iASiS: Big Data to Support Precision Medicine and Public Health Policy

iASiS envisions the transformation of clinical, biological and pharmacogenomic big data into actionable knowledge for personalized medicine and decision makers. This is achieved by integrating and analyzing data from disparate... [ view full abstract ]

iASiS envisions the transformation of clinical, biological and pharmacogenomic big data into actionable knowledge for personalized medicine and decision makers. This is achieved by integrating and analyzing data from disparate sources, including genomics, electronic health records, and bibliography. The integration and analysis of these heterogeneous sources of information enables the best decisions to be made, allowing for diagnosis and treatment to be personalized to each individual. iASiS offers a common representation schema for the heterogeneous big data sources. Data resources for two different disease categories are explored: lung cancer (LC) and Alzheimer's disease (AD). Methods: The iASiS infrastructure converts clinical notes into usable data, combines them with genomic data, related bibliography, image data and more, and creates a global knowledge graph. The iASiS knowledge graph facilitates the use of big data analytics in order to discover useful patterns and associations across different resources. Employing novel inference techniques, the iASiS knowledge graph leads to the generation of new knowledge, by combining pieces of information that may not be apparent when examining each source separately. The final iASiS system will be a uniquely rich and up-to-date source of information, which would otherwise be fragmented into different sources. Results: The initial iASiS components tested against a rich data set of biomedical literature comprising more than 100,000 textual AD related sources yielded interesting initial results. In particular, when asked to provide appropriate treatment for AD patients based on the patients’ genetic (allelic) status, the system identified alleles of risk with related treatments according to the current bibliography. Regarding LC, analysis on more than 170,000 clinical notes and 7,000 clinical reports from 706 patients revealed correlations between presence of risk factors, such as dyslipidemia, high blood pressure, smoking habit and COPD, and significant decrease in survival. Survival in females was significantly higher than in males, despite the smoking habit, stage and comorbidities. Discussion: iASiS will allow the generation of knowledge that will support precision medicine and more effective treatments for different diseases. The outputs from iASiS will have significant impacts on healthcare systems, ICT industry, individual patients and wider society.