Atrial fibrillation (AF) is the most common form of abnormal heart rhythm. At present, 25% of the world’s population aged 40 and above will experience AF in their lifetime. AF leads to a multi-fold increased risk of heart failure and stroke. This makes it a primary cause of hospitalisation, with treatment for AF being five times more costly than that of non-AF cardiac diseases. Therefore, AF occupies a large proportion of the total cost of heart disease treatment worldwide. Electrocardiograms provide a non-invasive approach for clinical diagnosis and monitoring treatment in patients with potential cardiac diseases. Remote monitoring and prognosis will play an increasingly important role in current and future clinical environments, particularly after the influence of the COVID-19 pandemic. Additionally, it is more efficient and cost-effective. We aim to develop a robust automatic software for detecting AF and other arrhythmias and recreate standard Holter reports for clinical use.