44. Role of coexisting ECG anomalies in the accuracy of smartwatch ECG detection of atrial fibrillation10.1016/j.cjca.2022.08.222 ↗
45. Accuracy of a smartwatch based single-lead electrocardiogram device in detection of atrial fibrillation10.1136/heartjnl-2019-316004 ↗
46. Ramezani, R., Cao, M., Earthperson, A., and Naeim, A. (2023). Developing a smartwatch-based healthcare application: Notes to consider. Sensors, 23.10.3390/s23156652 ↗
47. Machine learning: Algorithms, real-world applications and research directions10.1007/s42979-021-00592-x ↗
48. Ray, S. (2019, January 14–16). A quick review of machine learning algorithms. Proceedings of the 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon), Faridabad, India.10.1109/COMITCon.2019.8862451 ↗
49. Huillcen, H. (2024, June 20). Detection of Arrhythmias Using Heart Rate Signals from Smartwatches—Implementation. Available online: https://zenodo.org/records/12817732.