 Graph Machine Learning, GML, has become increasingly popular in recent years due to its ability to process complex data structures such as graphs. In particular, it has been widely used in the health informatics domain for disease prediction. This paper reviews the current state of GML in the health informatics domain by examining the literature on node classification and link prediction. The authors found that GML has been successfully applied to various disease prediction tasks, including diabetes, cancer, and heart disease. However, there remain several challenges associated with GML, such as interpretability and dynamic graph issues. Despite these limitations, GML has shown promise in the health informatics domain and holds great potential for further development. This article was authored by Hauhui Lu and Shahadaruddin.