Cardiovascular diseases (CVDs) are the major cause of mortality globally. The early diagnosis and treatment of CVDs are crucial to saving lives. Electrocardiography (ECG), a non-invasive method, is employed to record the heart’s electrical activity. ECG classification plays a pivotal role in diagnosing CVDs and monitoring treatment progress. However, the current ECG classification systems are often energy-intensive, costly, and lack accuracy. This paper introduces a novel ECG classification system that leverages Adaptive Spiking Neural Networks (ASD SNNs) implemented on a Field-Programmable Gate Array (FPGA). Compared to existing systems, ASD SNNs are more energy-efficient, cost-effective, and accurate. The proposed system holds the capability to transform ECG monitoring and improve the quality of life for individuals with CVDs.