The promise of precision medicine in oncology is predicated on the availability of accurate, high quality data from the clinic and the laboratory. Likewise, a Learning Health System is one in which we use data to monitor that we are following guidelines and care pathways to deliver the best care and not revert to prior practices (regression testing for care!) and also provide real world evidence to determine effectiveness and identify populations that would benefit from novel therapies. Into this mix of clinical drivers are the rapidly changing capabilities in instrumentation, computing, computation, and the pervasive use of sensors and smart devices. I will highlight a few of the obvious and perhaps not as obvious opportunities in leveraging the increasingly digital landscape in healthcare and biomedical research as we move toward a national learning health system for cancer.

1. Data: Where Precision Oncology
and Learning Health Meet
Warren A. Kibbe, Ph.D.
Professor, Biostatistics & Bioinformatics
Chief Data Officer, Duke Cancer Institute
warren.kibbe@duke.edu
@wakibbe
SAMSI Workshop on Precision Medicine, August 16, 2018

2. Outline
• Background
• Open Data!
• Precision Medicine
• Learning Health System
• Take homes

3. Take homes
• Networked digital devices are
ubiquitous and pervasive
• Data generation is no longer the
bottleneck
• Biomedical research and medicine
are data enterprises
• Data that is ‘digital first’ needs to
stay digital to be liquid

4. Take homes
• Data sharing is an accelerant
• Precision medicine and learning
health systems are symbiotic
• Decision Support needs accurate,
timely data

5. Personal & Professional Background
• PhD in Chemistry at Caltech, Postdoc in
molecular genetics of RAS
• Cancer research for 20+ years - cancer
informatics, data science, healthcare
• Faculty in the Feinberg School of Medicine at
Northwestern for 15+ years
• Director NCI CBIIT 2013-2017; NCI CIO
2013-2017; Acting NCI Deputy Director for
Data Science 2016-2017
• Lost three grandparents to cancer

6. Changes in Computing
• Converged devices
• Converged IT
• Ubiquity of devices, data, mHealth

7. 2017200220072012
10/23/2001
(~5yrsold)
997
1/9/2007
(~10yrsold)
iPod(10GBmax)
P(mp3)
iPhone(EDGE,16GBmax)
9/16/1999
(~3yrsold)
802.11bWiFi
4/3/2010
(~13yrsold)
iPad(EDGE,64GBmax)
4/23/2005
(~8yrsold)
9/26/2006
(~9yrsold)
7/15/2006
2/7/2007
Google
Drive
4/24/2012
(~15yrsold)7/11/2008
(~11yrsold)
iPhone3G
(16GBmax)
9/12/2012
(~15yrsold)
iPhone5(LTE,128GBmax)
Google
Baseline
3/9/2015
(~18yrsold)
Apple
ResearchKit
HTCVRHeadset
4/5/2016
(~19yrsold)
7/14/2014
(~17yrsold)
NextGen
Courtesy of Jerry Lee, NCI

9. Changes in Oncology
• Cancer is a grand challenge
• Anatomic vs molecular classification
• Health vs Disease

10. Understanding Cancer
• Precision medicine will lead to fundamental
understanding of the complex interplay between
genetics, epigenetics, nutrition, environment and
clinical presentation and direct effective,
evidence-based prevention and treatment.
Ramifications across many aspects of health care

11. Access to data has changed-Epic

12. From Apple Health App

13. $640M
(FY74)
$5.39 B
(FY16)

14. This redefinition has been driven by improved biological understanding

15. This change has been driven by improved technology - sequencing, imaging,
nanotech, drug developing, computing and the availability of data about
patient response to therapy

16. Changes in the Society
• Perceptions of privacy
• GA4GH – right to benefit from
research
• Social media
• Familiarity with IT
• Tobacco control
• Health disparities
• Accountable Care Act

17. (10,000+ patient tumors and increasing)
Courtesy of P. Kuhn (USC)
2006-2015:
A Decade of Illuminating the
Underlying Causes of Primary
Untreated Tumors Omics
Characterization
Cancer is a grand challenge
• Deep biological understanding
• Advances in scientific methods
• Advances in instrumentation
• Advances in technology
• Data and computation
• Mathematical models
Cancer Research and Care generate
detailed data that is critical to
create a learning health system for cancer
Requires:

18. In 2017 there were an
estimated
15,500,000
cancer survivors in the U. S.
In 2008 there were 10 million. In 2026 the projections are for more
than 20 million. ACS and NCI, 2016

19. Data is critical for understanding
cancer, treatment, survivorship
• Public data sets
– TCGA
– TARGET
– FoundationMedicine release 1 (GDC)
– GENIE (cBioPortal & Syapse; GDC)
– MMRF CoMMpass study
• Open data!

20. How do we solve problems in Cancer?
• Incentives for team science
• Engaged, Informed Consent
• We need FAIR, open data
• Promotes Ethical Behavior
• Support open source, open science
• Open Data drives rapid innovation

21. Data Sharing and the FAIR Principles
FAIR –
Making data
Findable,
Accessible,
Attributable,
Interoperable,
Reusable,
and provide Recognition
Force11 white paper
https://www.force11.org/group/fairgroup/fairprinciples

22. 22
Blue Ribbon Panel Report
Cancer Moonshot℠ Blue Ribbon Panel
“The Cancer Moonshot Task Force was
directed to consult with external experts
from relevant scientific sectors, including
the presidentially appointed National
Cancer Advisory Board(NCAB).
A Blue Ribbon Panel of scientific experts
was created to advise the NCAB.”

23. 23
National Cancer Data Ecosystem Recommendations
Recommendations
• Build a National Cancer Data
Ecosystem
– Enhanced cloud-computing
platforms
– Services that link disparate
information, including clinical,
image, and molecular data
– Essential underlying data science
infrastructure, standards,
methods, and portals for the
Cancer Data Ecosystem
Overarching goals
• Accelerate progress in cancer,
including prevention & screening
• From cutting edge basic
research to wider uptake of
standard of care
• Encourage greater cooperation
and collaboration
• Within and between academia,
government, and private sector
• Enhance data sharing
Overall goal: “Enable all participants across the cancer research and care continuum to
contribute, access, combine and analyze diverse data that will enable new discoveries
and lead to lowering the burden of cancer.”

24. 24
NCI Cancer Research Data Commons (CRDC) - Concept
NCI Scope: “Create a data
science infrastructure necessary
to connect repositories, analytical
tools, and knowledge bases”
Data commons co-locate data,
storage and computing
infrastructure with commonly
used services, tools & apps for
analyzing and sharing data to
create an interoperable resource
for the research community.*
*Robert L. Grossman, Allison Heath, Mark Murphy, Maria Patterson and Walt Wells, A
Case for Data Commons Towards Data Science as a Service, IEEE Computing in Science
and Engineer, 2016. Source of image: The CDIS, GDC, & OCC data commons
infrastructure at the University of Chicago Kenwood Data Center.

25. Vision:
Enable the creation of a Learning Healthcare System for
Cancer, where as a nation we learn from the contributed
knowledge and experience of every cancer patient. As
part of the Cancer Moonshot, we want to unleash the
power of data to enhance, improve, and inform the journey
of every cancer patient from the point of diagnosis
through survivorship.

26. Team Science is critical
Clinical Trials
Biostatistics
Bioinformatics
Clinical Care
Clinical Research
EHRs, Imaging, Lab Systems
Data Science
Analytics and Visualization
Open Data enhances collaboration and team science!

27. Scale is changing!

28. Openly shareable, but not always easy to access

29. AACR Project GENIE

30. Project GENIE Data

31. Impact of Data on Biomedical
Research
Challenges and Opportunities
– Workforce
– Ethics
– Data management
– New instrumentation & tech
– Computing, Analytics, Visualization,
Usability – Data Science
Biomedical research is a data driven enterprise

32. Where does all that leave us?

33. Data Science

34. Data Science Hype
Data is the new oil

35. Data science training

36. Data Science Ethics

37. Machine Learning and Data Analytics are
mainstream
0
500
1000
1500
2000
2500
3000
3500
4000
4500
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
Publications in PubMed, 12/29/17
Machine Learning Deep Learning

38. Human Cognitive Capacity

39. Sebastian Thrun

40. Back to Medicine

41. Biology and Medicine are now
data intensive enterprises
Scale is rapidly changing
Technology, data, computing and
IT are pervasive in the lab, the
clinic, in the home, and across the
population

42. Machine Learning, AI
• Machine Learning
• Deep Learning
• Cognitive Computing
• Neuromorphic Computing
• Assistive Devices

43. Opportunities
• Preclinical Models of Cancer
• Cancer as a rare disease
• Participants as partners
• Data Commons
• Compute on the Cloud

44. Challenges (and Opportunities)
• Changing models of reimbursement
• Data and compute infrastructure
sustainability
• Fusion of prevention, care, research,
surveillance

45. Real World Evidence
• Needs big data! Big open data!
• Needs population representation
• Need epidemiologists and
statisticians to understand the
potential biases in representation
• EHRs, NLP, Machine Learning can
power real world evidence learning
• Critical for a Learning Health
System

46. Take homes
• Networked digital devices are
ubiquitous and pervasive
• Data generation is no longer the
bottleneck
• Biomedical research and medicine
are data enterprises
• Data that is ‘digital first’ needs to
stay digital to be liquid

47. Take homes
• Data sharing is an accelerant
• Precision medicine and learning
health systems are symbiotic
• Decision Support needs accurate,
timely data

48. Questions?
Warren Kibbe, Ph.D.
warren.kibbe@duke.edu
@wakibbe