Presentation by Dr. Zhengxing Huang: Predictive monitoring of clinical pathways

Dr. Zhengxing Huang of Zhejiang University (Hangzhou, China)

Predictive monitoring of clinical pathways.

Accurate and timely monitoring, as a key aspect of clinical pathway (CP) management, provides crucial information to medical staff and hospital managers for determining the efficient medical service delivered to individual patients, and for promptly handling unusual treatment behaviors in CPs. In many applications, CP monitoring is performed in a reactive manner, e.g., variant treatment events are detected only after they have occurred in CPs. Alternatively, this study systematically presents a learning framework for predictive monitoring of CPs. The proposed framework is composed of both offline analysis and online monitoring phases. In the offline phase, a particular probabilistic topic model, i.e., treatment pattern model (TPM), is generated from electronic medical records to describe essential/critical medical behaviors of CPs. Using TPM-based measures as a descriptive vocabulary, online monitoring of CPs can be provided for ongoing patient-care journeys. Specifically, two typical predictive monitoring services, i.e., unusual treatment event prediction and clinical outcome prediction, are presented to illustrate how the potential of the proposed framework can be exploited to provide online monitoring services from both internal and external perspectives of CPs. Extensive evaluation on a real clinical data-set, typically missing from other work, demonstrates the efficacy and generality of the proposed framework for surveillance-based CP management in a predictive manner.

Back to event

New Employee: Zahra Valizadeh

Zahra1Zahra Valizadeh-Gh received her BSc. degree in applied mathematics from Kharazmi University, Tehran, Iran, in 2005, the MSc. degree in the same major from Sharif University of Technology, Tehran, Iran, in 2007, and the PhD. degree in numerical optimization from the Islamic Azad University (IAU), Iran, in 2012. Since 2012, she has been Assistant Professor at IAU. Now, she has joint to Information Systems Group as a visiting researcher for six mounths. Her research interests include the fuzzy logic, systems of fuzzy equations and systems of fuzzy relational equations/inequalities as well as the multi-criteria optimization theory.

Journal articles:

Z . Valizadeh-Gh, E . Khorram (2015) Linear Fractional Multi-Objective Optimization Problems Subject to Fuzzy Relational Equations with the Max-Average Composition, Applied and Computational Mathematics. Special Issue: New Advances in Fuzzy Mathematics: Theory, Algorithms, and Applications, 4(1-2), 20-30.

E. Khorram, R. Ezzati, Z. Valizadeh (2014) Linear fractional multi-objective optimization problems subject to fuzzy relational equations with a continuous Archimedean triangular norm, Information Sciences, 267, 225-239.

R. Ezzati, S. Khezerloo, N. Mahdavi-Amiri, Z. Valizadeh (2014) Approximate Non-negative Symmetric Solution of Fully Fuzzy Systems Using Median IntervalDefuzzi_cation, Fuzzy Information and Engineering, 6, 1-28.

E. Khorram, R. Ezzati, Z. Valizadeh (2012) Solving nonlinear multi-objective optimization problems with fuzzy relation inequality constraints regarding Archimedean triangular norm compositions, Fuzzy Optimization and Decision Making, 11(3), 299-335.

R. Ezzati, S. Khezerloo, N. Mahdavi-Amiri, Z. Valizadeh (2012) New Models and Algorithms for Approximate Solutions of Single-Signed Fully Fuzzy LR Linear Systems, Iranian Journal of Fuzzy Systems, 10(3), 1-26.

Z. Valizadeh, R. Ezzati, S. Khezerloo (2012) Approximate Symmetric Solution of Dual Fuzzy Systems Regarding Two Di_erent Fuzzy Multiplications, Indian Journal of Science and Technology, 5 (2), 2100-2112.

S. Khezerloo, M. Montazeri, Z. Valizadeh (2010) A New Method for Solving Fuzzy Linear System, International Journal of Industrial Mathematics, 2 (2), 97-104.

New Employee Lonneke Vermeulen

LVI studied Industrial Engineering (bachelor) and Operations, Management and Logistics (master) at the Eindhoven University of Technology, The Netherlands. In 2013 I graduated on my research towards ‘A process modelling method for Care Pathways’, which was conducted in participation with the Heart centre of the Catharina Hospital Eindhoven and supervised by Uzay Kaymak, Pieter van Gorp, Hui Yan and Erik Korsten. Since then I’ve been working on the development of the Clinical Decision Support System Tracebook, developed within the Brainbridge project of Shan Nan, from within the Catharina hospital. For the upcoming months I will continue my work on the Tracebook system and clinical trials, as well as write a paper of my master thesis research and preparing a conference on Fuzzy sets.

Colloquium IE&IS/IS Sept 5, 2014

Anna Wilbik

Decision support via linguistic summaries

The business environment (climate) is constantly changing, and it is becoming more and more complex. Making good decisions may require considerable amounts of relevant data, information, and knowledge. With the advancement in information technology, more and more data are stored and analyzed. The amount of data is beyond human cognitive capabilities and comprehension skills. There is an urgent need to process those data into knowledge. To meet those needs, the fields of data mining and knowledge discovery are developing rapidly. Following this trend, also the methods to summarize the data and to analyze these summaries are getting more and more important.

In this presentation we will present briefly the decision support framework, as well how the linguistic summaries fit there. We will conclude with some examples.

PhD defense of Rui de Almeida: Conditional Density Models Integrating Fuzzy and Probabilistic Representations of Uncertainty @June 26 Erasmus University Rotterdam

Erasmus School of Economics (ESE), Erasmus University Rotterdam – See More
On Thursday June 26 Rui de Almeida will defend his Ph.D. thesis entitled “Conditional Density Models Integrating Fuzzy and Probabilistic Representations of Uncertainty” @ Senate Hall, A-Building, Woudestein Campus 11.30-13.00 hrs.

Prom./coprom.: Uzay Kaymak / Prof.  João M. Sousa


Conditional density estimation is an important problem in a variety of areas such as system identification, machine learning, artificial intelligence, empirical economics, macroeconomic analysis, quantitative finance and risk management.

This work considers the general problem of conditional density estimation, i.e., estimating and predicting the density of a response variable as a function of covariates. The semi-parametric models proposed and developed in this work combine fuzzy and probabilistic representations of uncertainty, while making very few assumptions regarding the functional form of the response variable’s density or changes of the functional form across the space of covariates. These models possess sufficient generalization power to approximate a non-standard density and the ability to describe the underlying process using simple linguistic descriptors despite the complexity and possible non-linearity of this process.

These novel models are applied to real world quantitative finance and risk management problems by analyzing financial time-series data containing non-trivial statistical properties, such as fat tails, asymmetric distributions and changing variation over time.

New Employee Helen Ma

I did my PhD in the department of Computer Science in The Chinese University of Hong Kong from 2003 to 2006. My research project was bidding strategies in agent based continuous double auctions (CDAs). I had been researching on the new bidding strategy and powerful factors which can improve the performance of existing bidding strategies in CDAs. After that, I had worked as PostDoc from 2007 to 2012 in the national research institute of mathematics and computer science (CWI), and later at the department of the Built Environment, TU/e, The Netherlands. In the meanwhile, I had extended my research area from bidding strategies adopted by agents to the auctions mechanisms in centralized systems and distributed systems. Moreover, giving my experience on multi-agent simulation and adaptive agent behaviour, I had been involved in the activity travel scheduling for multiple individuals where joint activity and travel scheduling, credit mechanism, social network, and negotiation have been interwoven into such a dynamic system. Since 2012, I had been working at R&D, Vanderlande Industries. My work focused on a new generation of software product which plans realtime multiple shuttles’ travelling and meets the throughput requirement in the distribution center.

New Employee Harold Lijten

My name is Harold Lijten.
My colleagues describe me as a weathered professional with a broad and deep knowledge of the finance domain and its intersection with  IT.  My  professional specialization is enterprise- software architecture and software development.
During my daily practices some really interesting questions cross my path and they are the reason for me to maintain a solid link with the academic world.

One of these questions which has my attention for a long time is; can we create capabilities within the architecture of an information system which facilitate a substantial increase of the flexibility and life-time of an information system? My strong desire to answer this question has led to some years of research already.
The purpose of my current research is to determine the contribution of the concept scenario planning applied during the process of designing and developing an information system. The main subject of study is researching the possible implications for the life-time of an information system and its architecture when scenario planning is used during the process of design and development.

New Employee Bilge Celik Aydin

I am graduated from Industrial Engineering Department from Middle East Technical University in 2009. I completed my MSc degree in 2011 there while working as a teaching assistant. I have assisted courses such as simulation, systems thinking, network flow, work systems analysis and design, data mining and so on.
I focused on data mining and multi criteria optimization during my masters studies. For my thesis, I developed a distance-based multi-criteria optimization algorithm for the sorting problem.
I was involved in an applied project in KU Leuven last year about process improvement in the emergency department of Turnhout Hospital. We developed an advanced simulation model of the department based on the real data provided by the hospital. What-if analysis is conducted for evaluating the performance of different schedules. The project continues with integration of a genetic algorithm for staff schedules with the simulation model.

Presentation Dr Peter Szlosarek

A bioinformatic approach to mesothelioma therapeutics: from ADAM to TRAP

Arginine deprivation is a novel antimetabolite strategy for the treatment of arginine-dependent cancers that exploits differential expression and regulation of key urea cycle enzymes. Several studies have focused on inactivation of argininosuccinate synthetase 1 (ASS1) in a range of malignancies, including melanoma, hepatocellular carcinoma, and mesothelioma. Promoter methylation, in particular, has been identified as a mechanism for loss of the tumor suppressor role of ASS1 leading to tumoral dependence on exogenous arginine. Clinical trials of several arginine depletors are ongoing, including pegylated arginine deiminase (ADI-PEG20, Polaris Group, US) and bioengineered forms of human arginase. The challenge will be to identify tumors sensitive to arginine depletors, and integrate these agents into multimodality drug regimens using predictive biomarkers. Here, we have applied a bioinformatic approach to identify tractable pathways with ADI-PEG20 in the treatment of patients with mesothelioma. Recently, our phase 2 study of ADI-PEG20 in mesothelioma (ADAM) completed accrual and we are now launching a phase I combinatorial trial (TRAP) in the UK based on our bioinformatics studies.


Dr Peter Szlosarek (MBBS BSc MRCP PhD) is a Clinical Senior Lecturer at the Barts Cancer Institute, and Cancer Physician at St. Bartholomew’s Hospital, London. He studied Medicine and Pharmacology at King’s College, London and then specialised in Medical Oncology completing a PhD on the links between TNF-a, inflammation and cancer at the University of London. His clinical and lab research interests are in metabolic approaches to cancer therapy, particularly the role of arginine deprivation therapy in arginine-dependent cancers. This has led to clinical trials of the arginine-depleting agent ADI-PEG20 (Polaris Group, US) in mesothelioma (CTAAC grant) and small cell lung cancer, the latter a collaboration with the Ludwig Institute for Cancer Research in New York, US. He is funded by several grant bodies including Cancer Research UK, Barts and The London Charity, Medical Research Council and the British Lung Foundation. He maintains a research-orientated clinical practice at Barts in thoracic and cutaneous malignancy and is a member of the Royal College of Physicians, the Association of Cancer Physicians, the EORTC, AACR and ASCO.

Event details