weight in grams). Of course, clinicians intuitively make the leap from pounds to grams for an infant, but this is not ‘obvious’ to a computer.
the data equivalent of a lingua franca. The same is true for normalizing medical record numbers, units of measure, and other types of ‘master data.’
A moderately sized health system may have several hundred source systems, and large ones may have thousands. Key clinical data are often distributed widely in different EMRs, departmental systems, record keeping, patient registries, etc. More often than not these data are coded in differing terminologies, making it difficult to use them together as they are. Even health systems that are standardized on one terminology set (e.g., the International Classification of Diseases, ninth revision [ICD-9]) typically have different versions active and almost certainly have many source-specific custom codes. To render this ‘Tower of Babel’ computational, the warehouse must assert a common vocabulary,38
accuracy and resolution of true clinical data are improving rapidly. Unfortunately, key clinical data needed for translational research (e.g., tumor staging) is often locked up in unstructured free text dictated or typed by clinicians. Artificial intelligence techniques, including natural language processing (NLP), are now an effective means of extracting high-definition data from the free text captured in today’s EMRs,41 especially for research applications.
In the 2010 Patient Protection and Affordable Care Act, the US Congress funded the Patient-centered Outcomes Research Institute with $3 billion to spend between now and the end of the decade. Its work is guided by four questions from a patient’s perspective:
As good big data become ever more strategic, executive support for data governance is crucial, both in terms of correcting bad data and in terms of getting to common definitions. It can be an organizational challenge to reach consensus, and it is often not cheap. Consider the executive commitment at The Mayo Clinic: “Mayo’s Enterprise Data Governance (EDG) oversees all of Mayo’s data as an enterprise asset. EDG establishes and enforces policies, principles, and standards to optimize Mayo’s enterprise data assets through a Data Governance Committee, comprising 15 members from across Mayo’s three-campus enterprise. Members include the Executive Dean for Clinical Practice, Executive Dean for Education, CIO, CMIO, Chief Planning Officer, and others.”38
‘Enterprise Data Trust.’
Historically, the main source of ‘clinical’ data was a potentially misleading proxy, that is, payer claims data.40
As EMRs come online, the 1. 2. 3. 4. 5. 6. 7.
The Henry J. Kaiser Family Foundation, Healthcare Reform. Available at: http://healthreform.kff.org/
(accessed December 8, 2011).
Christensen CM, Grossman JH, Hwang J, The Innovator’s Prescription: A Disruptive Solution for Health Care, New York, London: McGraw-Hill, 2009.
National Institutes of Health, Office of Budget. http://officeofbudget.od.nih.gov/approp_hist.html
(accessed December 12, 2011)
Feero WG, Guttmacher AE, Collins FS, Genomic medicine — an updated primer, N Engl J Med, 2010;362:2001–11.
Definition of personalized medicine, National Cancer Institute. Available at: www.cancer.gov/dictionary
? cdrid=561717 (accessed December 8, 2011).
Hamburg MA, Collins FS, The path to personalized medicine, N Engl J Med, 2010;363:301–4.
Collins F, Personalized medicine: has the revolution arrived?, Nature, 2010;464:674–5.
(accessed December 8, 2011). 9.
A Catalog of Published Genome-Wide Association Studies, National Human Genome Research Institute. Available at: www.genome.gov/gwastudies/
(accessed December 8, 2011).
10. Davidson EH, Levine MS, Properties of developmental gene regulatory networks, Proc Natl Acad Sci U S A, 2008;105:20063–6.
11. Li GW, Xie XS, Central dogma at the single-molecule 94
Given my personal characteristics, conditions, and preferences, what should I expect will happen to me?
What are my options, and what are the benefits and harms of those options?
• What can I do to improve the outcomes that are most important to me? • How can the healthcare system improve my chances of achieving the outcomes that I prefer?42
This is one reason why it calls its data warehouse the
As simple and obvious as these questions seem, there are tremendous scientific, technologic, and social challenges that must be met in the course of finding the answers. The answers lie at the confluence of life sciences research and broad, detailed clinical observation. Effectively putting them to use requires delivering new insights and interventions out to clinicians at the point of care, and ultimately out to patients themselves. Omics, brain mapping, EMRs, population health studies, point-of-care applications, social networking, remote sensing—each are big data problems of the highest order in and of themselves. Bringing them all together, so we can tell each person how they can best be well, is humanity’s ultimate big data challenge. ■
level in living cells, Nature, 2011;475:308–15.
12. The beta-blocker heart attack trial. beta-Blocker Heart Attack Study Group, JAMA, 1981;246:2073–4.
13. National Committee for Quality Assurance, The State of Managed Care Quality, Washington, DC: National Committee for Quality Assurance, 1997.
14. Chassin MR, Loeb JM, Schmaltz SP, Wachter RM, Accountability measures – using measurement to promote quality improvement, N Engl J Med, 2010;363:683–8.
15. National Committee for Quality Assurance, The State of Health Care Quality, Washington, DC: National Committee for Quality Assurance, 2011.
16. Stafford RS, Radley DC, The underutilization of cardiac medications of proven benefit, 1990 to 2002, J Am Coll Cardiol, 2003;41:56–61.
17. Goss JR, Elmore JG, Lessler DS, Quality of health care delivered to adults in the United States, N Engl J Med, 2003;349:1866–8; author reply 1866–8.
18. Levinson DR, Adverse Events in Hospitals: National Incidence Among Medicare Beneficiaries, Washington, DC: US Department of Health and Human Services, 2010.
19. Physicians in the United States and Possessions by Selected Characteristics, American Medical Association, 2001. Available at: www.ama-assn.org/resources/
f (accessed December 8, 2011)
20. Lenfant C, Clinical research to clinical practice – lost in translation?, N Engl J Med, 2003;349:868–74.
21. Osterberg L, Blaschke T, Adherence to medication, N Engl J Med, 2005;353:487–97.
22. Bloss CS, Schork NJ, Topol EJ, Effect of direct-to- consumer genomewide profiling to assess disease risk, N Engl J Med, 2011;364:524–34.
23. Volpp KG, Troxel AB, Pauly MV, et al., A randomized, controlled trial of financial incentives for smoking cessation, N Engl J Med, 2009;360:699–709.
24. Schmidt H, Voigt K, Wikler D, Carrots, sticks, and health care reform — problems with wellness incentives, N Engl J Med, 2010;3:2010–2.
25. US Hospital Social Network List. Available at: http://ebennett.org/hsnl/
(accessed December 8, 2011).
26. Kane GC, Fichman RG, Gallaugher J, Glaser J, Community relations 2.0, Harv Bus Rev, 2009;87:45–50, 132.
27. Social Media Glossary, Social Media Use in Healthcare for Quality Improvement, 2011. Available at: http://tcf.innovationcell.com/book/archive/2010/12/social-
media-glossary (accessed December 8, 2011).
28. Manyika J, Chui M, Brown B, et al., Big Data: the Next Frontier for Innovation, Competition, and Productivity, The McKinsey Global Institute, 2011.
29. Ginsberg J, Mohebbi MH, Patel RS, et al., Detecting influenza epidemics using search engine query data, Nature, 2009;457:1012–4.
30. Chui M, Löffler M, Roberts R, The Internet of Things, McKinsey Quarterly, 2010.
| Page 2
| Page 3
| Page 4
| Page 5
| Page 6
| Page 7
| Page 8
| Page 9
| Page 10
| Page 11
| Page 12
| Page 13
| Page 14
| Page 15
| Page 16
| Page 17
| Page 18
| Page 19
| Page 20
| Page 21
| Page 22
| Page 23
| Page 24
| Page 25
| Page 26
| Page 27
| Page 28
| Page 29
| Page 30
| Page 31
| Page 32
| Page 33
| Page 34
| Page 35
| Page 36
| Page 37
| Page 38
| Page 39
| Page 40
| Page 41
| Page 42
| Page 43
| Page 44
| Page 45
| Page 46
| Page 47
| Page 48
| Page 49
| Page 50
| Page 51
| Page 52
| Page 53
| Page 54
| Page 55
| Page 56
| Page 57
| Page 58
| Page 59
| Page 60
| Page 61
| Page 62
| Page 63
| Page 64
| Page 65
| Page 66
| Page 67
| Page 68
| Page 69
| Page 70
| Page 71
| Page 72
| Page 73
| Page 74
| Page 75
| Page 76
| Page 77
| Page 78
| Page 79
| Page 80
| Page 81
| Page 82
| Page 83
| Page 84