Despite remarkable progress in the management of cardiovascular disease (CVD), major unmet needs remain with regard to mortality, hospitalisations, quality of life (QoL), healthcare expenditures and productivity. Acute coronary syndrome (ACS), atrial fibrillation (AF) and heart failure (HF) are major and growing components of the global CVD burden. Optimal management of these conditions is complicated by their complex aetiology and heterogeneous prognoses. Poor definition at the molecular level and co/multi-morbidities form major challenges for the development and delivery of targeted treatments. This renders response to therapy unpredictable, with large inter-individual variation and, importantly, small or undetectable treatment effects in large trials of unselected patients. Today’s treatment guidelines still reflect the scientific constraints of an earlier era where clinical markers to guide therapy are limited to conventional risk factors and end-organ damage, and where the main endpoint in clinical trials is patient death. Hence, drug development pipelines from early target validation through to late post-marketing work have proven to be slow, expensive and high-risk: the chance of eventual approval for a CVD drug candidate in Phase I trials is 7%, the lowest of any disease category (shared with oncology) 2. Moreover, tolerability of medication and adherence to treatment show wide variations. There is thus a need for better definition of these diseases, their markers and endpoints (including better segmentation of current heterogeneous patient groups acknowledging underlying mechanisms and comorbidities) and of their outcomes/prognoses (including functional capacity and quality of life [QoL]). BigData@Heart’s ultimate goal is to develop a Big Data--driven translational research platform of unparalleled scale and phenotypic resolution in order to deliver clinically relevant disease phenotypes, scalable insights from real-world evidence and insights driving