Abstract: I show how combining artificial intelligence with opinions from groups of physicians can diagnose skin cancer more accurately than either approach alone. I will also present recent work expanding these results using the DiagnosUs mobile application for crowdsourced biomedical image analysis.
Speaker Bio: Erik Duhaime is a PhD candidate in Work and Organization Studies at the MIT Sloan School of Management. My research uses experiments, simulations, and big data analysis to ask why, how, and when groups can be more than the sum of their parts. I tackle this question through two broad streams of research: one focused on behavioral decision making and group dynamics, and the other on how information technologies enable new methods of group decision making and problem solving.