Detecting fatigue is essential for ensuring safety in various sectors, especially in transportation and healthcare. The ECG Heartbeat Categorization Dataset available on Kaggle is used in this research to provide a comprehensive approach for fatigue detection using ECG signals. In order to detect signs of fatigue in real-time, our methodology uses both machine learning and deep learning frameworks to analyze distinct patterns in ECG signals. Additionally, the proposed system includes ECG heartbeat classification to broaden its application for detecting arrhythmias in real-time. With the dual-purpose system, proactive monitoring of patients for abnormal heart rhythms is now possible, allowing timely interventions and proactive management of cardiovascular health. Through experimental evaluation, it can be demonstrated that the proposed approach is effective in detecting fatigue and enabling proactive monitoring of cardiovascular health. By integrating wearable devices equipped with ECG sensors, our approach can be applied more effectively in real-world scenarios, which promises better safety and healthcare outcomes. The development of fatigue detection systems is aided by this research’s comprehensive solution that combines machine learning and deep learning techniques for improved accuracy and reliability.