Process mining analyses in intra-hospital patient transport
Process Mining is a young, analytical discipline for recognizing, monitoring and improving real business processes (i.e. processes that have not been adopted). It extracts knowledge from event logs available in today's information systems (software used to support them). In general, process mining can be understood as a bridge between data and process science (see van der Aalst, W.: Process Mining: Data Science in Action, 2016, p. 16).
Research project with real data in a German hospital
Designing healthcare facilities and processes is a complex task that affects the quality and efficiency of healthcare services. The ongoing demand for healthcare services and the associated costs necessitate the application of analytical methods to improve overall service efficiency in hospitals. However, variability in healthcare processes makes accomplishing this aim highly complicated.
The use case in a German hospital showed that process mining methods allow finding root causes for conformance issues and delays in the patient transport service process. This project addresses the complexity in the patient transport service process in a real-world setting, and proposes a method based on process mining to obtain a holistic approach to recognise bottlenecks and main reasons for delays and resulting high costs associated with idle resources. To this aim, the event log data from the patient transport software system is collected and processed to discover the sequences and the timeline of the activities for the different cases of the transport process.
In this case study a set of Key Performance Indicators is provided to measure the efficiency of intra-hospital patient transport services using process mining approaches. Furthermore, it conducts an extensive multidimensional analysis to support capacity planning by examining data containing various event- and case-specific information from the intra-hospital patient transport process for a period of 3.5 years beginning from January 2019 in a German hospital. Different perspectives are considered to enable multidimensional analysis and provide insights regarding the behavior of different elements involved in the transport process. Daily and hourly assignments are evaluated to investigate transport capacities, activity intervals, automatically and manually dispatched assignments, as well as the most significant routes concerning transport delays.
Process prediction approaches based on neural networks and metaheuristic optimization algorithms help to leverage the knowledge generated from process analyses into proactive process redesign measures.
Literature
Kropp, T.; Gao, Y.; Lennerts, K.
2024. OR Spectrum. doi:10.1007/s00291-024-00795-7
Kropp, T.; Faeghi, S.; Lennerts, K.
2024. Artificial Intelligence in Medicine – 22nd International Conference, AIME 2024, Salt Lake City, UT, USA, July 9–12, 2024, Proceedings, Part I. Ed.: J. Finkelstein, 138–150, Springer Nature Switzerland. doi:10.1007/978-3-031-66538-7_15
Kropp, T.; Faeghi, S.; Lennerts, K.
2022. The International Journal of Health Planning and Management, 38 (2), 430–456. doi:10.1002/hpm.3593
