TRAIL-Beta Congress 2012

The 2012 edition of the BETA Conference has taken place on 30-31 October, in Rotterdam, the Netherlands. This time, the conference was organized together with TRAIL Conference. The competitive venue at the Stadium of Feyenoord, the famous football team from Rotterdam, was the ideal setting for presenting our recent research results. The healthcare cluster of our department (IS@IEIS) presented recent research results on business process redesign in healthcare. The conference was also a good occasion for interacting with the researchers from the TRAIL research school.


2012 Edition of IEEE International Conference on Systems, Man and Cybernetics took place in Seoul, Korea.

Our papers “Addressing Health Information Privacy with a novel Cloud-Based PHR System Architecture” (with Pieter van Gorp, Marco Comuzzi and André Fialho) and “On Process Mining in Health Care” (with Ronny Mans, Tim van de Steeg and Meghan Dierks) received good reactions and generated interesting comments. These comments confirm the interest in this line of research.

The conference also featured a special panel session in honor of the cybernetics pioneer Norbert Wiener. The participants emphasized the importance of systems thinking and multidisciplinary engineering systems research for addressing the societal challenges of the 21st century.

Analysis of operative times in bariatric surgery: MSc defense Pablo Perdiguer

Pablo PerdiguerPablo Perdiguer has successfully defended his M.Sc. thesis titled “An Analysis of Operative Times in Bariatric Surgery and Modelling for Predicting the Consequences of Intra-Operative Complications in Anesthetic Procedures: data mining application in healthcare”. Pablo was an exchange student from Spain and studied Operations Management and Logistics in Eindhoven. His project was a collaboration with Catharina Hospital Eindhoven.

In this report, two different studies are carried out based on data obtained from the 4kp, a database at the Catharina Hospital in Eindhoven. The first analysis addresses the investigation of operative times in bariatric surgery, with a special focus on understanding their variation over recent years. Initially, some background is provided by a look at some of the literature on bariatric surgery, which is followed by an in-depth treatment of data mining. Indeed, the use of data mining techniques is one of the main features of this project and, in particular, the application of regression analysis and k-nearest neighbor algorithm for the prediction and classification of operative times.

Secondly, a modeling for the prediction of the consequences of intraoperative complications in anesthesia-related procedures is completed. Before the data mining techniques are applied, the complications and their evolution over time are explored, which serves as a first step in the subsequent analysis. For the study of the complications of complications, the accuracy of the algorithms involving decision tree classification and neuronal network prediction is tested, and alternative research models are also presented. All processes are part of the Knowledge Discovery in Databases framework, which provided a structured methodology with which to work.

The two aforementioned studies are part of work performed with the database, which is referred to as the extraction information. This process is fully supported by practicing doctors from the Catharina Hospital who contributed with their expert knowledge in order to better understand and discuss the results obtained. The information extracting procedure is aimed at providing useful results on bariatric surgery operative times and intraoperative complications in anesthesia-related operations, both general and bariatric-specific. In addition, the understanding of changes in operative times leads to the identification of what extra information is needed to improve the quality of the studies, and the modeling of complications might be helpful for practitioners in order to better comprehend the nature of patients’ complications.

All the studies discussed here are based upon prior work on the database, which can be regarded as the creating information phase. In this process, a well-filtered bariatric surgery database was created, and some guidelines for improving the current database, encompassing both data collection and data available, are given. Furthermore, data cleaning is done and transformations of the database through workflows that can be easily checked (automation of the process) are made available.

Finally, all results are discussed, including the incorporation of expert knowledge and advice, and the possibility of future work and its directions is addressed. In addition, a CD containing useful information and data used in this research is made available along with a hard copy of the project. Specifically, it contains Excel files with data directly extracted from the database, KNIME projects where workflows are created and this paper itself, accompanied by the final presentation in PowerPoint format.

Process mining in the anesthesia care: MSc defense Arnau Carbonell

Arnau CarboneMasterThesisFinalll has successfully defended his M.Sc. thesis titled “Analysis of the Treatment of Pain and Anxiety in the Anesthesia Care in an ERCP: a process mining application in heath care”. Arnau was an exchange student from Spain and studied Operations Management and Logistics in Eindhoven. His project was a collaboration with Harvard affiliated Beth Israel Deaconess Medical Center in Boston.

This work is an initial study into the application of process mining techniques in a clinical environment. Healthcare processes have to deal with an extraordinary uncertainty and healthcare organizations, because of their processes, are seen as highly dynamic, complex, ad hoc, and multidisciplinary. Unfortunately, process mining techniques are usually not meant for the medical environment, since they are more likely to be used in administrative processes. Therefore, in this study we search for appropriate mining methods to be applied in the medical setting. To carry out the study, two databases of the anesthesia care of ERCP (Endoscopic Retrograde Cholangio Pancreatography) are used. The study shows that existing process mining methods have a limited application with clinical data.