Crowdsourcing in Biomedical Research: Tapping on the Wisdom of Crowds to Improve the Accuracy of Mammography Screening

Abstract

The generation of large-scale biomedical data is creating unprecedented opportunities for basic and translational science. Crowdsourcing the analysis of complex and massive data in the form of scientific competitions, known as Challenges, has emerged as a new way of doing data science in which validation of the methods is automatically addressed. Challenges also encourage open innovation and create collaborative communities. I will discuss different aspects of the organization and lessons learned in the Digital Mammography DREAM Challenge.