In today’s ever evolving data ecosystem it is evident that data generated for a wide range of purposes unrelated to biomedicine possess tremendous potential value for biomedical research. Analyses of our Google searches, social media content, loyalty card points and the like are used to draw a fairly accurate picture of our health, our future health, our attitudes towards vaccination, disease outbreaks within a county and epidemic trajectories in other continents. These data sets are different from traditional biomedical data, if a biomedical purpose is the categorical variable. Yet the results their analyses yield are of serious biomedical relevance. This paper discusses important but unresolved challenges within typical biomedical data, and it explores examples of non-biomedical Big Data with high biomedical value, including the specific conundrums these engender, especially when we apply biomedical data concepts to them. It also highlights the “digital phenotype” project, illustrating the Big Data ecosystem in action and an approach believed as likely to yield biomedical and health knowledge. We argue that to address the challenges and make full use of the opportunities that Big Data offers to biomedicine, a new ethical framework taking a data ecosystem approach is urgently needed. We conclude by discussing key components, design requirements and substantive normative elements of such a framework.