AbstractThe medical practitioners analyze the electrical activity of the human heart so as to predict various ailments by studying the data collected from the Electrocardiogram (ECG). A Bundle Branch Block (BBB) is a type of heart disease which occurs when there is an obstruction along the pathway of an electrical impulse. This abnormality makes the heart beat irregular as there is an obstruction in the branches of heart, this results in pulses to travel slower than the usual. Our current study involved is to diagnose this heart problem using Adaptive Bacterial Foraging Optimization (ABFO) Algorithm. The Data collected from MIT/BIH arrhythmia BBB database applied to an ABFO Algorithm for obtaining best(important) feature from each ECG beat. These features later fed to Levenberg Marquardt Neural Network (LMNN) based classifier. The results show the proposed classification using ABFO is better than some recent algorithms reported in the literature.