Increasing accessibility and reproducibility of process mining research in healthcare
The goal of this thesis was to develop a set of best practices for process mining research in healthcare. Process mining in healthcare has been studied by several researchers already, but these studies suffer from disappointing results, which may be partly to blame to the low accessibility and reproducibility of the process mining research methodologies. Therefore, in this thesis we aimed to synthesize the most common and best research steps, or best practices, of previous process mining research by means of a multiple case study and expert interviews into one process mining methodology for healthcare which would show increased accessibility, reproducibility and results that are better, or at least comparable, to present process mining research. Pattern language was identified as the most suitable method to report the best practices and as a result, 22 best practices patterns that cover a variety of process mining research steps have been developed. Subsequently, 11 patterns were selected as recommendations for use in healthcare, as they showed the most promising results and highest accessibility. In addition, we have introduced the concepts of virtual machines and screencasts to the field of process mining as means to increase accessibility and reproducibility of the best practices pattern language. The results of the best practices and recommendations have been validated by experts at two Dutch healthcare institutions and showed that the process mining best practices pattern language is indeed able to produce process models which are of similar or superior quality compared to process models created
with conventional methodologies.
Get the PDF from the TU/e library
Comparing BPM approaches in the healthcare Domain: Case Handling vs. Model Driven Engineering (BPMone vs. Mendix)
In a world of continuously changing business environments, organizations are forced to deal with, and adjust to the demands for such level of change. To handle this level of change, many companies use different approaches and tools which include modeling and measuring business processes. Business Process Modeling provides support on business operations to improve business efficiency and to find new opportunities for the company. Not all organizations have recognized the added value of this approach. Especially healthcare organizations do not fully use the benefits of IT support. This thesis presents the pros and cons of two promising BPM approaches in the healthcare domain, with the Eye Care Network in Rotterdam as case study. The Eye Care Network is a collaborating healthcare business network of different players within the ophthalmology domain. There is often a network manager within a healthcare business network that wants to standardize the way the different players work. This can improve efficiency within the network and it can improve communication between the different players. The Eye Care Network, as a network manager, designed different treatment plans, as desired processes for treating patients in the hospitals connected to the network. One important aspect of these treatment plans is dealing with exceptions. Flexibility is required with this, to ensure the network members can continue providing their services, even when they want or need to deviate from the standardized process. This thesis presents the further investigated business process that describes the different steps a patient will endure during the treatment plan for the eye disease glaucoma. This thesis discusses how well two promising BPM approaches meet with the requirements from the Eye Care Network, based on the construction and evaluation of two prototypes. To be able to objectively compare the two approaches, the comparison framework of the thesis consists of seven principles divided over four different levels; case study level, design level, language level, and tool level. Model Driven Engineering (MDE) and Case Handling are the two approaches used to deal with the required flexibility by design. BPMone from Pallas Athena represents a specialized case handling tool, and Mendix represents a MDE tool. After creating a first version of both applications, BPMone could be seen as the best option out of the two tools. Mendix’s primary weakness is the lower level of abstraction, compared to BPMone. This results in the need of a higher specification effort, which leads to the risk of making bad design decisions. Decisions that are already taken implicitly in BPMone. However, this limitation can be overcome by changing the Mendix model with a number of novel patterns, based on the apparently stronger BPMone principles. Similar options are not seen for BPMone (nor is there a need for it). An improved version of the Mendix model resulted in a comparing situation where BPMone was no longer the clear winner. This thesis not only gives a description of the abstraction patterns it also shows how they could be used on other cases as well. The suitability is not limited to this specific healthcare setting, since the generalizability of the thesis conclusions are demonstrated by considering a case study from a completely different domain as well.
The goal of this thesis is to examine which BPM approach is best suiting the requirements given by the Eye Care Network, for their business process. Furthermore, the possibility to generalize these findings outside of this case study will be checked.
See attached: Poster Master Thesis_G.J.M.Muijres