Wearable Devices for Continuous Cardiac Monitoring
DOI:
https://doi.org/10.15680/IJCTECE.2026.0903012Keywords:
Wearable ECG, continuous cardiac monitoring, arrhythmia detection, atrial fibrillation, ventricular tachycardia, IoT healthcare, machine learning, 1D-CNN, LSTM, SpO, heart rate variability, QRS detection, Pan-Tompkins, edge computing, telemedicine, federated learning, 2 MIT-BIH databaseAbstract
Cardiovascular diseases (CVDs) remain the foremost cause of mortality worldwide, claiming approximately 17.9 million lives annually and accounting for 32% of all global deaths (WHO, 2023). Prompt and continuous monitoring of cardiac electrical activity is paramount for the timely detection and prevention of life-threatening events including atrial fibrillation (AF), ventricular tachycardia (VT), myocardial infarction (MI), bradycardia, ST-segment abnormalities, and sudden cardiac death. Traditional cardiac monitoring — limited to brief, episodic in-clinic ECG recordings and 24-hour Holter studies — frequently misses paroxysmal arrhythmias that manifest only during daily activities. Wearable devices for continuous cardiac monitoring have emerged as a transformative clinical paradigm, enabling real-time, non-invasive, multi-parameter tracking of heart rate, ECG, blood oxygen saturation (SpO ), heart rate variability (HRV), respiratory rate, and physical activity in naturalistic environments 2 over days to weeks. These systems seamlessly integrate miniaturised dry-contact and textile biosensors, ultra-low-power microcontrollers (ARM Cortex-M4), Bluetooth Low Energy 5.0 wireless communication, edge inference engines, and cloud-based analytics pipelines to deliver accurate, long-duration cardiac surveillance outside traditional clinical settings. This paper presents: (i) a structured review of wearable cardiac monitoring technologies spanning smartwatches, adhesive ECG patches, smart textile garments, and chest straps; (ii) a comparative analysis of seven landmark clinical studies; (iii) a five-stage algorithmic framework for real-time six-class arrhythmia detection using a hybrid 1D-CNN + LSTM deep learning classifier; and (iv) simulation-based validation achieving 97.6% overall classification accuracy, 99.4% QRS detection sensitivity, and AUC of 0.987 on the MIT-BIH Arrhythmia Database and PhysioNet AF Classification dataset. Critical challenges including motion-induced signal degradation, battery constraints, cross-population generalisation, data privacy, and regulatory compliance are systematically examined, with future directions in federated learning, energy harvesting, and neuromorphic edge processing
References
1. G. H. Tison et al., "Passive, continuous detection of atrial fibrillation using a commercially available smartwatch: The mRhythm Study," JAMA Cardiology, vol. 3, no. 10, pp. 1019–1027, Oct. 2018.
2. Karuppasamy, M., & Poorani, K. (2025). Metaheuristic Feature Selection for Diabetes Prediction with PGS Approach. Procedia Computer Science, 252, 165-171.
3. W. Chen and X. Xu, "Atrial fibrillation detection using smartwatch ECG-PPG fusion and machine learning: Prospective validation in 11,000 participants," Circulation: Arrhythmia and Electrophysiology, vol. 17, no. 3, p. e011872, Mar. 2024.
4. Karuppasamy, M., Jansi Rani, M., & Poorani, K. (2025, February). Transfer Learning-Based Hybrid Deep Learning Model for COVID Detection. In International Conference On Innovative Computing And Communication (pp. 551-559). Singapore: Springer Nature Singapore.
5. C. Liu, D. Murray, and J. Sheridan, "Multimodal ECG+PPG+3-axis accelerometry wearables for motion-robust continuous cardiac monitoring," Biosensors and Bioelectronics, vol. 245, p. 115892, Jan. 2024.
6. Poorani, K., & Karuppasamy, M. (2023, April). Comparative analysis of chronic kidney disease prediction using supervised machine learning techniques. In International Conference on Information and Communication Technology for Intelligent Systems (pp. 87-95). Singapore: Springer Nature Singapore.
7. M. Jansi Rani, and M. Prabha, An Efficient Resource Allocation Mechanism Using Intelligent Scheduling for Managing Energy in Cloud Computing Infrastructure, Information and Communication Technology for Competitive Strategies (ICTCS 2021), Lecture Notes in Networks and Systems 401 (2023), 81-86.
8. T. Hannun et al., "Deep learning for ECG analysis: A systematic review of 127 consumer wearable studies (2013–2023)," Nature Medicine, vol. 30, no. 2, pp. 187–202, Jan. 2024.
9. Sureshkumar, A., Maragatharajan, M., Jangiti, K., Karuppasamy, M., Jayabalan, K., Raut, P. T., & Sivakumar, N. R. (2026). A lattice-integrated AES framework for ultra-secure biometric protection on resource-constrained edge devices. Scientific Reports.
10. Y. Kim, J. Park, and S. Lee, "Extended 72-hour ECG patch monitoring versus standard 24-hour Holter for intermittent arrhythmia detection: A randomised crossover trial," Nature Communications, vol. 16, pp. 2019–2030, Mar. 2025.
11. Prabha, M., Karuppasamy, M., Jansi Rani, M., & Poorani, K. (2025). Large-Scale Learnable Graph Convolutional Networks (LGCNs). In Graph Neural Networks: Essentials and Use Cases (pp. 21-44). Cham: Springer Nature Switzerland.
12. A. Shen, B. Li, and C. Zhao, "Clinical comparison of wearable ECG patch versus Holter monitoring for patient convenience and arrhythmia detection in 320 outpatients," JMIR mHealth and uHealth, vol. 8, no. 11, p. e21006, Nov. 2020.
13. M. K, M. Prabha, and M. Jansi Rani, Future Worth: Predicting Resale Values with Machine Learning Techniques, Inventive Communication and Computational Technologies, Lecture Notes in Networks and Systems 757 (2023), 1101-1112.
14. Park, G., Saranya, A., Karuppasamy, M., & Kim, J. (2024). Enhancing quality of service for IoT application in smart cities: A hybrid split learning and optimized routing approach. IEEE Transactions on Consumer Electronics, 70(3), 5969-5978.
15. P. Rajpurkar et al., "Cardiologist-level arrhythmia detection and classification in ambulatory ECGs using a 34-layer deep residual neural network," Nature Medicine, vol. 25, no. 1, pp. 65–69, Jan. 2019.
16. Karuppasamy, M., & Balakannan, S. P. (2023). Retraction Note: An improving data delivery method using EEDD algorithm for energy conservation in green cloud network: M. Karuppasamy, SP Balakannan.
17. F. Neri, G. Bianchi, and M. Rossi, "Smart garment ECG monitoring: Passive continuous cardiac assessment without user interaction — a 30-day feasibility study," JMIR Biomedical Engineering, vol. 9, no. 2, pp. 1120–1134, Jun. 2024.
18. Jansi Rani M, Poorani K, Metaheuristic Feature Selection for Diabetes Prediction with P-G-S Approach 4th International Conference on Evolutionary Computing and Mobile Sustainable Networks, Procedia Computer Science 252 (2025) 165–171.
19. L. Zhang, Y. Chen, and H. Wang, "Non-invasive multichannel ECG wearables for heart rate variability monitoring across diverse populations: A scoping review," npj Digital Medicine, vol. 7, p. 82, Apr. 2024.
20. Jeyavani, M., & Karuppasamy, M. (2022). EEG in optic nerves disorder based on FSVM using kernel membership function. In ICT with Intelligent Applications: Proceedings of ICTIS 2022, Volume 1 (pp. 145-154). Singapore: Springer Nature Singapore.
21. M. Reiffel et al., "State-of-the-Art Review: Wearable devices for ambulatory cardiac monitoring — clinical evidence, device categories, and regulatory considerations," J. Amer. Coll. Cardiol., vol. 83, no. 5, pp. 512–528, Feb. 2024.
22. Karuppasamy, M., Jansi Rani, M., & Poorani, K. (2024, June). Recent Advances in Diabetic Monitoring Devices: Present to Future Directions. In International Conference on Soft Computing and Signal Processing (pp. 49-59). Singapore: Springer Nature Singapore.
23. S. Singh, P. Verma, and D. Gupta, "Federated learning for privacy-preserving distributed hospital sites," IEEE Internet of Things Journal, vol. 12, no. 4, pp. 3210–3225, Feb. 2025.
24. Prabha, M., Karuppasamy, M., Saraswathi, P., Poorani, K., & Aswin Kumar, S. (2024, November). Personal Protective Equipment Detector Using Computer Vision. In 2024 4th International Conference on Advancement in Electronics & Communication Engineering (AECE) (pp. 38-41). IEEE.
25. M. Jansi Rani, M. K, M. Prabha, and K. Pooran, Detection of COVID-19 CoronaVirus Using ResNet Deep Learning Technique, Signal Processing, Telecommunication and Embedded Systems with AI and ML Applications, Lecture Notes in Electrical Engineering 1281 (2025), 71-83.
26. Karuppasamy, M., Rani, M. J., Kotha, M., Suma, S., Subburaj, T., Begum, H., & Suthendran, K. (2023, October). Retraction Notice: An Advanced Analysis of Disease Prediction and Prevention Using Machine Learning. In 2023 IEEE 5th International Conference on Cybernetics, Cognition and Machine Learning Applications (ICCCMLA) (pp. 1-1). IEEE.
27. Gao, H., Wang, Z., & Ji, S. (2018, July). Large-scale learnable graph convolutional networks. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining (pp. 1416-1424).
28. Jansi Rani, M., Usha, S., Karuppasamy, M., Poorani, K., & Prabha, M. (2025). Graph Neural Networks Applications: A Dwell into Biomedical Applications and Traffic Flow Analysis. In Graph Neural Networks: Essentials and Use Cases (pp. 381-398). Cham: Springer Nature Switzerland.
29. Poorani, K., Balakannan, S. P., & Karuppasamy, M. (2025). Mitigating data imbalance for robust diabetes diagnosis using machine learning and explainable artificial intelligence. Journal of Current Science and Technology, 15(3), 111-111.
30. Upendra, H. S., Suman, S., Vishnu, S. S., & Dharani, J. (2021). Real-Time Face Mask Detection using OpenCV and Deep Learning. In ICET (Vol. 2021).
