With the increase of data in the medical domain over the years, it is extremely crucial that we analyze useful information and recognize patterns that can be used by the clinicians for better diagnosis of diseases. Clustering is a Machine Learning technique that can be used to categorize data into compact and dissimilar clusters to gain some meaningful insight. This paper uses partition and hierarchical based clustering techniques to cluster neonatal data into different clusters and identify the role of each cluster. Clustering discovers hidden knowledge which helps neonatologists in identifying neonates who are at risk and also helps in neonatal diagnosis. In addition, this paper also evaluates the number of clusters to be formed for the techniques using Silhouette Coefficient.