Graphs Opening Medical Care Information - Dave Fauth @ GraphConnect NY 2013

1,274 views
1,107 views

Published on

The current DocGraph social graph was built in Neo4J. With new enhancements in Neo4J 2.0, now was a good time to rebuild the social graph. The goal of this session is to show participants how simple it is to perform basic graph analysis of a healthcare dataset.

Published in: Technology, Business
0 Comments
1 Like
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
1,274
On SlideShare
0
From Embeds
0
Number of Embeds
0
Actions
Shares
0
Downloads
21
Comments
0
Likes
1
Embeds 0
No embeds

No notes for slide

Graphs Opening Medical Care Information - Dave Fauth @ GraphConnect NY 2013

  1. 1. Graphs Opening Medical Care Information @davefauth www.intelliwareness.org
  2. 2. About Me • • • • My Blog: http://www.intelliwareness.org Find me on Twitter: @davefauth Email me: dsfauth@gmail.com GitHub: http://github.com/davidfauth 2
  3. 3. Not talking about this….
  4. 4. Or this….
  5. 5. But we want to talk about this:
  6. 6. And this: Ryan Weald – isurfsoftware.com
  7. 7. I’ll try not to do this…
  8. 8. Or this….
  9. 9. Where we are today
  10. 10. Healthcare Data • Recommend watching Fred Trotter speak at GraphConnect – SF • Moving from no data -> bad data -> better data -> good data • Claims Data – Hard to accurately describe what a doctor is doing and how they are getting paid without claims data – Limited and not a good data set by any standard
  11. 11. Examples of Bad Data • Not enough data – More transparency without having to FOIA • State level data is hard to get
  12. 12. Better Data Sets • DocGraph Data – One of the “best” available – “Best” does not mean “good” • DocGraph Rx – Prescribing patterns for Medicare Part D patients • NPPES • NUCC
  13. 13. DocGraph Dataset • DocGraph by the numbers – Directed graph – Average total degree 52.8 – 940,492 providers (graph nodes/vertices) – 49,685,810 shared edges
  14. 14. DocGraph Data
  15. 15. Doctor Detail (docNPI.com)
  16. 16. Doctor Detail
  17. 17. NPPES • • • • National Plan and Provider Enumeration System Source of NPI (National Provider Identifier) No cost download  Information is entered and updated by provider Data quality is good to poor  • CSV file with 314 columns 
  18. 18. NUCC • National Uniform Claim Committee – Healthcare Provider Taxonomy – No cost download  • CSV file with 5 columns and 830 rows – Link taxonomy to NPPES reported taxonomy
  19. 19. DocGraph Data Nodes Organizations Specialties Providers Locations CountiesZip Census Relationships * Organizations -[:PARENT_OF] – Providers -[:SPECIALTY]Specialties * Lcations-[:LOCATED_FOR]-Providers * Providers -[:REFERRED]-Providers * Counties -[:INCOME_IN]- CountiesZip * Locations – [:LOCATED_IN]-CountiesZip
  20. 20. DocGraph Data Provider refers
  21. 21. DocGraph Data Specialty Specializes_in Provider refers
  22. 22. DocGraph Data Specialty Specializes_in Parent_Of Provider Parent Org Location_In Location refers
  23. 23. DocGraph Data Specialty Specializes_in Parent_Of Provider Parent Org Location_In Location refers
  24. 24. DocGraph Data Specialty Specializes_in Parent_Of refers Provider Income Parent Org Income_In Location_For Located_In Location Counties Zip
  25. 25. DocGraph RX Data • Reinforcing Jonathan Freeman’s talk on Hadoop and Neo4J
  26. 26. Time for Analysis
  27. 27. Fraud Referrals April 2013 - The owner and another senior executive of Sacred Heart Hospital and four physicians affiliated with the west side facility were arrested today for allegedly conspiring to pay and receive illegal kickbacks, including more than $225,000 in cash, along with other forms of payment, in exchange for the referral of patients insured by Medicare and Medicaid to the hospital, announced U.S. Attorney for the Northern District of Illinois Gary S. Shapiro.
  28. 28. Hadoop Page Rank
  29. 29. DocGraph RX Data • Originally obtained by ProPublica • Prescribing pattern for all physicians for Medicare Part D – 2011 • Largest public released prescribing database • 2 sets of data - 30M edges each • Related to business name and NDC-9 code – NDC 9 code allows for aggregation of drugs
  30. 30. DocGraph RX Data
  31. 31. DocGraph RX Data
  32. 32. DocGraph RX Data
  33. 33. DocGraphRx Data Drugs Specialty prescribes Specializes_in Parent_Of refers Provider Income Parent Org Income_In Location_For Located_In Location Counties Zip
  34. 34. DocGraph RX Data • http://whnt.com/2013/03/27/follow-updecatur-family-claims-prescription-drugsfrom-dr-shelinder-aggarwal-killed-their-son/ • http://www.palmbeachpost.com/news/news/ state-regional/doctors-booted-fom-medicaidfor-massive-oxy-doses-/nPpMf/
  35. 35. DocGraph RX Data • Back to “bad data” • http://www.albme.org/actions.html
  36. 36. Combine additional datasets • Medical data – Doctor referral data – Medicare doctor prescription practices – “Dollars for Doctors” – Drug company promotional payments • Census Data – Income data – Poverty data
  37. 37. Recommendation Engine? • Build a graph model of the data • Build a recommender model from the graph model • Graphs can be visualized, explained, discussed and debugged collaboratively

×