Expected Results and Impacts

The outputs from IASIS will have significant impacts on the EU healthcare system, ICT industry, individual patients and wider society as indicated below.  

Comprehensively map big data in a reachable and manageable way by applying principles for sharing and reusability, creating a network of knowledge by linking heterogeneous data sources for public health strategy.

IASIS will achieve this by bringing together disperse data sources, varying from electronic health records, to genomic data, and open databases, such as clinical scientific publications. The result of the fusion of this knowledge and data will result on the IASIS integrated platform. This platform will impact on the way healthcare professionals tackle the issues related to disease diagnosis and treatment and the subsequent decision making process. IASIS aims to offer a set of analytical tools that will enable the discovery of novel relationships and patterns in a very heterogeneous data set. IASIS also aims to add value in various fields such as the biomedical sciences and healthcare including personalised medicine, clinical research, drug discovery and public health.

Emerging data driven analytics and advanced simulation methods to study causal mechanisms and improve forecasts of spatial and temporal development of ill-health and disease.

IASIS will provide improved technologies for biomedical analysis, as well as new tools for using large datasets. The integration of all the extracted knowledge from the individual datasets will help us discover important patterns and relations (causal and temporal) between disease characteristics and treatment. This knowledge will be available for IASIS users (clinicians and policy makers) who will be able to draw very useful decisions about the diagnosis, treatment and prognosis of the disease. 

Develop innovative approaches to improve current risk stratification methodologies.

It is important for healthcare providers to understand their patient population including the common disease states and diagnosis. Risk stratification is one approach where providers assign a health risk status to a patient, and use the patient’s risk status to direct and improve care. IASIS will contribute towards this direction, by providing new important factors for defining patient risk status. The latter will occur by the innovative combination of different sources, which can reveal patterns and factors that could not be discovered before. 

Turning large amounts of data into actionable information to authorities for planning public health activities and implementation of an approach "health in all policies".

The vision for better information use for health system decision-making has never been stronger. Working toward a shared vision of better information for improved health can help realize an important opportunity to achieve the best possible health, the highest quality care and a sustainable, efficient health system - all of which can result in better health outcomes for Europeans. IASIS will put in place several components and tools that directly impact and reinforce the multidisciplinary decision-making process of involved healthcare professionals by presenting a consistent and integrated view of all relevant data sources. 

Placing prevention strategies on evidence base, evaluation of the efficiency and effectiveness of implemented strategies, feedback of results into the development of methods 

IASIS will be piloted in four research centres in two different European countries; quality and performance of the proposed techniques will be tested and validated in two different use cases: lung cancer (represented in the consortium by Universidad Politecnica De Madrid and Spanish Lung Cancer Group) and Alzheimer’s disease (represented by St George’s, University of London  and Alzheimer’s Research UK). The different nature of these two diseases, will give the possibility to prove the generality and adaptability of the proposed integrated platform. The evaluation of the quality of the integrated data, and the discovered novel associations and patterns, will provide strong evidences of the success of the IASIS system. 

Analysing the efficiency of patient pathway management both at primary care (prevention and early detection) and secondary care.

The IASIS platform will make available Web services for managing, consuming, and analysing the IASIS integrated knowledge base. Data management services will enable the retrieval of relevant patient information in a holistic manner. In addition, high-level analytics will allow for a descriptive analysis of the main characteristics of the patients, as well as for the detection of patterns between patient conditions, genetic variations, and treatment effects that will allow us to find potential novel associations, i.e., drug-gene and phenotype-genotype relations. The validation of these discoveries will provide not only the basis for the definition of public health policies that will positively benefit the patient quality of life, but also will empower clinicians with the knowledge for earlier detection of patient conditions and complications. 

Aligning big data and advanced simulation methods in order to provide high-leverage policy analysis for public health officials, across a range of epidemiology challenges.

The IASIS platform will make available Web services for predictive and prescriptive analytics that allow for the forecast and explanation of patient conditions and treatment effectiveness. Moreover, these computational methods, in conjunction with the properties of big data integrated in the knowledge base, will enable public health officials to explore the characteristics of the descriptive epidemiology of diverse diseases, e.g., lung cancer and Alzheimer’s disease. These features will result in the definition and modification of public health policies that will potentially impact on the epidemiology of these diseases. 

Cross-border and networking coordination and technology integration facilitates interoperability among the components of Big Data value chain.

The IASIS consortium is an EU-level initiative that integrates partners from four different countries, requiring a high degree of multidisciplinarity and interdisciplinarity to exploit all the potential of the contributions of each partner. Data provided from the IASIS partners and collaborators is heterogeneous and dissimilar, e.g., data is presented in different formats and languages, and rich patient information is expressed in free-text narratives and medical images. 

The IASIS platform will implement data integration and extraction techniques for solving these issues and ensuring interoperability across all the layers of the IASIS architecture. IASIS will design a unified schema and implement an integrated knowledge base, as well as linked data infrastructure to give the possibility to connect and integrate all these disperse sources of data. Moreover, novel data extraction techniques will be implemented to extract relevant knowledge from free-text narratives and medical images in the clinical datasets. In addition, interoperability across data of different languages will be possible; for example, for IASIS pilot in lung cancer, multilingual data from both Spanish and English will be used and integrated.