According to the characteristics of ECG analysis, large data quantum, high accuracy demand and real-time, a classified algorithm of arrhythmia based on clustering analysis is presented in this paper. According to "things-of-one-kind-come-together" principle, this algorithm uses the similarities of cases with same kind of heart disease at the same time, includes the factors of the individual difference to analyze arrhythmias by clustering QRS complex waveform and rhythm analysis as the subordinate method. Verified by eight records of MIT-BIR standard heart electricity database, the probability of correct clustering reaches above 90%, which shows that this algorithm can analyze arrhythmias effectively.