1. 1
Using Big Data Systems to Understand
Health Care Professional Conversations
in Public Social Media
Paul Grant
Chief Innovation Officer
Creation Healthcare
@paulgrant

2. 2
The views and opinions expressed in the following
PowerPoint slides are those of the individual presenter
and should not be attributed to Drug Information
Association, Inc. (“DIA”), its directors, officers,
employees, volunteers, members, chapters, councils,
Communities or affiliates, or any organization with
which the presenter is employed or affiliated.
These PowerPoint slides are the intellectual property of
the individual presenter and are protected under the
copyright laws of the United States of America and
other countries. Used by permission. All rights
reserved. Drug Information Association, Drug
Information Association Inc., DIA and DIA logo are
registered trademarks. All other trademarks are the
property of their respective owners.
Disclaimer

3. 3
Source: http://www.sxc.hu/profile/nosheep

4. 4 Photo credit: adactio / Foter / Creative Commons Attribution 2.0 Generic (CC BY 2.0)

5. 5
A sizeable proportion of consumers are
happy for companies to use their
personal data, providing they benefit
through more targeted marketing
Photo credit: http://www.ey.com/Media/vwLUExtFile/BigData/$FILE/ey-bigdata_v3.png

6. 6
Mainframe
data
Illustration credit: Modification from an image by HP/Syncsort
So-called ‘Dark Data’
Traditional
enterprise
data
Big Data
CRM ERP Data
warehouse
Web Social Log
files
Machine
data
Semi-
structured
Unstructured
Risk?
Opportunity?

7. 7
we know we know
Practical tip: Big data insights audit
we know we don’t knowwe don’t know
we don’t know
we don’t know
we know
we know
we know
we don’t know
we don’t know
Source:Adapted from http://www.doceo.co.uk/tools/knowing.htm

8. 8
Search behavior
Closed professional networks
Engagement with medical information
User generated content
– Professional collaboration sites
– Public social media
Semi-structured & unstructured sources

9. 9
Source 1: Search behavior

10. 10
Source 2: ‘Closed’ physician networks

11. 11
Product complaint
Public response
Passive
(Listening)
Active
(Stimulating)
Environment Evaluation Escalation Engagement
Monitoring and triage
Sed risus nulla, sollicitudin eget ornare vitae, blandit vitae lectus. Ut quis arcu ut nulla
facilisis tempus blandit a nibh.
jibbajabba
said
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed risus nulla,
sollicitudin eget ornare vitae, blandit vitae lectus. Ut quis arcu ut nulla
facilisis tempus blandit a nibh. Sed aliquam consectetur libero vitae
pellentesque. Pellentesque posuere imperdiet sem, vitae aliquet eros
elementum placerat.
dwight
said
Conversation of
interest
Compliment
Complaint
Question
Challenge
Information
Off-topic
Company
Person
Product
Company
Person
Product
Company
Person
Product
Company
Person
Product
Company
Person
Product
ALLOW: Go to step 3, escalate, engage
ALERT: Go to step 2, escalate
ACTION: Go to step 2, remove, explain
Other Step 2
Company
Person
Product
Positive
Negative
Ignore
Thank the person for
commenting
Correct
misinformation
Non-compliant
Explain why the
comment was
removed; remind of
terms or code
constraints
Factual
Incorrect
Adverse Event Drug Safety
Compliant
Legal / Medical
Opinion
Information check
Content check
Regulatory check
Private response
Situation room
Communications, PR,
Legal, Medical, etc.
2
3
4
Response
5
Report
Acknowledge issue;
next steps
Answer with
approved content or
redirect
Request
1
6
Product team
Inappropriate
Channel
Conversation
platforms
Practical tip: Listening and engaging

12. 12
Source 3: Engagement with MedInfo

13. 13 13

14. 14
What happens if we focus on a word like ‘fridge’

15. 15
Clear issue already
detectable week one,
escalation within business
to avoid week two peak
Normal
Issue

16. 16
Practical tip: ‘Mash-up’ data sources
Rank City Population MI requests Ratio
1&2 London/City of London(England) 7556900 818 0.011%
3 Birmingham(England) 984333 216 0.022%
10 Manchester(England) 395515 177 0.045%
4 Glasgow(Scotland) 610268 159 0.026%
6 Leeds(England) 455123 143 0.031%
22 Nottingham(England) 246654 141 0.057%
5 Liverpool(England) 468945 139 0.030%
18 Belfast(Northern Ireland) 274770 135 0.049%
9 Bristol(England) 430713 115 0.027%
31 Newcastle upon Tyne(England) 192382 108 0.056%
8 Edinburgh(Scotland) 435791 105 0.024%
44 Dundee(Scotland) 151592 77 0.051%
7 Sheffield(England) 447047 66 0.015%
62 Newport(Wales) 117326 65 0.055%
12 Leicester(England) 339239 63 0.019%
16 Cardiff(Wales) 302139 62 0.021%
23 Southampton(England) 246201 57 0.023%
38 Walsall(England) 172141 57 0.033%
26 London Borough of Harrow(England) 216200 52 0.024%
90 Lincoln(England) 89228 52 0.058%
43 Oxford(England) 154566 47 0.030%
17 Bradford(England) 299310 45 0.015%
24 Reading(England) 244070 45 0.018%
UK population data source: http://www.populationlabs.com/UK_Population.asp

17. 17
Health Care Professionals are increasingly
collaborating online through social networks
Source 4:

18. 18
“The public physician might author blogs,
create videos, publish e-books, share news,
or curate links on Twitter. The public
physician is involved not just in social
dialogue but in the creation of retrievable
content allowed by the democratization of
media and facilitated by easy‐to‐use
technology…”

19. 19

20. 20
>400 million Tweets to date and averaging 300,000 Tweets per day
Illustration credit: Creation Pinpoint® data presented at Stanford Medicine X 2014

21. 21
Discussion between rheumatologists about
how to manage RA when DMARDs have
failed, and the application of biologics in this
situation, and where there are particular
considerations such as joint sepsis
Twitter, for clinical conversations!
Source: https://twitter.com/rheumi_/statuses/370599136531591168

22. 22
Practical tip: Aggregate!
106 comment Twitter conversation, April 2013
Word cloud of EM debate on heart failure treatment
Source: https://twitter.com/TBayEDguy/status/322087728760094720

23. 23
Health reform – issues and concerns
Source: http://hcpdols.com/healthreform/

24. 24
Varies by role and location
Source: http://hcpdols.com/healthreform/

25. 25 Photo credit: Todd Buchanan http://vimeo.com/98482319

26. 26
The digital world changes the model of influence
26
Hierarchy based on seniority,
experience and publications
Collaborative ‘flattened’ relationships,
not ordinarily common in real-world
Traditional KOL model: Emerging DOL model:

27. 27
Source: Creation Pinpoint® study into inflammation in the United Kingdom
1284 nodes, 1633 edges

28. 28
Practical tip: Identify ‘DOLs’
Source: http://www.creationpinpoint.com/unveiling-the-creation-pinpoint-oncology-project/

29. 29
Influence on other DOLs…
Source: http://www.creationpinpoint.com/unveiling-the-creation-pinpoint-oncology-project/

30. 30
Conversations and topics
Source: http://www.creationpinpoint.com/unveiling-the-creation-pinpoint-oncology-project/

31. 31
Network of conversational influence
Source: http://www.creationpinpoint.com/unveiling-the-creation-pinpoint-oncology-project/

32. 32
Practical tip: Online ‘big data’ research
Therapy area
What topics around your therapy area and/or indication would you focus on?
2
Brand & comparative products
Would you want to study ‘mentions’ of your brand and/or comparative products?
3
Region
What region or countries would you focus on?
4
Include patients?
In addition to HCP perspectives, would you also look at the conversations of patients & consumers?
5
Market factors
Are there market factors to be aware of or do you have existing insights to compare outputs with?
Such as new data; product launch; competitor activity; changes in policy?
6
Your goals
What would you hope to gain from online ‘big data’ research?
E.g. discover customer needs; plan messaging; develop advocates; measure results
1

33. 33
Paul Grant
Chief Innovation Officer
Creation Healthcare
@paulgrant
Join the conversation #DIA2015
Discussion