Objective: Fuzzy clustering algorithm is a partition method used to assign objects from a data set to a cluster by marking the average location. Furthermore, Fuzzy Subtractive Clustering (FSC) with hamming distance and exponential membership function is used to analyze the cluster center of a data point. Therefore, the purpose of this research is to determine the number of clusters with the best quality by comparing the Partition Coefficient (PC) values for each number produced. Methods: The data set which is heart failure patient data is 150 data obtained from UCI Machine Learning. The data consists of 11 variables, including age , anemia , creatinine phosphokinase , diabetes ejection fraction , high blood pressure , platelets , serum creatinine , serum sodium , gender , and smoke . It simulated and processed using Fuzzy Subtractive Clustering Algorithm, Jupyter Notebook Software with Python programming language. Result: The results showed that the most optimal number of clusters is 3, which are selected based on the largest PC value. Conclusion: Based on the results obtained, the highest P value is in cluster 3, therefore heart failure can be grouped into 3, namely low, moderate, severe.