USING (BIG) DATA TO
EFFECTIVELY EMPOWER TOMORROW'S
NURSE LEADERS
Dr. Robert J. McGrath
0 5 10 15 20 25 30 35 2009 2013 2015 2020 0.79 4.1 7.9 35
WHAT IS A ZETTABYTE?
1,000,000,000,000 Gigabytes 1,000,000,000 Terabytes 1,000,000 Petabytes 1,000 Exabytes 1 Zetabyte 1 Terabyte holds about as much as 210 DVDs10%
StructuredThese are the data that exist in databases
10%
Structured
These are the data that exist in databases
90%
Unstructured
Sensors, pictures, video, audio. These are the elements people and machines generate regularly, and are most of the story to be told.
90%
Unstructured
Sensors, pictures, video, audio. These are the elements people and machines generate regularly, and are most of the story to be told.
EMR Org. Info Research Info Quality of Care Treatment Decisions Demogr Health Insurance Knowledge generation Decisions
Prediction Visualization Reporting
ETL Data Mining Data Integration
Data Collection and Storage
Sander Klaus, KPMG http://www.slideshare.net/sanderklous/big-data-in-healthcare
Internal Data External Data
0%
100%
•
In 2012, OECD Countries spent $59 Billion in biomedical
research
•
Bayer could replicate only 25% of 67 studies
•
Amgen only 11% of 53 studies
•
Two studies: 1500 BMJ reviewers missed 92% of errors
•
Even in RCT studies, reviewers failed to detect important
deficiencies of 93 control studies
•
John Ioannidis at Stanford University argues that most published findings are
false
.•
In February of 2014, Regina Nuzzo argues in Nature that P-values are highly
skewed.
•
The more implausible the hypothesis — telepathy, aliens, homeopathy — the
greater the chance that an exciting finding is a false alarm, no matter what
the
P
value is.
THE LOOMING DEMOGRAPHIC CONUNDRUM
1950 7.2 1980 5.1 2011 4.1 2050¹ 2.1 Living LongerUS Life expectancy for Males @ 65
1940: 12 years 2007: 18 years
Aging Beyond Our Ability to Support
623K New Medicare beneficiaries each year 1995-2010
1.6M New Medicare beneficiaries each year 2010-2030
2X
In 2030, Medicare will have twice as many beneficiaries as in 2010
Number of People 20-64 for Every Person >65
http://www.cms.gov/Research-Statistics-Data-and-Systems/Statistics-Trends-and-Reports/NationalHealthExpendData/NationalHealthAccountsProjected.html
CONFRONTING A CHANGING PARADIGM
The Evolution of Incentives for Providers
Fee for Service DRG / Quality Cost
Incentives Accountable Care
Patient Volume Length of Stay Ancillary Testing
Health Care Environmental Paradigm
• Volume driven primary & specialty care
• Emergence of quality & safety processes & metrics
• Increased transparency on pricing & outcomes
The “Triple Aim” (Value)
• Improve the experience of care
• Improve the health of populations
• Reduce the per capita costs of health care
• Two-way risk sharing
GLOBAL PAYMENT IMPLICATIONS
EXAMPLES of “Re-Thinking” Care Delivery Systems Under Global Payment
Models
“Rapid Access Care”
ER use change
Diagnostic Testing
In system vs. out of system perspectives
Chronic Illness – Behavioral Health Impact
Implications for primary care delivery systems
Improving Population Health is Challenging
Better the Experience of Care Lower Per Capita Health Costs Improve Population Health
Better
Value
Transforming Health Care Delivery
System
CARE SYSTEM TRANSFORMATION FOCUS AREAS
Enhanced Primary
Care
Care Management
Patient Engagement
and Activation
Post Acute Care
Partnerships
Aligned Payer
Relationships
Integrated
Information
Technology
20Core Integration Strategy:
Some Outcome Inefficiencies Media Enhanced Health Outcomes Providers Non-profits Schools Civic Groups
Government Businesses Public Health Faith-based Food environment
Fragmented system
Integrated system
EMR Org. Info Research Info Quality of Care Treatment Decisions Demogr Health Insurance Knowledge generation Decisions
Prediction Visualization Reporting
ETL Data Mining Data Integration
Data Collection and Storage
Sander Klaus, KPMG http://www.slideshare.net/sanderklous/big-data-in-healthcare
Internal Data External Data
CURRENT HEALTH CARE INFORMATION
TECHNOLOGY LANDSCAPE
•
GOOD AT:
•
Large-scale institutional EHRs can facilitate communication within the
institution
•
Hospital to emergency department to in-house medical clinic.
•
BAD AT:
•
Need for custom screens and solutions
•
Clunky tools lead to department or office specific work arounds that don’t
easily translate
•
And non HIPAA compliant alternatives like emails.
•
Or…Using fax and phone
AMERICAN ACADEMY OF NURSING ON POLICY:
A CALL TO ACTION: ENGAGE IN BIG DATA SCIENCE
“No more evident is this than in nursing where after decades of implementing
EHRs nurses still cannot consistently use electronically collected data to
conduct research or report quality and patient safety outcomes.”
http://authenticmedicine.com/growing- hospital-computer-information-system-stopped-stephen-mussey-md/
HIPAA
•
Covered: Data for clinical care is covered
•
Not Covered:
•
Data collected by a pharmaceutical manufacturer in a clinical trial
•
Searches that people do online for health information
•
Social media or mobile health apps to collected and store and use data.
•
Stage 1
•
91% of eligible hospital and 68%of eligible providers have been paid in the EHR
Incentive Program
•
Stage 2 Progress is beginning
•
Requires enhanced capabilities for interoperability, patient engagement and
quality measures
•
893 certified products as of May 2014
•
8 hospitals and 252 providers have attested as of May 2014
•
Stage 3 measures are being finalized
•
ONC held first (annual) Nursing Summit
•
239 attendees; 80% from frontline nursing roles
MEANINGFUL USE
•
A large majority (82%) indicated that bi-directional sharing of
clinical and/or patient data with local healthcare organizations
is important or very important to their organization.
•
Analytics for Quality improvement most common (90%)
•
Inpatient care utilization and outcomes analysis (80%)
•
Adverse event reporting (75%)
eHealth Initiative, Key Findings from eHealth Initiative Survey on Data and Analytics. August, 2013. http://www.ehidc.org/resource-center/publications/view_document/26
READINESS:
2013 CIO SURVEY
BUT…..
•
Only 18 percent of respondents indicated that they have sufficient
trained staff to collect, process, and analyze data.
•
Twenty-six percent report that although they have tried hiring more
staff for analytics, they have not found sufficiently trained candidates.
•
Thirty-four percent of respondents note that senior leadership had not
prioritized analytics as a key area for staffing needs.
DATA COLLABORATIVES
Academia Patients / Consumers IT Industry Clinical Delivery Public Health Payers / Employers Communities HIE’s[case studies here]
GE HEALTHCARE AND SAS ANALYTICS
• How to capture “near misses” in health care
• Airlines do it often (50:1 ratio)
• Health care its estimated at about 300:1
• There's been a tenfold increase in the number of events being captured by the GE Medical Event Reporting System (MERS).
OHIO MEDICAID: CARESOURCE CLAIMS ANALTYICS
Using claims, Ohio found:
• A patient with 27 unique doctor visits in one month and 30 different prescriptions written (seven of them just for asthma).
• Patients who were taking medicine that was contraindicated, prescribed by different doctors.
• Patients who visited the ER so many times for headaches that they were exposed to dangerous amounts of radiation because of multiple CAT scans.
By providing the data to nurse care managers they were able to improve quality:
• An office can generate a list of patients overdue for a blood sugar test and call the patients for reminder appointments.
• Prescriptions are immediately visible to doctors when a patient visits, allowing them to better manage a member’s health.
NH AND APCD DATA
UNH Institute for Health Policy helped the Accountable Care Project across the state with the goal of: Creating and sustaining a payment reform/clinical/quality improvement learning network.
- APCD (all payer claims data)
METHODS – PROVIDER IDENTIFICATION, NPI REVIEW
COPYRIGHT, 2014. UNIVERSITY OF NEW
HAMPSHIRE. ALL RIGHTS RESERVED. 40
Category % of claims in category “Fix”
1. Consistent NPI (No concerns) 46.09% None Needed
2. Consistent NPI when populated, but sometimes missing
9.62% Most prevalent NPI was assigned to the Service Provider ID
3. Always missing NPI 3.90% No fix attempted
4. Multiple, inconsistent NPI (could include some missing)
40.39%;
5.15% Changed NPI
Most prevalent NPI was assigned to the Service Provider ID
NH ACO / APCD
• Other Issues:
• Defining Primary Care?
• Patient attribution
• Geographic representation (so as not to attribute costs by MSA)
• Report design (big challenge…)
• Site- and region-level reporting (2 sets)
• 11 clinical measures
• Reporting by 19 geographic regions
• Reporting by 21 site designations
• Reporting for 3 types of data (commercial, Medicaid, Medicare)
• 2 years of data
REPORT DESIGN: TOO MUCH INFO!
•
All in PDF output
•
More than 2,000 pages of
reports across full report suite
SOLUTION
•
SAS Visual Analytics
•
Provides online secure portal
•
Ability to drag and drop variables for a variety of cuts
•
On the fly graphics and visualizations
PREDICTIVE ANALYTICS
UC Irvine Health:
•
Had millions of data points across 1.2 million patients over 22 years in Excel files and
paper
•
Needed to migrate to a singular data warehouse into a single platform (Hortonworks)
which fed medical center and the research center.
•
The Key…HADOOP.
PREDICTIVE ANALYTICS
UC Irvine Health:
•
One outcome is clinical nursing. Patients wearing vital sign sensors transmit every
minute
•
4,320 per patient per day
•
Using predictive algorithms, nurses get signals for near term health risk
outcomes.
•
Those vitals can then be combined for other data on that patient or on historical
patiets with similar risk factors etc…
•
Let the data uncover what was once hidden.
THE FUTURE:
Start-Up Funding by digital health companies in 2014
In here: What is a data scientist? Will there be a nurse or quality analytics role?
WHAT SHOULD NURSE LEADERS BE READY FOR?
BIG DATA CONFERENCE: EXPERT NURSING PANEL
2013
Recommendations
• 1. Implement strategies that advance the adoption of standardized terminologies for clinical documentation by nurses in electronic health records.
• 2. Conduct two policy updates via conference call/webinar for the expert panel membership ( June 2014 and September 1, 2014) following the Big Data Conference
• 3. Conduct an open “Policy Dialogue” entitled “Putting the Health Back in Electronic Health Records” at the 2014 Annual AAN Conference in October 2014
A CALL TO ACTION: ENGAGE IN BIG DATA SCIENCE
• Develop a strategy/campaign for educating front line nurses, students, and faculty on informaticscompetencies and the value of standardized nursing data.
• Advocate for the adoption of Systematized Nomenclature of Medicine - Clinical Terminology and Logical Observation Identifiers Names and Codes as national standards for clinical data, and link them with nursing terminologies through mappings.
• Convene a consensus conference with leaders of the major nursing organizations and
interprofessional stakeholders to educate them, hear their views, and ultimately speak in one voice.
• •Refresh and activate the American Nurses Association's Nursing Information & Data Set Evaluation Center criteria to advance systems that represent and value nursing data.
• •Continue bold participation in standards and EHR standards development to ensure a nursing voice
Members of the American Academy of Nursing's Expert Panel on Nursing Informatics and Technology attended the conference and participated in developing the following key components of the action plan: Nursing Outlook Volume 62, Issue 1, January–February 2014, Pages 64–65
• Many industries moving to expanded roles for the advanced data consumer
• Chief Data Officer
• Chief Analytics Officer
• Director of Nursing Informatics / Analytics
• BUT…Data Science in Different than Informatics
• Beyond storage, retrieval and reporting it includes:
• Advanced analysis, predictive and prescriptive analysis
• The ability to distill and convey information both verbally, orally and visually
• The ability to match strategic and process questions to capabilities