Bridging Data Complexity with GATNet for Learning in Interconnected Electronic Medical Records Graphs

Heterogeneous graphs are a data format for graphs that could define complicated and diverse real-world interactions by accommodating distinct sorts of nodes and edge types.Heterogeneous graphs organize varied medical data to help patients, therapies, drugs, and healthcare practitioners make informed decisions.Medical recommendation systems use them to represent and analyze complicated connections between healthcare data items.Heterogeneous graphs can potentially be constructed and analyzed using the Graph Attention Network (GAT).The purpose of this research is to tackle the issue of implementing a complicated and extremely diverse dataset, which consists of: Using the GATNet (Graph Attention Network) method, we will show how to perform two things: (1) Construct a model with several attributes and relationships using EMR (electronic medical record), and (2) Use that model in a disease prognostic prediction challenge.The initial graph database utilizes a graphical depiction of a patient's progression, showcasing a query of a predictive network that produces analytical findings of AUROC-0.75 and AUPRC-0.17 which is 0.03% & 0.02% higher compared to the existing models.