A Graph Database Approach for Temporal Modeling of Disease Progression

The high cost of managing chronic diseases for individuals and governments, as well as the negative impact on the quality of life, highlights the importance of controlling and preventing the chronic disease progression. Understanding the disease progression model is one of the first steps, which can lead to more effective planning for interventions. Most of the different approaches for statistical modeling of disease progression work with the graph. On the other hand longitudinal medical data could be represented in the form of a graph and modeling them in this way has a great deal of potential for analyzing and tracking medical event. Data structures, data model features, query facilities and special commands in graph database for traversing and detection patterns could be useful for building summarized information based on transitions between different stages of a particular disease in individual graphs. Given the fact that clinical data is collected at different times, software and formats, there is a need for a flexible framework for data linkage. Use of graph databases brings this flexibility into account and provide a highly scalable framework for data integrating and linkage. In this study, at first simple medical observations related to patients with varying degrees of Alzheimer's disease stored in a graph database (Neo4j) and then by reviewing the capabilities of this environment in building transition graph of different stages of the disease, suggestions for the model development with more details were presented.