Published on March 29, 2014
1 Big Data in Health: The Global Burden of Disease Study Peter Speyer @peterspeyer March 29, 2014
Big data in health 2 • Surveys • Censuses • Disease registries • Vital registration • Verbal autopsy • Mortuaries / burial sites • Police records Variety Volume Velocity • Hospital / ambulatory / primary care records • Claims data • Surveillance systems • Administrative data • Literature reviews • Sensor data • Social media • Quantified self
IHME input data cataloged in the GHDx 3
From data to impact 4 Big data Audiences 1. Data access 2. Data preparation 3. Data analysis 4. Data translation Getting relevant data in useful formats to the right audiences
Example: Global Burden of Disease Study • A systematic scientific effort to quantify the comparative magnitude of health loss due to diseases, injuries and risk factors • GBD 2010 results published in The Lancet in 2012 – 291 causes, 67 risk factors – 187 countries – 1990-2010 – By age and sex • GBD 2013 Update in process 5
1. Accessing the data • Systematic identification of all relevant data sources – Data Indexers – Lit reviews • Challenges – Data on paper, PDF, proprietary & obsolete formats – Patient / participant consent – Confidentiality / de-identification – Cost 6 Tristan Schmurr / Flickr CC Chapman / Flickr
2. Preparing data for analysis • Data extraction (databases, tables, papers) • Analysis of microdata • Correction for bias • Data quality issues, e.g. garbage codes • Cross-walks, e.g. between ICDs 7
Demo: Tobacco Viz 8
3. Analyzing data • Use all available data – Use covariates: indicators related to quantity of interest • Test the modeling approach, e.g. predictive validity testing (CODEm) • Apply appropriate corrections, e.g. causes of death to match all-cause mortality • Quantify uncertainty • Review: 1000+ experts, peer-reviewed publication
4. Data translation 10 • Academic papers • Policy reports • Data search engine • Data visualizations – Input data – Comprehensive results – Key insights
Visualization demos 11
Calcification Inhibitors in CKD and Dialysis Patients
Gautam Siwach engaged at Tackling the challenges of Big Data by MIT Computer ... data sets. In health ... a big amount of scientific data; ...
Learn about big data and how IBM can help you use big data to achieve big ... Get started with big data and ... Take the next step with IBM Big Data ...
Access free Gartner research and webinars on the latest Big Data and Analytics opportunities and challenges for businesses in 2016.
Why Is Big Data Important? The importance of big data doesn’t revolve around how much data you have, but what you do with it. You can take data from any ...
... tracking epidemiologicaldata, or other methods of data collection-Health ... Introduction to Health Education and Health ... Global health;
Big data is new and “ginormous” and scary –very, very scary. No, wait. Big data is just another name for the same old data marketers have ...
... analysis and advice on big data ... and current Customer of IBM Global ... SaneIT, That was a lot of insight stuffed into one report on the health ...
Big data is an evolving term that describes any ... Big Data skills; Get more resources on big data in this ... Step-by-step guide to acing your ...
With big data analytics, ... embraced the power of collecting and analyzing data. That’s a great first step, ... To get the most out of your data, ...
How President Obama’s campaign used big data to ... reforming the health ... An experimental program would use those steps to develop a range of ...