Principal Investigator: Dr Carsten Dietrich
Siemens Healthcare GmbH, Erlangen, GermanyTags: 49398, data-analytics, data-integration, patient stratification, Precision Medicine, prognosis, risk prediction
Due to recent breakthroughs in molecular diagnostics and imaging, the amount of clinically relevant data is constantly growing. As a result, medicine and healthcare are drifting towards being ‘big data’ disciplines. Precision medicine refers to the idea of delivering the right treatment to the right patient at the right time. In order to enable precision medicine and to improve the quality of healthcare in the future, we need methods that integrate complex and heterogeneous clinical data and translate it into actionable clinical knowledge.
This study aims to tackle both requirements. We start with bringing the different types of data provided by the UK Biobank in context with each other and with existing biological and clinical knowledge from public databases. For instance, to assess the association of genetic variants with a specific clinical outcome, single nucleotide variants will be considered both in their biological context – e.g. affected genes, biological pathways and known implications for health and disease – as well as their clinical context – e.g. other physical measures and patient socio-demographics and lifestyle.
This will allow us to gain a more holistic view on specific clinical pictures and to then develop machine learning algorithms that are particularly suited to leverage this contextual information and the rich relationships between single data entities for supporting clinical decision making – e.g. assessing the risk of developing a certain disease or discovering new disease endotypes.