Using large administrative data for mining patients’ trajectories for risk stratification: An example from urological diseases

A novel statistical approach to cluster hospitalisation trajectories for urological patients was used to explore potential clusters of patient risks and their associations with outcome quality indicators. This study supports the observation that baseline comorbidities and diagnosis can be predictive of higher hospitalisation rates and, therefore, poorer health outcomes. This demonstrates that it is possible to identify patients at risk of developing complications, higher length of stay and readmissions by using baseline comorbidities and diagnosis from administrative data.