Ph.D., Associate Professor, Medical University of South Carolina
Lewis Frey, Ph.D., has focused on methods of data integration and analysis for the purpose of discovery. Specifically, he has examined the use of sequential event data in the electronic health record for determining trajectories of care related to outcome. The analysis includes clustering of high-risk groups of patients based on comorbidities to project near term outcomes such as readmission. Novel analysis of integrated heterogeneous data provides opportunity for discovery and improved patient care through bench-to-bedside translational research. He is leading the development of big data methodologies applied to the Veterans Affairs Informatics and Computing Infrastructure (VINCI). The goal is to create a system for distributable clinical, personalized, pragmatic predictions of outcomes (Clinical3PO) with easy deployment of preconfigured virtual machines.
Clinical Dx Showcase: C3PO Protocols for Predictive Analytics
At the Medical University of South Carolina (MUSC) we have implemented a research big data solution for precision medicine. Through a National Institute of Health funded project we developed an open source big data research platform, Clinical Personalized Pragmatic Predictions of Outcomes (C3PO), which has been deployed within the Veterans Affairs Informatics and Computing Infrastructure (VINCI), at Medical University of South Carolina (MUSC) and at Christiana Care Health Systems in Delaware. The VA deployment has focused on predictive analytics around type 2 diabetes on a national scale to predict outcomes of patients. At MUSC we have built a predictive model of readmission that has been demonstrated to reduce hospitalization by wrapping care management services around the patient at the clinic level. The virtualization of C3PO has enabled us to replicate and extend the research at MUSC to a larger population of 80,000 patients at Christiana Care and demonstrate the generalizability of our models