Joint Master Thesis RWTH PADS / University of Pisa Comparative Process Mining in Healthcare
Healthcare is a dynamic field, in which a large variety of healthcare professionals cooperates in order to facilitate a high quality treatment of patients. Whereas some treatments are very specialized and are only executed in a limited number of hospitals, e.g. highly complex deceases are typically treated in academic hospitals, a lot of treatments are performed by a variety of different hospitals. Consider for example the fact that most hospitals comprise of an emergency department. To evaluate how well a specific hospital is doing for a common type of treatment, we are interested to compare the way they treat their patients w.r.t. the way that other hospitals treat similar patients. However, in order to do so, a clear understanding of the processes performed for the different hospitals, is needed.
The different information systems, used by the different hospitals, allow us to track, often in great detail, the execution of the different processes the perform for their patients. As such, these information systems allow us to obtain valuable traces of event data. Recent developments in the research field of process mining, which represents a large body of data driven analysis techniques on the basis of such event data, allows us to gain detailed insights in the execution of these processes. The advantage of deriving insights in processes based on operational data relates to the fact that we observe what actually happened, i.e. as captured by the data. However, the current state of the field of research is still rather "a-posteriori", i.e. one is able to exploit all kinds of tools and techniques that allow us to investigate in great detail what happened during the execution of a process, what went wrong and why this is the case.
In this MS.c. thesis project, which is a joint project of the University of Pisa and the RWTH PADS chair, the student is asked to investigate the application of comparative process mining, in the context of healthcare data. Initially, different complex data sets, originating from the healthcare domain, need to be analysed, describing patient treatment in different hospitals. Based on the analysis, the student, in cooperation with the supervision team (both from Pisa and RWTH), investigates what existing comparative process mining techniques are applicable to use on the data to derive meaningful insights in the differences between the different hospitals. Furthermore, the student is challenged to develop novel ways, e.g. by exploiting simulation and alignments, to compare different data sets describing the execution of similar processes. The student is expected to execute a significant part of the thesis at both institutes, i.e. in Aachen and in Pisa.
This is a unique opportunity to work on real data and get experience in performing a research project abroad. Moreover, it is very likely that the tools and techniques developed in the context of this MS.c. thesis work will be adopted in practice!
Knowledge of basic computer science concepts, good programming skills (Java/Python) and an interest in theoretical and practical aspects of process mining (i.e. conformance checking) and business process management recommended.
- Process Mining Book
- Coursera Process Mining Course
- Process Mining in Healthcare; A case study
- Process Mining in Healthcare: A literature review
Prof.dr.ir. Wil van der Aalst (RWTH)
Prof. Davide Aloini (University of Pisa)
Sebastiaan van Zelst (RWTH)
Elisabetta Benevento (University of Pisa and Roma “Tor Vergata”)
Alessandro Stefanini (University of Pisa)