Speaker: Beata Puncevic from Blue Cross Blue Shield of Michigan
Big data, data science and analytics have the potential to radically change how healthcare services are delivered and improve patient health. In this possible future: – Consumers will become empowered to make informed healthcare choices – Providers will deliver outcome-based care that is designed for individual patient needs – Insurance companies will create products that are proven to improve member health, engage customers through better consumer experience, and optimize operations – Pharmaceuticals will use predictive modeling of biological processes and drugs, improve selection of trial patients and minimize risk while improving drug effectiveness Insurance companies and providers are critical components in the healthcare supply chain. Despite this potential, encumbered by complex legacy architectures and processes and held back by low R&D budgets, these players have been slow to embrace the new architectures that can make the future possible. With the healthcare industry being pressured from all sides of the business model, the time to adapt is now. However, the path forward for these organizations must be uniquely suited to be successful given their current state and priorities. This talk is about a case study on the business strategy, technology architecture powered by Hortonworks Hadoop and implementation approach that can be a recipe for success.
Speakers: Vamshi Punugoti from and Bryan Lari from MD Anderson Cancer Center
The University of Texas MD Anderson Cancer Center is one of the world’s most respected centers devoted exclusively to cancer patient care, research, education and prevention. As an organization that is fairly new to the HDP eco-system, the team has gone through its share of trials and tribulations. In this session, MD Anderson team members will share their approach to starting the journey, related experiences and lessons learned focusing primarily on the important interactions between people, processes and technologies. This session is designed for Summit attendees from hospitals, pharmaceutical companies, and research universities who are looking for ways to begin or accelerate their Hadoop journey.
Speaker: Jay Etchings from Arizona State University
Expression quantitative trait loci (eQTL) is a method of studying the effects of genomic variations on gene expression. The quantitative trait thus being measured is the gene expression. Genomic variations in this study were single nucleotide polymorphisms (SNPs) measured using genotyping arrays in TCGA breast cancer samples. Previously, PLINK had been used to run basic association between SNPs and gene expression on eQTL datasets. PLINK is an open source population genetics tool with capabilities for running the various statistical test on large data sets within legacy HPC systems. The movement of this method to Hadoop has not only increased efficiency but has enabled a queriable data source and a visual pipeline where precision medicine merges with genomic science.