Symposium: Supporting physicians in the treatment of comorbid patients: GLARE’s approach




Symposium: Supporting physicians in the treatment of comorbid patients: GLARE’s approach

Faculty of Science


Conference / Symposium

GLARE is a general system supporting physicians in the acquisition, representation and execution of clinical practice guideleines (CPGs). CPGs are widely used to support physicians, but only on individual pathologies. The treatment of patients affected by multiple diseases (comorbid patients) requires the development of new approaches. We propose a new approach, to support (but not to substitute) physicians in the different phases of the treatment: (i) focusing on the parts of the CPGs that are relevant for the treatment of the patient at hand, (ii) detection of possible interactions between the focused actions, on the basis of a domain-independent and CPG-independent ontology, (iii) selection of the modality to be adopted in order to manage each single interaction,  and (iv) “merge” of the different managements (in case more than one interaction has to be taken into account).  As an additional and peculiar feature, in phases (ii)-(iv) GLARE deeply takes into account temporal reasoning, to face only those interactions that can actually occur in time, and to propose temporalized solutions to such interactions.


Short Bio:

Paolo Terenziani, PhD

Since October 2000, he is Full Professor in the Department of Computer Science of such a University. Paolo Terenziani’s research activity covers different areas of Computer Science: Artificial Intelligence, Databases, and Medical Informatics. As regards Artificial Intelligence, his activity concerned Knowledge Representation, with specific attention to the fields of temporal reasoning (constraint propagation algorithms, treatment of periodicity) and diagnosis. In the field of DataBases, he mainly focused on the extension of “standard” relational models and algebrae to deal with time-related phenomena, and with the semantics of temporal databases. As regards Medical Informatics, since 1997 he is involved with Azienda Ospedaliera S. Giovanni Battista in Turin (the second hospital in Italy, as regards dimensions) in a long-term project for the development of GLARE, a semi-automatic manager of clinical guidelines.

Paolo Terenziani published more than 120 papers about these topics in refereed international journals and conference proceedings. As a recognition of his research merits, in 1998 he got the annual “Artificial Intelligence Prize” from the Italian Association for

Artificial Intelligence. 


From Big Data to Better Cancer Care

Since 2008 MAASTRO Clinic (Maastricht, The Netherlands) has  been embarking on a research program called Computer Assisted Theragnostics or CAT. In various CAT projects (euroCAT, duCAT,  chinaCAT, ozCAT, VATE), a global IT infrastructure is developed in which cacner centers are being connected with currently up to 25 partners. The aim of CAT is to enable cross-institute, privacy-preserving, data sharing & machine learning and more efficient clinical evidence generation: a concept now commonly referred to as "Rapid Learning". 
In the seminar innovative technology to extract, store and process (big) data for Rapid Learning and will be discussed.  All this data is often seen as tremendously promising and is predicted to change health care radically, but at this point in time is mostly a challenge as we keep accumulating data without a clear path to clinical applications while privacy concerns are on the rise. Methods and examples how we go from data to making a difference in lives of cancer patients will be presented. As will the methods to do this in a way that preserves the privacy of patients. 

Key words: Big Data, Distributed Learning, Image Mining, Semantic Web, Ontologies

Short bio:
Andre Dekker, PhD
Prof. Andre Dekker is a board-certified medical physicist at MAASTRO Clinic, Maastricht, The Netherlands since 2005. He has been the head of Medical Physics until 2009 and then led for numerous years the department of Information and Services that manages medical informatics and ICT. He is now responsible for all Research and Education activities at the hospital. He was appointed as a full professor at Maastricht University in 2015 where he holds the chair "Clinical Data Science"
From 2008, he started and is the principal investigator of the GROW-Maastricht University research division of MAASTRO Knowledge Engineering. His research focuses on two main themes: 1) global data sharing infrastructures; 2) machine learning on this data for decision support systems. The main scientific breakthrough has been the development of a Semantic Web and ontology based data sharing and distributed learning infrastructure that does not require data to leave the hospital. This has reduced many of the ethical and other barriers to share data.
Prof. Dekker has authored over 100 publications (h-index 40) in peer reviewed journals covering informatics, imaging, radiotherapy, tissue optics and heart disease and holds multiple awarded patents. He has held visiting scientist appointments at the Christie Hospital NHS trust; University of Sydney Australia; Liverpool and Macarthur Cancer therapy centres Australia; Illawarra Shoalhaven Local Health District Australia; Universita Cattolica Del Sacro Cuore, Italy; Radiation Therapy Oncology Group, USA, Varian Medical Systems, USA and the Princess Margaret Hospital in Canada.