Abstract: A critical goal in precision medicine is to identify patient subgroups based on their characteristics, and to design targeted interventions for improving health outcomes. Here we describe a generalizable method for the identification, replication, visualization, and interpretation of patient subgroups through the use of bipartite networks applied to the problem of unplanned hospital readmission. The results have implications for designing targeted interventions and improving predictive modeling.
Learning Objective 1: Identification, replication, visualization, and interpretation of patient subgroups through the use of bipartite networks.
Learning Objective 2 (Optional): Challenges and solutions for visualizing large datasets.
Learning Objective 3 (Optional): Understand implications of methodology to precision medicine and predictive modeling.
Suresh Bhavnani (Presenter)
Yu-Li Lin, University of Texas Medical Branch
Laxminarasimha Chennuri, UTMB
Julianna Borres, University of Texas Medical Branch
Tianlong Chen, UTMB
Yong-Fang Kuo, University of Texas Medical Branch