Cardiovascular diseases are among the leading causes of death across the world. Early detection of heart abnormalities such as arrhythmia can significantly reduce the risk of severe complications and improve patient survival rates. Arrhythmia refers to irregular heartbeats that may be too fast, too slow, or irregular. Continuous monitoring of heart signals can help identify such abnormalities at an early stage. This project proposes a wearable Internet of Things-based system for real-time arrhythmia detection and cardiac risk prediction using machine learning techniques. The system uses wearable sensors to continuously collect electrocardiogram signals and other physiological parameters from the user. These signals are transmitted through IoT communication technologies to a processing platform where machine learning algorithms analyze the data. The proposed system aims to detect abnormal heart rhythms in real time and alert patients or healthcare providers immediately. By integrating wearable devices, IoT communication, and machine learning analysis, the system supports remote healthcare monitoring and early diagnosis. This technology can improve patient safety, reduce hospital visits, and support preventive healthcare solutions.