Biostatistics and Medical Informatics Department Seminar with Quefeng Li (University of North Carolina

Multimodal statistical models have gained attention in recent years, yet there lacks rigorous statistical inference tools for inferring the significance of a single modality within a multimodal model. Dr. Li will propose a novel entropy-based metric - expected relative entropy - to quantify the information gain of one modality in addition to all other modalities in the model. Such a tool is using for making personalized treatment recommendations based on individual patient profiles.