Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Evolve: InSTEDD's Global Early Warning and Response System

2,235 views

Published on

American Medical Informatics Association (AMIA) Spring Congress, Walt Disney World Swan, May 28th–30th, 2009, Orlando, Florida, USA

  • Okay I'll keep that in mind, also...GROW YOU DOWNLINE FAST - Works with any mlm. Have dozens joining whatever mlm your doing today! Go to: www.mlmrc.com
       Reply 
    Are you sure you want to  Yes  No
    Your message goes here
  • Be the first to like this

Evolve: InSTEDD's Global Early Warning and Response System

  1. 1. EVOLVE: INTEGRATED GLOBAL EARLY WARNING AND RESPONSE SYSTEM Innovative Support to Emergencies, Diseases, and Disasters Photo credit: IRMA (Integrated Risk Management for Africa) AMIA Spring Congress Walt Disney World Swan May 28 th –30 th , 2009, Orlando, Florida, USA Taha Kass-Hout, MD, MS Director, Global Public Health and Informatics
  2. 2. Overview <ul><li>Infectious disease events represent substantial morbidity , mortality , and socio-economic impact </li></ul>
  3. 3. Late Detection – Response DAY CASES Opportunity for control
  4. 4. Early Detection and Response DAY CASES Opportunity for control
  5. 5. Public Health Measures 1000 Malaria infections (100%) 50 Malaria notifications (5%) Specificity / Reliability Sensitivity / Timeliness <ul><ul><li>Main attributes </li></ul></ul><ul><ul><ul><li>Representativeness </li></ul></ul></ul><ul><ul><ul><li>Completeness </li></ul></ul></ul><ul><ul><ul><li>Predictive value positive </li></ul></ul></ul>Get as close to the bottom of the pyramid as possible Urge frequent reporting: Weekly  daily  immediately
  6. 6. Public Health Measures Time <ul><ul><li>Main attributes </li></ul></ul><ul><ul><ul><li>Timeliness </li></ul></ul></ul>Health care hotline Signal as early as possible
  7. 7. <ul><li>One of four major initiatives of the UN Millennium Action Plan (2000) </li></ul><ul><ul><li>mHealth for Development: The Opportunity of Mobile Technology for Healthcare in the Developing World (2009) </li></ul></ul>Making Mobile Tech Work for Health Photo Source: UN Foundation
  8. 8. Making Mobile Tech Work for Health Avian Influenza Exercise: Stung Treng Province, Cambodia, October 13-15, 2008 SE Asia Region (Source: Wikipedia) The Komphun rural Health Center serves over 7000 population in the Stung Treng and neighboring provinces. Cell phone use during the Avian Influenza Exercise: Stung Treng Province, Cambodia, October 13-15, 2008
  9. 9. Growth of Mobile Technologies Adapted from Dzenowagi, WHO, 2005
  10. 10. <ul><ul><li>Internet penetration levels among the population as a whole </li></ul></ul><ul><ul><ul><li>India 5.2% </li></ul></ul></ul><ul><ul><ul><li>Malaysia 59.0% </li></ul></ul></ul><ul><ul><ul><li>Thailand 20.5% </li></ul></ul></ul><ul><ul><ul><li>Myanmar 0.1% </li></ul></ul></ul><ul><ul><li>This compares to about 73.6% for North America </li></ul></ul><ul><ul><ul><li>Some countries in Asia are also shown to be high such as Japan, S. Korea, Taiwan and Hong Kong </li></ul></ul></ul>Internet Penetration in Asia Pacific Nigel Collier, BioCaster: http://biocaster.nii.ac.jp Data Source: http://www.internetworldstats.com/stats3.htm#asia
  11. 11. Urban – Rural Population, SE Asia UNCTAD Handbook of Statistics 2004 Adapted from Dzenowagi, WHO, 2005 Year: 2002
  12. 12. Our Approach <ul><li>Hybrid human and machine-based </li></ul><ul><li>Collaborative and cross-disciplinary </li></ul><ul><li>Web 2.0/3.0 (geo-semantic) platform </li></ul>
  13. 13. Information Sources <ul><li>Event-based ad-hoc unstructured reports issued by formal or informal sources </li></ul><ul><li>Indicator-based (number of cases, rates, proportion of strains…) </li></ul>Timeliness, Representativeness, Completeness, Predictive Value, Quality, …
  14. 14. Evolve Architecture and Processes Best Poster Award for Improving Public Health Investigation and Response at the Seventh Annual ISDS Conference, 2008 http://kasshout.blogspot.com/2008/12/best-poster-award-for-improving-public.html
  15. 15. Evolve Architecture and Processes Feature extraction, reference and baseline information Tags Multiple Data Streams User-Generated and Machine Learning Metadata Comments Spatio-temporal Flags/Alerts/Bookmarks Evolve Bot Event Classification, Characterization and Detection Previous Event Training Data Previous Event Control Data Metadata extraction Machine learning Social network Professional feedback Anomaly detection Collaborative Spaces Hypotheses generation esting
  16. 16. Evolve Related items (e.g., News articles) are grouped into a thread. Threads are later associated with events (hypothesized or confirmed). Collaborative-centric semantic tags Expert-generated semantic tags Publish and Share Information Create a filter (by keyword, tag, topic, location, or time) and subscription (email, GeoRSS, SMS Text Messaging, Twitter, etc.) An event is monitored through a thread of items Data source: SE Asia Evolve Collaborative Workspace http://riff.instedd.org/space/ProMed-MBDS List view Yin Myo Aye, MD: ProMED MBDS Taha Kass-Hout, MD, MS: InSTEDD
  17. 17. Evolve Expert-centric auto-generated (machine-learning) semantic tags and related items Data source: SE Asia Evolve Collaborative Workspace http://riff.instedd.org/space/ProMed-MBDS Tags are semantically ranked (a statistical possibility match). Users can further train the classifier by rejecting a suggestion. Users can also train the geo-locator by rejecting or updating a location . Yin Myo Aye, MD: ProMED MBDS Taha Kass-Hout, MD, MS: InSTEDD
  18. 18. Evolve Map view Data source: SE Asia Evolve Collaborative Workspace http://riff.instedd.org/space/ProMed-MBDS Semantic map to monitor topic rise or decay over time Yin Myo Aye, MD: ProMED MBDS Taha Kass-Hout, MD, MS: InSTEDD
  19. 19. Evolve Filter feature which automatically filters content by topic of interest Filter content by radius Data source: SE Asia Evolve Collaborative Workspace http://riff.instedd.org/space/ProMed-MBDS Yin Myo Aye, MD: ProMED MBDS Taha Kass-Hout, MD, MS: InSTEDD
  20. 20. Automatic Classification <ul><li>Current classification includes: </li></ul><ul><ul><li>7 syndromes </li></ul></ul><ul><ul><li>10 transmission modes </li></ul></ul><ul><ul><li>> 100 infectious diseases </li></ul></ul><ul><ul><li>> 180 micro-organisms </li></ul></ul><ul><ul><li>> 140 symptoms </li></ul></ul><ul><ul><li>> 50 chemicals </li></ul></ul>
  21. 21. Indicators and Insights <ul><li>Approximations of Epidemiological Features </li></ul><ul><li>Response </li></ul><ul><li>Local Public Community Reaction (Public and Responders) </li></ul><ul><li>Infrastructure </li></ul><ul><li>Infectious Disease Disaster </li></ul>
  22. 22. Snapshot: SE Asia, 2008-2009 <ul><li>From September 1, 2008 to February 27, 2009 </li></ul><ul><li>998 near real-time reports on </li></ul><ul><ul><li>46 infectious diseases that effect humans or animals </li></ul></ul><ul><ul><li>Myanmar, Thailand, Laos, Cambodia, and Vietnam </li></ul></ul><ul><ul><li>220 provinces, 239 districts, and 14 cities </li></ul></ul>Data source: SE Asia Evolve Collaborative Workspace http://riff.instedd.org/space/ProMed-MBDS
  23. 23. Snapshot: SE Asia, 2008-2009 <ul><li>From September 1, 2008 to February 27, 2009 </li></ul><ul><li>The infectious disease event reporting in SE Asia was of: </li></ul><ul><ul><li>Low socioeconomic disruption (83%), </li></ul></ul><ul><ul><li>High socioeconomic disruption (17%); with indicators of: </li></ul></ul><ul><ul><ul><li>potential sociological crisis (16.4%), and </li></ul></ul></ul><ul><ul><ul><li>disaster (0.6%) </li></ul></ul></ul>Data source: SE Asia Evolve Collaborative Workspace http://riff.instedd.org/space/ProMed-MBDS
  24. 24. Influenza A(H1N1), 2009 Data source: Google Insights for Search http://www.google.com/insights/search/#q=%22swine%20flu%22%2C%22avian%20flu%22&cmpt=q avian flu swine flu
  25. 25. Influenza A(H1N1), 2009 Data source: HashTags.org monitoring Twitter http://hashtags.org/tag/swineflu/messages
  26. 26. Influenza A(H1N1), 2009 Data source: A(H1N1) Evolve Collaborative Workspace http://riff.instedd.org/space/SwineFlu Yin Myo Aye, MD: ProMED MBDS Taha Kass-Hout, MD, MS: InSTEDD
  27. 27. Influenza A(H1N1), 2009 Data source: A(H1N1) Evolve Collaborative Workspace http://riff.instedd.org/space/SwineFlu Yin Myo Aye, MD: ProMED MBDS Taha Kass-Hout, MD, MS: InSTEDD Mid-March 2009 thru May 19 th 2009
  28. 28. Influenza A(H1N1), 2009 Data source: A(H1N1) Evolve Collaborative Workspace http://riff.instedd.org/space/SwineFlu Mid-March 2009 thru May 19 th 2009 Yin Myo Aye, MD: ProMED MBDS Taha Kass-Hout, MD, MS: InSTEDD
  29. 29. Influenza A(H1N1), 2009 Data source: A(H1N1) Evolve Collaborative Workspace http://riff.instedd.org/space/SwineFlu Mid-March 2009 thru May 19 th 2009 Yin Myo Aye, MD: ProMED MBDS Taha Kass-Hout, MD, MS: InSTEDD
  30. 30. Avian Influenza: Egypt, 2009 Tracking the recent Avian Influenza Outbreak in Egypt (reports started to appear late January 2009). Data source: Africa Evolve Collaborative Workspace http://riff.instedd.org/space/AfricaAlerts
  31. 31. Worldwide Health Events, 2008 Data source: Early Detection and Response Evolve Collaborative Workspace http://riff.instedd.org/space/DEMOEventDetection
  32. 32. Acknowledgment
  33. 33. Through Funding from…
  34. 34. Thank You! In STEDD 400 Hamilton Avenue, Suite 120 Palo Alto, CA 94301, USA +1.650.353.4440 +1.877.650.4440 (toll-free in the US) [email_address] Cambodia, Photo taken by Taha Kass-Hout, October 2008 “ this pic says it all- our kids are all the same- they deserve the same ”, Comment by Robert Gregg on Facebook, October 2008

×