Catheter ablation has become a very efficient strategy to terminate sustained cardiac arrhythmias like atrial flutter (AFlut). Identification of the optimal ablation spot, however, often proves difficult when scar from previous ablations is present. Although the application of electro-anatomical mapping systems allows to record thousands of intracardiac electrograms (EGMs) from each atrium, state-of-the-art techniques provide limited options for automatic signal processing. Goal of the presented research was the development of an algorithm to detect EGMs that present double potentials (DPs), as these often indicate functional or anatomical lines of block for cardiac excitation. Using an annotated database, we developed several features based on the morphological descriptors of DPs. These were used to train a binary decision tree which was able to detect DPs with a correct rate of over 90%.