Early Heart Attack Detection Using Real-Time ECG Signals: A Systematic Survey

Heart attacks remain one of the leading global health threats, making early detection a critical step in saving lives. Wearable devices, like smartwatches, are now playing a transformative role by offering real-time ECG monitoring and providing continuous tracking of heart activity. This allows individuals and healthcare providers to detect early warning signs, such as irregular heartbeats or abnormal ECG patterns, before they develop into serious emergencies. This survey explores the integration of real-time ECG monitoring into everyday devices, focusing on its growing importance in early heart attack detection. It reviews commonly used algorithms, such as convolutional neural networks and long short-term memory, as well as algorithms like support vector machines, random forests, and k-nearest neighbor networks. These algorithms analyze ECG data to detect cardiac anomalies with precision. The paper also discusses the benefits of early detection, challenges such as algorithm accuracy and device battery life, and the potential for future improvements in both wearable technology and machine learning models. These advancements could further enhance the reliability and accessibility of heart monitoring, leading to better outcomes for patients worldwide.