1 / 11

Dynamic Network Approach to Health Surveillance

Dynamic Network Approach to Health Surveillance. Prof. Kathleen M. Carley kathleen.carley@cs.cmu.edu. Early Warning and Disease Mapping. Understanding the general state of health in a community is critical for rapid and effective response Disaster Response Early Indicators Forecasting

artan
Download Presentation

Dynamic Network Approach to Health Surveillance

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Dynamic Network Approach to Health Surveillance Prof. Kathleen M. Carley kathleen.carley@cs.cmu.edu

  2. Early Warning and Disease Mapping • Understanding the general state of health in a community is critical for rapid and effective response • Disaster Response • Early Indicators • Forecasting • Various types of sensors are often used to provide early indications of medical conditions • water usage • OTC drug purchases

  3. Bio-War Features Agents move in networks which influence what they do, where, with whom, and what they know, what diseases they get, when, how they respond to them, etc. Major difference in network and disease effects based on race, gender and age. • Input • Census data – social and organizational • School district data • Worksite and entertainment locations & size • Hospitals and clinics locations & size • Social Network characteristics from census • IT communication procedures & access • Wind characteristics • Spatial layout of city • Disease models • Influenza, small pox, anthrax, … • Illustrative Output • Over the counter drug sales • Insurance claim reports (Dr. visits) • Emergency room reports • Absenteeism (school and work) • Web access and medical phone calls • In-house questionnaires

  4. Networks & Cyber networks Social Network Cyber Network

  5. haiti.ushahidi.com • Earthquake Jan 12, 2010 • 2,471 reports posted as of Feb 7, 2010 • 6 categories of classification • Over 25 subcategories • Text, pictures, & video Where do first responders start? 12 Jan 2010 photo posted to http://haiti.ushahid.com

  6. Haiti Semantic Network (9 or more tweets) HELP

  7. Density Medical Categories in Ushahidi Over Time

  8. Influenza – The “Gold” Standard • Typical data sources • Viral Surveillance (specimens) • Mortallity • Influenza associated pediatric deaths • Influenza associated hospitalization • Outpatient illness (office/clinic visits) http://www.cdc.gov/flu/weekly/

  9. Google Flu Trends • Typical data sources • Country provided data • Search term based hits http://www.google.org/projects.html http://www.google.com/publicdata

  10. News And TweetsApproximately 4-5 day lead

  11. Key Lessons • Some medical information in social media – but inconsistent • Key challenges • Operate at the symptom level … and many things look like flu • Data cleaning to improve signal • Identifiers for other than flu and disaster related medical needs • Geospatial tracking • Integration across media • Volatile state of social media • Country specific social media technologies • Change in usage • Change in technology • Future direction • Linking demographics and medical information • Auto-instantiation of simulation for forecasting

More Related