This paper presents a novel machine learning framework for detecting Paroxysmal Atrial Fib-rillation (PxAF), a pathological characteristic of Electrocardiogram (ECG) that can lead to fatalconditions such as heart attack. To enhance the learning process, the framework involves a Gen-erative Adversarial Network (GAN) along with a Neural Architecture Search (NAS) in the datapreparation and classifier optimization phases. The GAN is innovatively invoked to overcome theclass imbalance of the training data by producing the synthetic ECG for PxAF class in a certifiedmanner. The effect of the certified GAN is statistically validated. Instead of using a general-purposeclassifier, the NAS automatically designs a highly accurate convolutional neural network architecture customized for the PxAF classification task. Experimental results show that the accuracy of theproposed framework exhibits a high value of 99% which not only enhances state-of-the-art by up to5.1%, but also improves the classification performance of the two widely-accepted baseline methods,ResNet-18, and Auto-Sklearn, by 2.2% and 6.1%