This talk describes an instance-specific causal Bayesian network (CBN) learning method that searches the space of CBNs to build a causal model that is specific to an instance (e.g., a patient). The search is guided by attributes of the given instance (e.g., patient symptoms, signs, lab results, and genotype). We describe the results of applying the method to molecular cancer data to estimate the gene alterations (e.g., gene mutations) that are driving the cancerous behavior of individual tumors, which are the instances in this application.
Asthma is a major cause of healthcare costs in children, particularly in the high-risk subgroup, Puerto Ricans. We aim to identify susceptibility genes for asthma in Puerto Ricans. We conducted GWAS and EWAS of asthma. We also conducted mQTL, eQTL and eQTM analyses to test for association between the top SNPs and DNA methylation and gene expression in nasal epithelium. We identified multiple SNPs, CpG sites and expressed genes associated with asthma.
I plan to make the argument that we should use behavioral science principles when building quality improvement tools for physicians. I will discuss my research on the problem of trauma triage (an archetypal time-sensitive problem that occurs under conditions of uncertainty), with a brief digression to provide a primer on behavioral science, and sharing our efforts to use theoretically-based video games to recalibrate physician heuristics (intuitive judgments) in trauma.
Join from your computer or phone: