Life Sciences & Health Care

Session 4.1

Thursday, September 17, 2015 - 10:30 to 12:00
LC Ceremonial hall 1
Juan Sequeda



Semantic data integration in the health care industry

A common problem in large and complex organizations is the distribution of information over various systems. This hampers overview creation of business relevant data. Typically, this issue is further complicated by the problem, that often non-standardized strings are used to describe concepts (i.e. external cooperation partners or diseases are expressed in various ways). In the context of clinical cooperation’s, we developed an application to solve these issues. First, we integrated data from several relational databases with different table schemas. To become independent of the source system, we converted the data to simple RDF triples containing the information from the different relational databases. Subsequently, this intermediate RDF was processed in Unified Views, a custom ETL (Extract Transform Load) tool, specifically build for RDF - ETL tasks. Within Unified Views, spelling variants were normalized and further information such as institutional or disease hierarchies were added. Moreover, the data is converted to a predefined RDF model. Finally the data was loaded into a RDF data store (Virtuoso) and queried using SPARQL. The queries were wrapped by an intuitive user interface. Due to the semantic enrichment of the data during the ETL conversion, outstanding search and overview features could be provided to the end-users.


Clinical decision system for GIST cancer

Clinical decision support system application are a class of application to support physicians in their choice in treating patients. Cancer treatment is one of the area where Cdss applications can help physicians due to strict recommendations and the need for deciding if patients are eligible to enter clinical trial.

In Poland a pilot study conducted at the Marie-Curie Oncology Center in Warsaw (MCMCC) revealed that medical errors lead to decrease of patient survival at about 20%. The key point of our prototype was to educate and/or directly help medical practitioners in applying recommended treatment. 

Our application, called Clinical decision support system (Cdss) for GIST cancer treatment, has been developed in collaboration with the MCMCC to help physicians treat GIST cancer and is currently used experimentally in this center. Our application has been formalized using semantic web standards from the application structure to the patient and clinical recommendations that are shown. The application is using fast reasoning to decide what is the next step in the treatment and to add recommendations to the form that is shown. This kind of technologies have already been applied to such applications but never to this extent. The Cdss application that we have implemented is a practical implementation of the semantic form paradigm that we are working on in our company: a way to formalize forms by using semantic technologies to enhance productivity and data consistency.

A Linked Data Platform for Finite Element Biosimulations

Biosimulation models have been recently introduced to understand the exact causative factors that give rise to impairment in human organs. Finite Element Method (FEM) provides a mathematical framework to simulate dynamic biological systems, with applications ranging from human ear, cardiovascular, to neurovascular research. Due to lack of a well-integrated data infrastructure, the steps involved in the execution and comparative evaluation of large Finite Element (FE) simulations are time consuming and are performed in isolated environments. In this paper, we present a Linked Data platform to improve the automation in integration, analysis and visualisation of biosimulation models for the inner-ear (cochlea) mechanics. The proposed platform aims to help domain scientists and clinicians for exploring and analysing Finite Element (FE) numerical data and simulation results obtained from multiple domains such as biological, geometrical, mathematical, physical models. We validate the platform by conducting a qualitative survey and perform quantitative experiments to record overall performance.