Data Analytics
Download as PPT, PDF4 likes752 views
This document discusses the promise and challenges of data analytics in healthcare and biomedical research. It notes that we are at a point of deception, where digitization is disrupting traditional models through increased data volume, velocity and variety. The document outlines NIH's Big Data to Knowledge initiative to accelerate biomedical discovery through open data sharing and improved analytics. Precision medicine is highlighted as one area that could see major breakthroughs through these approaches. Challenges around data standards, privacy, workforce needs and demonstrating value are also discussed.
Data Analytics
- 1. Data Analytics Philip E. Bourne, PhD, FACMI Associate Director for Data Science National Institutes of Health UM iSchool November 3, 2015
- 2. Pre-reading Health Informatics: Practical Guide for Healthcare and Information Technology Professionals Chapter 3 Healthcare Data Analytics William Hersh
- 3. This is a Conversation NOT a Lecture
- 4. We Have Been Successful World Climate Report 2011 http://www.cnet.com/news/china-unseats-u-s-in-supercomputer-ranking/
- 5. Why Now?
- 6. Harnessing Data to Improve Health: BD2K (Big Data to Knowledge) NIH’s 6-year initiative to use data science to foster an open digital ecosystem that will accelerate efficient, cost-effective biomedical research to enhance health, lengthen life, and reduce illness and disability Programs and activities: Advance discovery for biomedical research Facilitate use and re-use of biomedical data Develop analytical methods and software Enhance biomedical data science training
- 7. Big Data in the Life Sciences … This speaks to something more fundamental that more data … It speaks to new methodologies, new skills, new emphasis, new cultures, new modes of discovery …
- 8. The History of Computational Biomedicine According to Bourne 1980s 1990s 2000s 2010s 2020 Discipline: Unknown Expt. Driven Emergent Over-sold A Service A Partner A Driver The Raw Material: Non-existent Limited /Poor More/Ontologies Big Data/Siloed Open/Integrated The People: No name Technicians Industry recognition data scientists Academics Searls (ed) The Roots in Bioinformatics Series PLOS Comp Biol
- 9. Consider what the expert prophets are saying …
- 10. We are at a Point of Deception … Evidence: – Google car – 3D printers – Waze – Robotics – Sensors From: The Second Machine Age: Work, Progress, and Prosperity in a Time of Brilliant Technologies by Erik Brynjolfsson & Andrew McAfee
- 11. Example - Photography Digitization Deception Disruption Demonetization Dematerialization Democratization Time Volume,Velocity,Variety Digital camera invented by Kodak but shelved Megapixels & quality improve slowly; Kodak slow to react Film market collapses; Kodak goes bankrupt Phones replace cameras Instagram, Flickr become the value proposition Digital media becomes bona fide form of communication
- 12. We Are At a Point of Deception The 6D Exponential Framework Digitization of Basic & Clinical Research & EHR’s Deception We Are Here Disruption Demonetization Dematerialization Democratization Open science Patient centered health care
- 13. What Are Some General Implications of Such a Future? Open collaborative science becomes of increasing importance The value of data and associated analytics becomes of increasing value to scholarship Opportunities exist to improve the efficiency of the research enterprise and hence fund more research Current training content and modalities will not match supply to demand Balancing accessibility vs security becomes more important yet more complex
- 14. An Example of That Promise: Comorbidity Network for 6.2M Danes Over 14.9 Years Jensen et al 2014 Nat Comm 5:4022
- 16. “And that’s why we’re here today. Because something called precision medicine … gives us one of the greatest opportunities for new medical breakthroughs that we have ever seen.” President Barack Obama January 30, 2015
- 17. Precision Medicine Initiative National Research Cohort – >1 million U.S. volunteers – Numerous existing cohorts (many funded by NIH) – New volunteers Participants will be centrally involved in design and implementation of the cohort They will be able to share genomic data, lifestyle information, biological samples – all linked to their electronic health records
- 19. Center of Excellence for Mobile Sensor Data-to-Knowledge (MD2K) Santosh Kumar, Ph.D. Director, MD2K Center of Excellence Professor & Moss Chair of Excellence in Computer Science University of Memphis https://datascience.nih.gov/bd2k/funded-programs/centers
- 20. MD2K Applications – CHF and Smoking
- 21. Strategic Areas Sustainability Workforce Development & Diversity Discovery & Innovation Policy & Process Leadership Research Objects in the Commons Voxel Wide Genome Scanning MRI standardization Over 100 Public Lectures Collaboration with a Minority Institution 185 Institutions Involved Genomic Data Sharing Policy Example: BD2K Center Working Across Strategic Areas
- 22. BD2K Targeted Software Topics Supports innovative analytical methods and software tools that address critical current and emerging needs of the biomedical research 2015 Topics (18 awards, U01s) – Data Compression – Data Provenance – Data Visualization – Data Wrangling 2016 Topics (U01s, under review) – Data Privacy – Data Repurposing – Applying Metadata – 2016: Crowdsourcing and interactive Digital Media (UH2)
- 23. Goal: To strengthen the ability of a diverse biomedical workforce to develop and benefit from data science
- 24. Key Chapter Points Provenance Proof of the value of analytics is still forming Work force - shortage
- 26. I not only use all the brains I have, but all I can borrow. – Woodrow Wilson
- 27. The Team 27
- 28. NIHNIH…… Turning Discovery Into HealthTurning Discovery Into Health [email protected] https://datascience.nih.gov/ http://www.ncbi.nlm.nih.gov/research/staff/bourne/
Editor's Notes
- #7: Updated by ADDS group 8/25/15
- #15: 16 million hospital inpatient events (24.5% of total), 35 million outpatient clinic events (53.6% of total) and 14 million emergency department events (21.9% of total
- #17: Photos: FC tweet; RK screen grab
- #18: Images of people from Infographic (NOTE: Image is just a placeholder—Jill will tweak) Detailed Notes: National Research Cohort <<OR name of study>> >1 million U.S. volunteers committed to participating in research Will combine a number of existing cohorts Will include Dept of Veterans Affairs Million Veteran Program—note Veteran is singular per http://www.research.va.gov/MVP/
- #22: Detected 8 genetic variants influencing volume of brain structures to provide insight into brain development and neuropsychiatric dysfunction. MRI images from >30,000 people Meta-analysis of GWAS data from >13,000 people Replicated results with data from >17,000 people Designed standardized protocols for image analysis, quality assessment, genetic imputation, and association. Developed 3D models for 1,500 subjects Used freely available software for measurements
- #24: Short term: produce a searchable catalog of physical and virtual courses; Funding diversity awards to work with BD2K Centers; Expand IRP training started Jan 2015 e.g. Software carpentry and Train the trainers Long term: evaluation