A Knowledge Graph Approach for the Secondary Use of Cancer Registry Data

Population-based central cancer registries collect valuable structured and unstructured cancer data primarily for surveillance and reporting. The collected data includes (1) categorization of each cancer case (tumor) at the time of diagnosis, (2) demographic information about the patient such as age, gender, and location at time of diagnosis, (3) first course of treatment information, and (4) survival outcomes when available. While advanced analytical approaches such as SEER*Stat and SAS exist, we provide a knowledge graph approach to organizing cancer registry data for advanced analytics which offers unique advantages over existing approaches. This knowledge graph approach semantically enriches the data and enables straightforward linking capability with third-party data to help understand variation in cancer outcomes. A knowledge graph was developed using Louisiana Tumor Registry data. We present the advantages of the knowledge graph approach by examining: i) scenario-specific queries and ii) linkages with publicly available external datasets. Our results demonstrate this graph based solution can perform complex queries, improve query run-time performance by 81%, and more easily conduct iterative analyses to enhance researchers understanding of cancer registry data.