Integrating Portable Ecg Devices With Cloud Systems for Cardiac Arrhythmia Detection

This article presents a real-time, cloud-integrated cardiac monitoring system developed using a portable ECG device that communicates via HTTPS and REST API protocols. The raw ECG signals are transmitted in JSON format to a secure cloud server, where Symlet4 wavelet transform is employed to denoise the signals in real time. This process enables the accurate extraction of key cardiac features, including HRV, QRS complex, RR interval, QT interval, PR interval, ST segment, P wave, and T wave. These features are processed and stored for subsequent analysis. Arrhythmia classification is initially performed using rule-based clinical logic derived from these parameters, while a structured dataset is concurrently generated to support the development and training of machine learning models for future diagnostic applications. Additionally, HRV data is visualized in real time through a responsive frontend interface, facilitating remote cardiac health monitoring by healthcare professionals. The system was validated using ECG recordings from 98 patients of varying ages to assess performance, reliability, and scalability across diverse clinical and home care scenarios. This article highlights a novel implementation of wavelet-based ECG signal filtering integrated with cloud computing within a complete IoT-based healthcare architecture.