clinical integration and the continuum of...
TRANSCRIPT
Ellen M. Harper DNP, RN-BC, MBA, FAAN
Vice President, Chief Nursing Officer Cerner Corporation
DISCLAIMER: The views and opinions expressed in this presentation are those of the author and do not necessarily represent official policy or position of HIMSS.
Clinical Integration and the Continuum of Care April 12, 2015
-
Conflict of Interest
Ellen M. Harper DNP, RN_BC, MBA, FAAN
Has no real or apparent conflicts of interest to report.
© HIMSS 2015
Learning Objectives Attendees will:
• Explore today's barriers and challenges to sharable
comparable data
• Discuss the framework for universal requirements
• Identify differences in the context of nursing outcomes
• Address the impact of software versions and
configurations and analyze the variation in
quality measures
Increasing Adoption Rates
Source: Keith Ellison, Wikipedia
Technology Diffusion Rate for Consumer Products
5
Hall and Khan (2003) http://books.google.com
Technology Revolution
Healthcare is Data Driven
Healthcare is Data Driven
Digitization – Scanned Document
Digitization – Scanned Document
Datafication – When Words become Data that is “Machine Readable”
Include:
• Simple text search
• Child concepts
• Synonyms
• Related Concepts
Datafication – When Words become Data that is “Machine Readable”
Putting the Pieces Together
Continuous Use of Data
Primary purpose - to track an individual patient’s health
Documented once and used multiple times
Temperature 38 degrees
Respiratory Rate 28
Systolic Blood Pressure
98 mm/hg
Heart rate 110
Glucose 148 mg/dl
Continuous Use of Data -
Operating
Characteristics
• Sensitivity 68-91%
• Specificity 91-97.6%
• PPV up to 68%
Monitoring
• Over 130 facilities
• 32,960 persons per
hour
• 791,040 lives per day
Version 14
Sepsis
Client Achievements Sepsis
1980 lives saved since 2010 at ……
• Over $27.3 Million in cost savings
• Sepsis mortality rate decrease by 4.2%
• Sepsis LOS reduced from 9.8 days to 8.3 days
156 lives saved in FY2014 at ……
• Sepsis, any diagnosis, mortality rate decrease by 1.42%
• Nearly 1 patient saved every 2 days
Sepsis mortality rate dropped 20% at ……
• Sepsis LOS reduced from 6.3 days to 4.8 days
Continuous Use of Data – Interdisciplinary Care Planning
Admitted for Heart Failure
mental instability & history of
clotting disorder
unsteady gait CPOE
Risk for
VTE
Risk for Delerium
sedatives
(Risk for)
Falls
anticoagulant therapy
Risk for
Injury
History Of fall
Morses Falls Score = 55
Disorientated Incontinent
Lethargic
Continuous Use of Data -
Falls Risk
Age Greater Than 70
Lives alone Social isolation Takes more
than 10 medications
Chronic conditions (Heart
Failure, AMI)
# of admission In previous 6
months
Continuous Use of Data - Readmission Prevention
Client highlight
Performance Improvement
Using predictive analytics to drive the health and care of the
population across care settings
Monitor
Readmission risk is
monitored and updated every
2hrs to better align care
21%
Reduced high risk
readmissions by 21% for
heart failure patients
Manage
Patients that receive high
risk education have a 20%
lower readmission rate
Strong Readmission Prevention Outcomes
Largest Accountable Care
Organization in the USA
by Modern Healthcare,
With over 609,000 patients
in value-based
agreements,
11 Acute Care Hospitals
Chicago, Illinois
Used with permission from Advocate Health Care
Respirations labored
Weak cough
Disorientated
Chest tube
Lethargic
Respiratory Status Outcomes
Continuous Use of Data -
Calculating Workload
Predicted
staffing Scheduled
Staff Retrospective
Average Staffing
Demand for
Staff
Predictive Modeling – RN Staffing Need
$1,554,964$1,810,960
$3,365,924$3,089,974
$2,622,948
$5,712,922
$4,644,938$4,433,908
$9,078,846
$0
$1,000,000
$2,000,000
$3,000,000
$4,000,000
$5,000,000
$6,000,000
$7,000,000
$8,000,000
$9,000,000
$10,000,000
FY11 FY12 Total
OT Savings LOS Savings Total Savings
Overtime (OT) and Length of Stay (LOS) Savings
Caspers, B. A., & Pickard, B. (2013). Value based resource management. Nursing Administration Quarterly, 37(2), 95-104.
Big Data - Sharable & Comparable
HIMSS CNO-CNIO Vendor Roundtable
• Background & Sponsorship
• Facilitated by
– Gail E. Latimer, MSN, RN, FACHE, FAAN,
– Roy L. Simpson, DNP, RN, DPNAP, FAAN
• Three Workgroups were founded
– Big Data Principles
– Vendor Nurse Role
– Human Factors
Key objectives:
• Serve as an advocate and leader for the nursing community
• Provide guidance on informatics competencies for nursing
• Provide guidance on EHR related topics including analytics, interoperability, usability, terminology, workflow, quality and outcomes
Workgroup Members Big Data Principles Workgroup
Ellen Harper, DNP, RN-BC, MBA, FAAN Vice President, CNO - Premier West Cerner
Joyce Sensmeier, MS, RN-BC, CPHIMS,
FHIMSS, FAAN Vice President, Informatics HIMSS
Sue Lundquist, BSN, RN-BC Director, Patient Care Solutions, Health
Services Siemens
Marion McCall, BBA, RN, CNOR, CPHIMS Chief Clinical Officer OverSite Solutions
Beth Meyers, RN, MS, CNOR Chief Nurse Executive, Analytics
Strategy Director Infor
Sara Parkerson, RN, MSN Clinical Solution Development Manager Philips Healthcare
Libby Rollinson, MSN, RN Director, Content Solutions, Enterprise
Information Solutions McKesson
Workgroup Members
Guiding Principles for Big Data in Nursing Key Recommendations
• Promote Standards and Interoperability
• Advance Quality eMeasures
• Leveraging Nursing Informatics Experts
Read the full white paper at
www.himss.org/Big10
Promote Standards and Interoperability
Promote Standards and Interoperability
Nurses should…
Promote standardized terminologies that address the documentation needs of the entire care team regardless of care setting
– Use ANA-recognized nursing terminology that is mapped to national standards i.e. SNOMED CT or LOINC
Recommend research-based assessment scales and instruments that are standardized through an international consensus body
– Lack of standardization makes comparison of data challenging and adds to the burden of cost for copyright permissions and/or licensing of such instruments.
Promote Standards and Interoperability
Nurses should…
Recommend ANA recognized nursing terminologies be consistently updated
– And made available to international standards organizations for translation and complete, comprehensive mapping
Promote consistent use of discrete data elements in support of research, analytics and knowledge generation
– Minimize use of free text documentation. When ‘within defined limits’ is used, discrete data elements should be stored within the EHR
• Shift to the use of eMeasures
• Need to review the integrity of the data
• Failure will result in inaccurate reporting and potentially financial risk
Advance Quality eMeasures
Advance Quality eMeasures
Nurses should…
Support the development and design of quality eMeasures
– Ensure the data is collected, and measured within the clinician's workflow, not as additional documentation
Paper measure sets must be evaluated for appropriateness
– Expectations should be set for which data is collected, how the data are collected and the required terminologies to be used.
Nurses should…
Participate in programs that define and promote new quality eMeasures
– Include time for testing and piloting with defined timeframes that consider all stakeholders
Clinical quality eMeasures must support evidence-based, cost effective care
– That care follows clinical practice guidelines and minimizes the negative impact on clinicians' workflow.
Advance Quality eMeasures
Leverage Nursing Informatics Experts
• ANA recognized Nursing Informatics as a specialty in 1992
• Yet not been widely utilized or maximized to their fullest potential
• Needed to support the cognitive interaction between the nurse, the nursing process, data, patients and technology
American Nurses Association (2015). Nursing Informatics:
Scope and Standards of Practice, Second Edition. Silver
Spring, MD: nursesbooks.org
Nurses should….
• Utilize nurse informaticists who provide valuable insight into concept representation, design, implementation, and optimization of health IT to support evidence-based practice, research, and education
• Hire nurse informaticists who have formal informatics training, education, and certification
Leverage Nursing Informatics Experts
Research – Bridge the Gap
Financial
Data
Benchmark
Data
Health Plan Data
Device Data Monitors, Vents, Smart Pumps
EHR Data
Claims Data
Staffing Data
Medication Data
Moving to a Learning Health System
Data-driven Discovery (Machine Learning)
Discovery of New “Categories”
Clustering and Classification
Dimensionality Reduction
Modeling
Causal Link vs. Association Analysis
The Art & Science of Nursing