Applying Process Mining Research Articles

Understanding Process Mining for Data-Driven Optimization of Order Processing

The ability to design agile and efficient business processes is a decisive success factor for companies in increasingly dynamic and complex business environments. End-to-end order processing is of particular importance in this context. Traditional approaches to optimize the order processing are often one-time snapshots in subjective workshops that require high manual efforts. A modern approach for process optimization is process mining. However, process mining has so far only been applied to specific parts of the end-to-end order processing. Companies have not yet succeeded in extending the application of process mining to end-to-end order processing because they lack the necessary know-how about the method. A process mining demonstrator can help to explain the functionality, potential and limitation of this method to employees by visualizing the connection between the physical process and its digital image. The aim of this paper is to develop a process mining demonstrator for learning factories. The parallel experience of physical process runs and the creation of their digital images on end-to-end process level helps to teach the functionality of process mining to employees in a learning factory environment.

Process discovery on geolocation data

Fleet tracking technology collects real-time information about geolocation of vehicles as well as driving-related data. This information is typically used for location monitoring as well as for analysis of routes, vehicles and drivers. From an operational point of view, the geolocation simply identifies the state of a vehicle in terms of positioning and navigation. From a management point of view, the geolocation may be used to infer the state of a vehicle in terms of process (e.g., driving, fueling, maintenance, or lunch break). Meaningful information may be extracted from these inferred states using process mining. An innovative methodology for inferring process states from geolocation data is proposed in this paper. Also, it is presented the potential of applying process mining techniques on geolocation data for process discovery.

Diagnosis Analysis of Patient Process Log Data

Nowadays, since there are so many big data available everywhere, those big data can be used to find useful information to improve design and operation by using various analysis methods such as data mining. Especially if we have event log data that has execution history data of an organization such as case_id, event_time, event (activity), performer, etc., then we can apply process mining to discover the main process model in the organization. Once we can find the main process from process mining, we can utilize it to improve current working environment. In this paper we developed a new method to find a final diagnosis of a patient, who needs several procedures (medical test and examination) to diagnose disease of the patient by using process mining approach. Some patients can be diagnosed by only one procedure, but there are certainly some patients who are very difficult to diagnose and need to take several procedures to find exact disease name. We used 2 million procedure log data and there are 397 thousands patients who took 2 and more procedures to find a final disease. These multi-procedure patients are not frequent case, but it is very critical to prevent wrong diagnosis. From those multi-procedure taken patients, 4 procedures were discovered to be a main process model in the hospital. Using this main process model, we can understand the sequence of procedures in the hospital and furthermore the relationship between diagnosis and corresponding procedures.

A practical process mining approach for compliance management

PurposeThe purpose of this study is to examine whether the compliance management activities in the risk management environment of financial institutions can be enhanced using a Process Mining application.Design/methodology/approachIn this research, an implementation procedure for a selected Process Mining application is developed and evaluated at a financial institution in Germany.FindingsThe evaluation of the process data with the Process Mining application Disco shows that the compliance of the real-life execution of business processes can be monitored in real-time. Moreover, potential non-compliant activities and durations can be analysed in a detailed manner.Research limitations/implicationsWhen the research results are regarded, it must be considered that a general condition for the usage of a Process Mining application is that the process data is available and exportable in the required format and that data privacy regulations are fulfilled.Originality/valueThis research presents a practical use case for the implementation of a Process Mining application at the risk management department of financial institutions. It shows the value of using a technical application to carry out tedious tasks that are usually executed manually. This value is discussed and compared with the aim to help financial institutions in determining how the effectiveness and efficiencies of compliance management activities can be improved. Therefore, this research can be taken as a foundation for the practical implementation of a Process Mining application at financial institutions.

Towards Analytics-Enabled Efficiency Improvements in Maritime Transportation: A Case Study in a Mediterranean Port

The current digitalization trend, the increased attention towards sustainability, and the spread of the business analytics call for higher efficiency in port operations and for investigating the quantitative approaches for maritime logistics and freight transport systems. Thus, this manuscript aims at enabling analytics-driven improvements in the port transportation processes efficiency by streamlining the related information flow, i.e., by attaining shorter time frames of the information and document sharing among the export stakeholders. We developed a case study in a mid-sized European port, in which we applied Process Mining (PM)—an emerging type of business analytics—to a seven-month dataset from the freight export process. Four process inefficiencies and an issue that can jeopardize the reliability of the time performance measurements were detected, and we proposed a draft of solutions to cope with them. PM enabled enhancements in the overall export time length, which might improve the vessels’ turnover and reduce the corresponding operational costs, and supported the potential re-design of performance indicators in process control and monitoring. The results answer the above-mentioned calls and they offer a valuable, analytics-based alternative to the extant approaches for improving port performance, because it focuses on the port information flow, which is often related to sustainability issues, rather than the physical one.

Privacy-Preserving Process Mining

Privacy regulations for data can be regarded as a major driver for data sovereignty measures. A specific example for this is the case of event data that is recorded by information systems during the processing of entities in domains such as e-commerce or health care. Since such data, typically available in the form of event log files, contains personalized information on the specific processed entities, it can expose sensitive information that may be traced back to individuals. In recent years, a plethora of methods have been developed to analyse event logs under the umbrella of process mining. However, the impact of privacy regulations on the technical design as well as the organizational application of process mining has been largely neglected. This paper set out to develop a protection model for event data privacy which applies the well-established notion of differential privacy. Starting from common assumptions about the event logs used in process mining, this paper presents potential privacy leakages and means to protect against them. The paper also shows at which stages of privacy leakages a protection model for event logs should be used. Relying on this understanding, the notion of differential privacy for process discovery methods is instantiated, i.e., algorithms that aim at the construction of a process model from an event log. The general feasibility of our approach is demonstrated by its application to two publicly available real-life events logs.

General System Theory and the Use of Process Mining to Improve Care Pathways.

General System Theory was proposed in the post-war period as a unifying framework for interdisciplinary science based on the idea that systems have a set of similar properties and characteristics regardless of discipline. General System Theory laid the foundations for talking about things in terms of systems, many of its terms are now embedded in everyday language and it underpins a broad range of systems approaches and systems thinking. This chapter will describe the key elements of the original General System Theory (GST) including control, feedback, emergence, holism and the notion of a hierarchy of systems within systems. It will review the origin, content and foundational role of systems theory in biology, medicine, computer science, organizational theory and its central contribution to health informatics. In recent years, healthcare organizations have been encouraged to see themselves within the context of learning health systems (LHS) and to use emerging big data analytics techniques such as process mining to develop better, integrated and personalized pathways of care for patients. We use GST to reflect on these emerging approaches through a discussion and case study on recent work in urgent and emergency care. Our aim is to trace the influence of GST through emerging LHS ideas and use the framework of GST to reflect on the opportunities and limitations of our process mining approach. In particular, we will reflect on how GST can explain successes and failure in the application of process mining to care pathways and the challenges and opportunities ahead.

Applying process mining and semantic reasoning for process model customisation in healthcare

ABSTRACT Process flexibility plays a key role in high variability environments, such as healthcare. In this type of environment, the process model needs to change some elements to adjust to specific sets of requirements. Thus, this paper proposes a process model customising method based on ontology and process mining. The method proposed is applied in customising process models for acute ischemic stroke treatment. During process model customisation, the method provides decision-making support for users, thereby ensuring a structurally correct process customisation and enabling improves patient treatment by means of recommendations.

Clustering Cardiovascular Risk Trajectories of Patients with Type 2 Diabetes Using Process Mining.

Patients with type 2 diabetes have a higher chance of developing cardiovascular diseases and an increased odds of mortality. Reliability of randomized clinical trials is continuously judged due to selection, attrition and reporting bias. Moreover, cardiovascular risk is frequently assessed in cross-sectional studies instead of observing the evolution of risk in longitudinal cohorts. In order to correctly assess the course of cardiovascular risk in patients with type 2 diabetes, we applied process mining techniques based on the principles of evidence-based medicine. Using a validated formulation of the cardiovascular risk, process mining allowed to cluster frequent risk pathways and produced 3 major trajectories related to risk management: high risk, medium risk and low risk. This enables the extraction of meaningful distributions, such as the gender of the patients per cluster in a human understandable manner, leading to more insights to improve the management of cardiovascular diseases in type 2 diabetes patients.

Getting There: Evidence-Based Decision-Making in Road Trauma Prehospital Transport and Care in Queensland

Introduction:Process mining, a branch of data science, aims at deriving an understanding of process behaviors from data collected during executions of the process. In this study, we apply process mining techniques to examine retrieval and transport of road trauma patients in Queensland. Specifically, we use multiple datasets collected from ground and air ambulance, emergency department, and hospital admissions to investigate the various patient pathways and transport modalities from accident to definitive care.Aim:The project aims to answer the question, “Are we providing the right level of care to patients?” We focus on (i) automatically discovering, from historical records, the different care and transport processes, and (ii) identifying and quantifying factors influencing deviance from standard processes, e.g. mechanisms of injury and geospatial (crash and trauma facility) considerations.Methods:We adapted the Cross-Industry Standard Process for Data Mining methodology to Queensland Ambulance Service, Retrieval Services Queensland (aero-medical), and Queensland Health (emergency department and hospital admissions) data. Data linkage and “case” definition emerged as particular challenges. We developed detailed data models, conduct a data quality assessment, and preliminary process mining analyses.Results:Preliminary results only with full results are presented at the conference. A collection of process models, which revealed multiple transport pathways, were automatically discovered from pilot data. Conformance checking showed some variations from expected processing. Systematic analysis of data quality allowed us to distinguish between systemic and occasional quality issues, and anticipate and explain certain observable features in process mining analyses. Results will be validated with domain experts to ensure insights are accurate and actionable.Discussion:Preliminary analysis unearthed challenging data quality issues that impact the use of historical retrieval data for secondary analysis. The automatically discovered process models will facilitate comparison of actual behavior with existing guidelines.

Generating time-based label refinements to discover more precise process models

Process mining is a research field focused on the analysis of event data with the aim of extracting insights related to dynamic behavior. Applying process mining techniques on data from smart home environments has the potential to provide valuable insights in (un)healthy habits and to contribute to ambient assisted living solutions. Finding the right event labels to enable the application of process mining techniques is however far from trivial, as simply using the triggering sensor as the label for sensor events results in uninformative models that allow for too much behavior (overgeneralizing). Refinements of sensor level event labels suggested by domain experts have been shown to enable discovery of more precise and insightful process models. However, there exists no automated approach to generate refinements of event labels in the context of process mining. In this paper we propose a framework for the automated generation of label refinements based on the time attribute of events, allowing us to distinguish behaviourally different instances of the same event type based on their time attribute. We show on a case study with real life smart home event data that using automatically generated refined labels in process discovery, we can find more specific, and therefore more insightful, process models. We observe that one label refinement could have an effect on the usefulness of other label refinements when used together. Therefore, we explore four strategies to generate useful combinations of multiple label refinements and evaluate those on three real life smart home event logs.

Hospital Management Based On Semantic Process Mining: A Systematic Review

Introduction: Semantic Process Mining is the extension field of process mining that is based on getting knowledge of conceptual event logs (based on ontologies) for analyzing frequent and rare processes. In the healthcare studies, semantic process mining has been used in different hospitals in order to improve processes.Material and Methods: A review of the usages of semantic process mining in hospitals is done. This review contains 65 articles from PubMed, dblp and Google scholar. It is searched from 2000 to 2017. One of them was duplicated and finally, we received 64 articles. Data were extracted according to PRISMA guidelines.Results: Out of 64 articles, 6 of them were related with inclusion and exclusion criteria. Most of them detect business process mining. In 80% of studies, the semantic process mining was useful and effective to improve hospital processes and improve its management.Conclusion: This review can show an overview the application of process mining in hospitals. It can help researchers to compare semantic process mining with other methods for improving processes in hospitals and finally, it shows the use of semantic process mining to enhance hospitals processes.

Enabling value stream mapping for internal logistics using multidimensional process mining

Pen and paper-based value stream mapping (VSM) is the established tool for recording processes, identifying waste and deriving recommendations for action. However, today, its application in manufacturing industry requires a high level of effort and is challenging due to product and process complexity, as well as dynamics. To overcome these shortcomings, we are developing a methodology to apply process mining (PM) to internal logistics for a mixed-model assembly line. The methodology combines multidimensional process mining (MDPM) techniques with proven principles of lean production and VSM. Firstly, internal logistics is modelled using existing event data by automatically mapping physical logistics activities (e.g. transport, store). Secondly, to enable PM, the event data is transformed into enriched event logs. Thirdly, the MDPM approach contains (1) a discovery analysis, (2) a performance analysis and (3) a conformance analysis including a reference process classification for each individual part and process. Finally, a waste analysis and strategy for practitioners is designed to identify and prioritise wasteful parts and processes. The methodology has been applied and evaluated in a case study at a German automotive manufacturer. In the case study, we analysed 7500 parts and 15 reference processes. An analysis for each individual part and process has not been available yet. We could both identify part-specific root causes (e.g. a long lead time) and process-specific root causes (e.g. a low trace fitness). The main contribution of this paper is to provide an MDPM methodology for practitioners to enable a continuous recording, evaluation and waste analysis of each individual part and process within internal logistics.

Detection of Bottlenecks in Hospital Processes from the XAVIA HIS System using Process Mining

Sanitary services present various challenges, one of them are bottlenecks. bottlenecks cause anomalies and eventualities in the processes flow, directly affecting the patient’s attention quality. The health organizations procure to apply a process management focusing and the usage of different technologies to improve their performance. Process mining is a technology for the process analysis, which possibilities to identify characteristics and issues associated with the execution of the process from information systems. XAVIA HIS system has the necessary characteristics to contribute to the identification of bottlenecks applying process mining techniques. This research had as objective to develop and integrates an analysis view to identify bottlenecks from the XAVIA HIS system. To fulfill the proposed objective was selected and personalized the Replay a log on Petri Net for Performance / Conformance technique of process mining on the system. The analysis view developed and incorporated to the system, will allow making an analysis of the sanitary institutions execution processes. The solution proposal benefits the professionals and patients of the hospital institutions, increasing that way the quality of the provided services.

Process Mining and Conformance Checking of Long Running Processes in the Context of Melanoma Surveillance.

Background: Process mining is a relatively new discipline that helps to discover and analyze actual process executions based on log data. In this paper we apply conformance checking techniques to the process of surveillance of melanoma patients. This process consists of recurring events with time constraints between the events. Objectives: The goal of this work is to show how existing clinical data collected during melanoma surveillance can be prepared and pre-processed to be reused for process mining. Methods: We describe an approach based on time boxing to create process models from medical guidelines and the corresponding event logs from clinical data of patient visits. Results: Event logs were extracted for 1023 patients starting melanoma surveillance at the Department of Dermatology at the Medical University of Vienna between January 2010 and June 2017. Conformance checking techniques available in the ProM framework and explorative applied process mining techniques were applied. Conclusions: The presented time boxing enables the direct use of existing process mining frameworks like ProM to perform process-oriented analysis also with respect to time constraints between events.

Can process mining automatically describe care pathways of patients with long-term conditions in UK primary care? A study protocol

IntroductionIn the UK, primary care is seen as the optimal context for delivering care to an ageing population with a growing number of long-term conditions. However, if it is to...

Applying process mining techniques to improve emergency response planning for chemical spills

To evaluate an implementation process for emergency planning and to assess its effectiveness, a technical method based on process mining is utilized for the first time in hazardous chemical accidents from the perspectives of workflow and organizational structure. The proposed method investigates: (1) how the emergency-response tasks of a target emergency plan are effectively executed; and (2) how the emergency-response actors coordinate and cooperate with each other. For this purpose, a fuzzy mining algorithm was applied to reconstruct the drill process for analysing workflow. Social network mining techniques, namely density, reciprocity, node degree, centrality, and handover of work metrics, were utilized to explore the organizational structure among the actors. By means of emergency-response drills, a pre-defined emergency plan for chlorine release was analyzed, for which mining results were obtained. Regarding the workflow, four deviations were detected from the target emergency plan, which suggest ways of improving the plan rules. Regarding the organizational structure, the most influential actors A1, A5, A10, whose actions directly determined the plan implementation and outcome. The proposed method can facilitate the improvement of existing processes and organizational structures for chemical accident emergency response planning.

Predictive Monitoring of Business Processes: A Survey

Nowadays, process mining is becoming a growing area of interest in business process management (BPM). Process mining consists in the extraction of information from the event logs of a business process. From this information, we can discover process models, monitor and improve our processes. One of the applications of process mining, is the predictive monitoring of business process. The aim of these techniques is the prediction of quantifiable metrics of a running process instance with the generation of predictive models. The most representative approaches for the runtime prediction of business process are summarized in this paper. The different types of computational predictive methods, such as statistical techniques or machine learning approaches, and certain aspects as the type of predicted values and quality evaluation metrics, have been considered for the categorization of these methods. This paper also includes a summary of the basic concepts, as well as a global overview of the process predictive monitoring area, that can be used to support future efforts of researchers and practitioners in this research field.

Practical Aspects of Event Logs Creation for Industrial Process Modelling

Abstract In the paper we address the challenge of applying process mining techniques for discovering models of underground mining operations based on a sensor data. The paper presents practical approach of creation an event log based on industrial sensors data gathered in an underground mine monitoring systems. The proposed approach enables to generate event logs at different generalization levels based on several numbers of discovered stages of devices performance. For discovering process stages data mining techniques such as exploratory data analysis, clustering and classification have been applied. Created event log has been used in one of the process mining tasks - process model discovery.

Using Process Mining to examine the sustainability of instructional support: How stable are the effects of metacognitive prompting on self-regulatory behavior?

The current study investigates the sustainability of metacognitive prompting on self-regulatory behavior using a Process Mining approach. Previous studies confirmed beneficial short-term effects of metacognitive prompts on the learning process and on learning outcomes. However, the question of how stable these effects are for similar tasks in the future so far remains unanswered. Also, the use of online trace methods and the emergence of new analytical approaches allow deeper insights into the sequential structure of learning behavior. Therefore, we examined long-term effects of instructional support on sub-processes of self-regulated learning using Process Mining. Think-aloud protocols from 69 university students were measured during two hypermedia learning sessions about Educational Psychology. Metacognitive prompts supported the experimental group (n = 35) only during the first session. Based on a process model generated by using the data of the first learning task, we analysed the sustainability of effects during the second learning session. Results showed significant differences between the experimental and control group regarding the frequency of metacognitive strategies, which remain stable over time. Additionally, the application of Process Mining indicated which sequences of learning events were transferred to the second session. Our findings demonstrate the benefits of evaluating instructional support using analysis techniques that take into account the sequential structure of learning processes. While the results provide initial evidence for sustainable long-term effects on self-regulatory behavior, they have to be replicated in future research.