Big Data for Precision Medicine
Turn clinical and pharcogenomics Big Data into knowledge in a way that unknown patterns can be unrevealed. Two main life-threatening diseases are considered: Lung cancer and the Alzheimer’s disease. Big data collected from heterogeneous data sources is integrated into a knowledge graph and knowledge discovery and prediction techniques on top of the knowledge graph allow for the discovery of patterns for supporting precision medicine and health policy making.
Precision medicine promises to transform the delivery of healthcare to patients. Healthcare is evolving from a reactive “one-size-fits-all” system towards a system of predictive, preventive, and precision care. A personalised medicine approach is expected to lead to better health outcomes, improved treatments, and reduction in toxicity due to variable or adverse drug responses.
The goal of Project IASIS is to seize the opportunity provided by a wave of data heading our way and turn this into actionable information that would match the right treatment with the right type of patient. A current challenge is that there are large, heterogeneous sets of data ranging from different sources, which if combined would enable the best decisions to be made, allowing for diagnosis and treatment to be personalised to each individual. IASIS is testing this approach in two disease areas – lung cancer and Alzheimer’s disease – but with the longer-term ambition that this approach will be more widely applicable to other disease areas.