Machine Learning-Based Cardiac Fibrillation Diagnosis with ESP8266

Cardiac arrhythmias, particularly atrial fibrillation, represent a significant health risk, leading to increased mortality and morbidity rates worldwide. Early detection and timely intervention are critical to improving patient outcomes. This paper describes a real-time cardiac arrhythmia detection system that utilizes the AD8232 sensor for electrocardiogram (ECG) signal acquisition. The collected data is processed and analyzed through an artificial intelligence model deployed on Google Colab to predict the occurrence of arrhythmias. The system offers high diagnostic accuracy, with prediction results delivered to the user within one minute via applications such as Twilio, Viber, and WhatsApp. This approach enhances preventive healthcare by providing quick and accurate diagnostics, empowering users to take immediate action. The proposed system contributes to the advancement of accessible, low-cost, and efficient arrhythmia monitoring, offering a valuable tool for improving cardiovascular health.