Causal inference algorithms for mixed data and applications to Precision Medicine
The Benos’ group develops computational, machine learning methods to address important questions in medicine. We are interested in identifying the factors that affect chronic disease onset and progression and cancer survival. We also develop predictive methods and tools that can directly improve health. To do so, we use probabilistic graphical models and other machine learning methods that can integrate and mine high-dimensional, multi-modal data. In this presentation we will show some recent advances in the area of causal modeling over mixed data and their applications in diseases such as chronic obstructive pulmonary disease (COPD) and cancer.