The importance of interpretability and visualization in ML for medical applications

摘要: Many areas of science have made a sharp transition towards data-dependent methods, enabled by simultaneous advances in data acquisition and the development of networked system technologies. This is particularly clear in the life sciences, which can be seen as a perfect scenario for the use of machine learning to address problems in which more traditional data analysis approaches might struggle. But this scenario also poses some serious challenges. One of them is the lack interpretability and explainability for complex nonlinear models. In medicine and health care, not addressing such challenge might seriously limit the chances of adoption of these methods. In this summary paper, we pay specific attention to one of the ways in which interpretability and explainability can be addressed in this context: data and model visualization