Extending a Data Management Maturity Model for Process Mining in Healthcare.

BACKGROUND: Many components must work together to continuously improve processes in healthcare organizations. Process mining has recently developed into a discipline that can make a significant contribution here. OBJECTIVES: We want to extend an existing management tool to assess and improve the capability of organizations in this area. METHOD: We add a dimension to the adoption readiness assessment and maturity model for sharable clinical pathways to assess and improve event data quality. RESULTS: We present different approaches for formal and checkpoint assessments and an embedding of the improvement strategy with examples. CONCLUSION: The additional dimension from the process mining domain integrates with the existing model. At all levels, links can be established between the various aspects of event data quality with existing dimensions. The model has yet to be tested in a real-world use case.

FHIR2BPMN: Delivering Actionable Knowledge by Transforming Between Clinical Pathways and Executable Models.

Healthcare processes have many particularities captured and described within standards for medical information exchange such as HL7 FHIR. BPMN is a widely used standard to create readily understandable processes models. We show an approach to integrate both these standards via an automated transformation mechanism. This will allow us to use the various tools available for BPMN to visualize and automate processes in the healthcare domain. In the future we plan to extend this approach to enable mining and analyzing executed processes.

Data Quality- and Master Data Management - A Hospital Case.

Poor data quality prevents the analysis of data for decisions which are critical for business. It also has a negative impact on business processes. Nevertheless the maturity level of data quality- and master data management is still insufficient in many organizations nowadays. This article discusses the corresponding maturity of companies and a management cycle integrating data quality- and master data management in a case dealing with benchmarking in hospitals. In conclusion if data quality and master data are not properly managed, structured data should not be acquired in the first place due to the added expense and complexity.

Supporting knowledge discovery in medicine.

Our ontology-based benchmarking infrastructure for hospitals, we presented on the eHealth 2012, has meanwhile proven useful. Besides, we gathered manifold experience in supporting knowledge discovery in medicine. This also led to further functions and plans with our software. We could confirm and extent our experience by a literature review on the knowledge discovery process in medicine, visual analytics and data mining and drafted an according approach for extending our software. We validated our approach by exemplarily implementing a parallel-coordinate data visualization into our software and plan to integrate further algorithms for visual analytics and machine learning to support knowledge discovery in medicine in diverse ways. This is very promising but can also fail due to technical or organizational details.