Semi-hypothesis guided exploratory analysis for biomedical applications

Abstract

Medical research and clinical trials are often based on hypotheses that were observed from clinical practice with noticeable evidence. Forming clinically significant hypotheses will greatly benefit the success of clinical research and ensure both external and internal validity of the trial. In this talk, I will introduce a knowledge discovery approach to automatically identify populations of subjects with commonly occurred comorbidities, genotypes, and phenotypes that present statistically high contract between populations. To focus on a confined set of medical problems as most of medical researchers would like to target (hypertension and diabetes versus all chronic diseases), this approach is able to take a set of selected attributes of interest and expand knowledge discoveries from the initial set. The computational approach consists of a forward floating search method for population selection, a hierarchical frequent pattern mining tree to efficiently handle dense associations, contrast mining for identifying actionable plans, and accumulated contrast (ac-)index for ranking mining results for biomedical researchers. I will present exploratory analysis process and results from the Simon's Simplex Collection (SSC) by the Simons Foundation Autism Research Initiative (SFARI) which comprises data representing 11,560 individuals from 2,591 families. Putative autism subtypes were explored by partitioning families based on demographics and autism phenotypes. An extended contrast mining procedure identified genetic combinations showing preferential association for one of the contrasted subgroups, emphasizing combinations novel to the autistic proband within each family tree. Potentials for other biomedical applications will also be discussed.