Interactive Data-Driven Process Model Construction

Dixit, Prabhakar M.; Verbeek, H. M. W.; Buijs, Jorn op den; Aalst, Wil M. P. van der

doi:10.1007/978-3-030-00847-5_19

Cited by 29 publications

(20 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The interactive PM is a PM approach specific for the discovery of process models, and bases its strengths on the combination of domain knowledge and PM techniques (Dixit et al, 2018). This allows for the generation of more precise process models, as the potential drawbacks of automated discovery techniques are suppressed by the intervention of the domain expert.…”

Section: Literature Discussionmentioning

confidence: 99%

Process mining applications in the healthcare domain: A comprehensive review

Guzzo

Rullo

Vocaturo

2021

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Process mining (PM) is a well-known research area that includes techniques, methodologies, and tools for analyzing processes in a variety of application domains. In the case of healthcare, processes are characterized by high variability in terms of activities, duration, and involved resources (e.g., physicians, nurses, administrators, machineries, etc.). Besides, the multitude of diseases that the patients housed in healthcare facilities suffer from makes medical contexts highly heterogeneous. As a result, understanding and analyzing healthcare processes are certainly not trivial tasks, and administrators and doctors look for tools and methods that can concretely support them in improving the healthcare services they are involved in. In this context, PM has been increasingly used for a wide range of applications as reported in some recent reviews. However, these reviews mainly focus on discussion on applications related to the clinical pathways, while a systematic review of all possible applications is absent. In this article, we selected 172 papers published in the last 10 years, that present applications of PM in the healthcare domain. The objective of this study is to help and guide researchers interested in the medical field to understand the main PM applications in the healthcare, but also to suggest new ways to develop promising and not yet fully investigated applications. Moreover, our study could be of interest for practitioners who are considering applications of PM, who can identify and choose PM algorithms, techniques, tools, methodologies, and approaches, toward what have been the experiences of success.

show abstract

Section: Literature Discussionmentioning

confidence: 99%

Process mining applications in the healthcare domain: A comprehensive review

Guzzo

Rullo

Vocaturo

2021

WIREs Data Min & Knowl

View full text Add to dashboard Cite

show abstract

“…In this way, domain knowledge is embedded in the discovery processes, instead of being used to interpret the output of an automated algorithm. Using a case study of the patient trajectory of lung cancer patients, Benevento et al [10] show that the interactive process discovery approach of Dixit et al [23] generates control-flow models which are both accurate and understandable. In contrast, automated control-flow discovery algorithms might experience difficulties to generate such an accurate and understandable model.…”

Section: Process Discoverymentioning

confidence: 99%

Using Process Mining in Healthcare

Martin

Wittig²,

Muñoz-Gama

2022

Lecture Notes in Business Information Processing

View full text Add to dashboard Cite

This chapter introduces a specific application domain of process mining: healthcare. Healthcare is a very promising domain for process mining given the significant societal value that can be generated by supporting process improvement in a data-driven way. Within a healthcare organisation, a wide variety of processes is being executed, many of them being highly complex due to their loosely-structured and knowledge-intensive nature. Consequently, performing process mining in healthcare is challenging, but can generate significant societal impact. To provide more insights in process mining in healthcare, this chapter first provides an overview of healthcare processes and healthcare process data, as well as their particularities compared to other domains. Afterwards, an overview of common use cases in process mining in healthcare research is presented, as well as insights from a real-life case study. Subsequently, an overview of open challenges to ensure a widespread adoption of process mining in healthcare is provided. By tackling these challenges, process mining will become able to fully play its role to support evidence-based process improvement in healthcare and, hence, contribute to shaping the best possible care for patients in a way that is sustainable in the long run.

show abstract

“…Compared to our extended incremental process discovery, all approaches remain a black-box from a user's perspective since they work in a fully automated fashion. In [5], an interactive modeling approach is proposed. A user constructs the model guided by the algorithm, i.e., the user makes the design decisions in the process model, as opposed to our approach, where the discovery algorithm is guided by the user.…”

Section: Related Workmentioning

confidence: 99%

Freezing Sub-Models During Incremental Process Discovery: Extended Version

Schuster¹,

Zelst²,

Aalst³

2021

Preprint

View full text Add to dashboard Cite

Process discovery aims to learn a process model from observed process behavior. From a user's perspective, most discovery algorithms work like a black box. Besides parameter tuning, there is no interaction between the user and the algorithm. Interactive process discovery allows the user to exploit domain knowledge and to guide the discovery process. Previously, an incremental discovery approach has been introduced where a model, considered to be "under construction", gets incrementally extended by user-selected process behavior. This paper introduces a novel approach that additionally allows the user to freeze model parts within the model under construction. Frozen sub-models are not altered by the incremental approach when new behavior is added to the model. The user can thus steer the discovery algorithm. Our experiments show that freezing sub-models can lead to higher quality models.

show abstract

Interactive Data-Driven Process Model Construction

Cited by 29 publications

References 23 publications

Process mining applications in the healthcare domain: A comprehensive review

Process mining applications in the healthcare domain: A comprehensive review

Using Process Mining in Healthcare

Freezing Sub-Models During Incremental Process Discovery: Extended Version

Contact Info

Product

Resources

About