Declarative process mining in healthcare

Clinical guidelines aim at improving the quality of care processes through evidence-based insights. However, there may be good reasons to deviate from such guidelines or the guidelines may provide insufficient support as they are not tailored toward a particular setting (e.g., hospital policy or patient group characteristics). Therefore, we report a case study that shows how process mining techniques can be used to mediate between event data reflecting the clinical reality and clinical guidelines describing best-practices in medicine. Declarative models are used as they allow for more flexibility and are more suitable for describing healthcare processes that are highly unpredictable and unstable. Concretely, initial (hand made) models based on clinical guidelines are improved based on actual process executions (if these executions are proven to be correct). Process mining techniques can be also used to check conformance, analyze deviations, and enrich models with conformance-related diagnostics. The techniques have been applied in the urology department of the Isala hospital in the Netherlands. The results demonstrate that the techniques are feasible and that our toolset based on ProM and Declare is indeed able to provide valuable insights related to process conformance.