Bio:In the current data-rich healthcare environment, our capacity to collect vast amounts of longitudinal, multimodal, multiscale data needs to be matched with a comparable ability to transform this data into knowledge that enables precision health. I direct the Integrated Diagnostics Shared Resource, an interdepartmental resource that is prospectively collecting and curating clinical, imaging, and molecular data to improve the detection and characterization of early-stage cancer. My research lab focuses on the systematic integration of data from multiple sources and biological scales to enhance the performance and trustworthiness of clinical prediction models. We develop computational tools that harness this multimodal, multiscale data to aid physicians with formulating timely and accurate management strategies for individual patients. We devise unique approaches for efficiently representing this data, applying and validating artificial intelligence/machine learning algorithms to reliably extract patterns, and interpreting these patterns to understand disease progression better. We work on problems related to data wrangling, knowledge representation, machine learning, and interpretation and utilize a wide spectrum of techniques from statistical approaches to machine and reinforcement learning, depending on the problem at hand.