This paper describes the rough set classifier for cardiac disease classification over the medical dataset obtained from characteristics feature of ECG signals. The sets of characterizes feature are used as an information system to find minimal decision rules that may be used to identify one or more diagnostic classes. After gathering knowledge from various medical books as well as feedback from well-known cardiologists, a knowledge base has been developed. The rough set-based degree of attributes dependency technique and their significance predicted the universal least decision rules. Such rule has the least number of attributes so that their combination defines the largest subset of a universal decision class. Hence, the minimal rule of an information system is adequate for predicting probable complications. Lastly, the performance parameters such as accuracy and sensitivity have been expressed in the form of confusion matrix by ROSETTA software which yields information about actual and predicted classification achieved by the proposed system. © Springer Nature Singapore Pte Ltd. 2019.