cwd 2019 - mahidol university€¦ · top 15 most popular social networking sites may 2018 top 15...
TRANSCRIPT
cwd 2019
4th International Conference on Prevention and
Management of Chronic Conditions: Innovations in
Nursing Practice, Education, and Research
Health and Nursing Informatics:
Evidence-based practice
Prof. Dr. Connie Delaney
Dean, School of Nursing, University of Minnesota
• Describe the science of informatics,
and specifically health and nursing.
• Discuss nursing and health data
resources.
• Illustrate data informed nursing
practice.
cwd 2019
Health and Nursing Informatics:
Evidence-based practice
What is informatics?
• Science of how to use data, information and knowledge to improve
human health and the delivery of health care services
• Includes information & communications technology (ICT)
• Supports improvements in the safety, quality, effectiveness and
efficiency of care
• Bioinformatics- clinical- pubic health informatics, microscopic-
macroscopic, translational informatics, consumer health.
www.amia.org cwd 2019
The Data Trilogy
Data Analytics (DA) is the science of
reporting and analyzing raw data with the purpose of drawing conclusions about that information.
Data Science is an interdisciplinary field about
processes and systems to extract knowledge orinsights from data in various forms. It is a is a continuationof data analysis fields such as statistics, machine learning, data mining, and predictive analytics.
Big Data: Electronic data sets so large and complex
that they are difficult (or impossible) to manage with traditional software and/or hardware.
Raghupathi and Raghupathi. (2014) Big data analytics in healthcare: promise and potential. Health Information Science and Systems,
2:3 http://www.hissjournal.com/content/2/1/3cwd 2019
Big Data Research
• Ability to analyze vast amounts of data about a topic rather than just use smaller sets.
• Willingness to embrace data's real-world messiness rather than privilege exactitude.
• Growing respect for correlations rather than only a continuing quest for causality.
Viktor Mayer-Schönberger and Kenneth Cukier: Big Data - A revolution that will transform how we live, work and think; John Murray Publishers, London, 2013
cwd 2019
Contexts for Big Data Science
- National & Global -
• Learning Health System (LHS)
• Triple/Quadruple aim
• Precision medicine and person-centric care
• Connected communities
• Research/Scholarship:– Clinical Translational Science Awards
– Patient Centered Outcomes Research Institute (PCORI)
• Global connectivity
cwd 2019
Big Data Drivers • Electronic Health Record
• Health Insurance Claims
• Quantified Self Movement (1
trillion sensors)
• Geo-spatial Data
• Intranet of Things (IoT)
• Social Media (1.8 billion
subscribers)
• eMobile Health (6 billion
cellphones)
• Whole Gene Sequencing (6
billion diploid pairs/genome)
Topol, E. (2015) The Patient Will See You
Now. Basic Books, New York.
cwd 2019
Top 15 Most Popular Social Networking Sites
May 2018Top 15 Most Popular Social Networking Sites as derived from our eBizMBA Rank which is a
continually updated average of each website's Alexa Global Traffic Rank, and U.S. Traffic Rank.
Estimated monthly visitors.
http://www.ebizmba.com/articles/social-networking-websites
1,500,000,000 + 1,499,000,000 + 400,000,000 + 275,000,000 + 250,000,000
100,000,000
cwd 2019
Objectives
• Describe the science of informatics,
and specifically health and nursing.
• Discuss nursing and health data
resources.
• Illustrate data informed nursing
practice.
cwd 2019
Health and Nursing Informatics:
Evidence-based practice
Public and Government Data Sets
•CMS – Medicare Claims Public Use Files
•CDC- National Center for Health Statistics
•AHRQ – Agency for Healthcare Research and Quality
cwd 2019
Health Affairs
Optum Labs: Building A Novel
Node In The Learning Health
Care SystemPaul J. Wallace,*, Nilay D. Shah, Taylor Dennen, Paul A. Bleicher
and William H. Crown
Abstract
Unprecedented change in the US health care system is being
driven by the rapid uptake of health information technology
and national investments in multi-institution research
networks comprising academic centers, health care delivery
systems, and other health system components. An example
of this changing landscape is Optum Labs, a novel network
“node” that is bringing together new partners, data, and
analytic techniques to implement research findings in
health care practice.
Partners• Mayo Clinic• AARP• AMGA • Boston Scientific • Boston University• Lehigh Valley• Pfizer Inc. • Rensselaer Polytechnic• Tufts Medical Center • UM School of Nursing• Harvard Medical School • Medica Research Institute• Merck • University of Maryland• The Brown University School of
Public Health• Johns Hopkins Bloomberg School
of Public Health• MIT Sloan School of
Management • Novartis Pharmaceuticals
Corporation• ResMed
http://content.healthaffairs.org/content/33/7/1187.full?ijkey=b8qVnVJW
pdA4s&keytype=ref&siteid=healthaff cwd 2019
UnitedHealthcare
UnitedHealth Group: A diversified managed health care company offering a spectrum of products and services to 70 million individuals through two operating businesses: UnitedHealthcare and Optum.
• UnitedHealthcare: The largest single health carrier in the United States.
• UnitedHealthcare Optum: – One of the largest health information, technology,
services and consulting companies in the world.
– Population health management, care delivery and improving the clinical and operating elements of the system.
cwd 2019
Data Categories
• Demographics
• Pharmacy claims
• Physician and facility claims
• Lab test results
• Socioeconomic data
• EHR data (clinical)
• Health risk appraisal
• Date of death
cwd 2019
Optum Labs Data Warehouse
• Approximately 150 million lives (40 million EHR)
• 3400 fields per life
• Claims and electronic health records data (~25% of data is linked)
• 20 + years of data
• Includes Medicare Advantage
cwd 2019
Partners Sample of Academic/Industry
Partnerships
Funding
Source
Otolaryngology Prediction model: causal factors in patients presenting with
dizziness
NIH
Nursing Prediction model: Patients experiencing adverse effects of statin
therapy
UM Internal
Prediction model: Cardiovascular disease risk prediction using
EHR/claims data
UM Internal
AHC Seed
Symptom management of liver transplant patients RO1
Prevention of urinary tract infections in young women RO1
Public Health Prediction model: Diffusion of knowledge from clinical trials to
practice.
NIH
Comparative effectiveness of extended oral anticoagulant use PCORI
Contemporary Venous Thromboembolism Treatment - NIH NIH
Neurosurgery Comparative effectiveness between surgical and non-surgical
intervention of low back pain.
NIH
cwd 2019
Vision for Data in a
Clinical Data Warehouse
Clinical DataNMDS
Management Data
NMMDS
Other Data Sets
Continuum of Care
cwd 2019
Celebrating our
foundation for
“Big Data/Data
Science”
Global standards
eMeasures
EHRs
Magnet
Resources
Workforce
cwd 2019
National Center Expanded Interprofessional Learning Continuum
Model
IOM. Measuring the Impact of Interprofessional Education and Collaborative Practice and Patient Outcomes
Enabling or Interfering Factors
Professional Culture
Enabling or Interfering Factors
Professional Culture Institutional Culture
Financing PolicyWorkforce Policy
Nexus Learning ContinuumEducation and Clinical Learning Environments
(Formal and Informal)
Foundational Education Graduate Education Continuing Professional Development
Interprofessional Education
Health Outcomes(Quadruple Aim)
Learning Outcomes System Outcomes
Practices for promoting, incenting, rewarding IPECP
Changes to care delivery structures + processes to
support efficient high-quality, patient-centered, IP team-based
care
Cost Effectiveness
Patient Experience
Individual Health
Population Health
Cost
Practices for protecting and enhancing provider well-
being
Reactions
Attitudes /Perceptions
Knowledge / Skills
Collaborative Behavior
Performance in Practice(individual and team)
IPE Core Data Set(Intervals)
Interprofessional Education Learning
Environment Survey
Interprofessional Clinical Learning
Environment Survey
Teamness (ACE-15)
Interprofessional Competencies
(ICCAS)
Critical Incidents
HealthOutcomes
Partnership History, Structure
Structural characteristics of
education institutions
Structural characteristics of practice settings
Nexus Program Proposal (Baseline)
cwd 2019
Secure, HIPAA and FERPA compliant
infrastructure and data sharing environment
focused on interprofessional practice and
education, housed at the University of Minnesota
Standard measures applicable and comparable
across environments exploring key elements of
education, practice and the Nexus
Easy access to data through dashboards and
standardized reports; additional analysis available
through advanced analytics, big data and
comparable data sets
Authorized users have the ability to manage
users access, review Nexus Program status,
and send invitations to other users to join
their Nexus Programs
Program Management
National Center IPE Information Exchange &
Core Data Set
Informatics Driven Dashboard
IPE Core Data Set
National Center Data Repository
cwd 2019
Network Members
cwd 2019
Objectives
• Describe the science of informatics,
and specifically health and nursing.
• Discuss nursing and health data
resources.
• Illustrate data informed nursing
practice.
cwd 2019
Health and Nursing Informatics:
Evidence-based practice
Comparison of Observational Studies to Secondary Analysis of Big Data
Observational Studies
• Few data sources
• Limited set of variables (10’s –1000’s)– Demographics
– Clinical
– Insurance claims
– Census
• Small number of hypothesis
• Long, expensive data collection, analysis and evaluation cycle
Secondary Data Analysis
• Multi-source, data mash-up
• Many variables (> million)– EHR
– Imaging
– Social media
– Genomic
• Large number of hypothesis
• Short data collection, analysis and evaluation cycle
cwd 2019
Knowledge Discovery: Data Mining
• The computational process of discovering patterns in large, complex datasets.
• Goal of KDD: Extract information and transform it into an understandable structure (knowledge).
• Exploratory studies
• Pattern recognition
• Data visualization
cwd 2019
Nursing Data, Visualization
Techniques, & Home Health Care
• Karen A. Monsen, PhD, RN, FAAN
Professor and Director, Center for
Nursing Informatics & Scientific Team
• Omaha System Partnership for
Knowledge Discovery and Healthcare
Quality Data Repository
cwd 2019
Using Pattern Comparison Pre- and Post-Intervention to
Demonstrate Intervention Effectiveness
Knowledge scores across problems over time
– Pre-intervention, patterns by race/ethnicity
– Post-intervention, patterns by problem
Benchmark = 3
Monsen, K. A., Areba, E. M., Radosevich, D. M., Brandt, J. K., Lytton, A. B., Kerr, M. J., Johnson, K. E., Farri, O, & Martin, K. S. (2012).
cwd 2019
Using Kaplan-Meier Curves to Depict
Problem Stabilization
This research was supported by the National Institute of Nursing Research (Grant #P20 NR008992; Center for Health Trajectory Research). The
content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institute of Nursing Research
or the National Institutes of Health. Monsen, K. A., McNaughton, D. B., Savik, K., & Farri, O. (2011). Problem stabilization: A metric for problem
improvement in home visiting clients. Applied Clinical Informatics, 2, 437-446 http://dx.doi.org/10.4338/ACI-2011-06-RA-0038
cwd 2019
Using Data Visualization to Detect
Client Risk PatternsMonsen, K. A. et al., 2014
Each image (sunburst) was created
in d3 from public health nursing
assessment data for a single
patient. Data were generated by
use of the Omaha System signs
and symptoms and Problem Rating
Scale for Outcomes
Key:
• Colors = problems
• Shading = risk
• Rings = Knowledge, Behavior, and
Status
• Tabs = signs/symptoms
Documentation patterns suggest a
comprehensive, holistic nursing
assessment.
Kim et al. found that the presence
of mental health signs and
symptom tends to be associated
with more diagnostic problems and
worse patient condition
Kim, E., Monsen, K. A., Pieczkiewicz, D. S. (2013). Visualization of Omaha System data enables data-
driven analysis of outcomes. American Medical Informatics Association Annual Meeting, Washington D. C.
Funded by a gift from Jeanne A. and Henry E. Brandt.cwd 2019
Using Data Visualization to Detect
Nursing Intervention Patterns
Each image (streamgraph)
was created in d3 from
longitudinal public health
nursing intervention data for a
single patient. Data were
generated by use of the
Omaha System in clinical
documentation
Key:
• Colors = problems
• Shading = actions (categories)
• Height = frequency
• Point on x-axis = one month
From 403 images, 29 distinct
patterns were identified and
validated by clinical experts
Documentation patterns
suggest both a unique nurse
style and consistent patient-
specific intervention tailoring
Monsen, K.A., Hattori, K., Kim, E., Pieczkiewicz, D. (In review). Using visualization methods
to discover nurse-specific patterns in nursing intervention data.
Streamgraph development funded by a gift from Jeanne A. and Henry E. Brandt.
Monsen, K. A. et al., 2014
cwd 2019
Purpose
To develop a predictive model for hospital-acquired
CAUTIs using multiple data sources
Specific Aims
Aim 1: Create a quality, de-identified dataset combining
multiple data sources for machine learning tasks
Aim 2: Develop and evaluate predictive models to find
the best predictive model for hospital-acquired CAUTI
Park, J. (2016). Developing a Predictive Model for Hospital-Acquired Catheter-
Associated Urinary Tract Infections Using Electronic Health Records and Nurse
Staffing Data. Dissertation. University of Minnesota
Acute Care – Cather Associated Urinary Tract Infection
(CAUTI) J Park
Factors Associated with CAUTI
Decision Tree model Linear Regression model
• Female
• Longer length of Stay
• Presence of rationale for
continued use of catheter
• Less total nursing hours per
patient day
• Lower percent of direct care
RNs with specialty nursing
certification
• Higher percent of direct care
RNs with BSN, MSN, or PhD
• Age ( ≥56)
• Longer length of stay
• Presence of rationale for
continued use of catheter
• Charlson comorbidity index
score ≥ 3
• Glucose lab result > 200 mg/dl
• Higher percent of direct care
RNs with associate’s degree in
nursing
• Higher percent of direct care
RNs with BSN, MSN, or PhD
Park, J. (2016). Developing a Predictive Model for Hospital-Acquired Catheter-Associated Urinary Tract
Infections Using Electronic Health Records and Nurse Staffing Data. Dissertation. University of Minnesota
Acute Care – Catheter Associated Urinary Tract
Infection (CAUTI)
A Data Mining Approach to Determine
Sepsis Guideline Impact on Inpatient
Mortality and Complications
Michael Steinbach, PhD; Bonnie L. Westra, PhD, RN, FAAN, FACMI; György J. Simon, PhD
Lisiane Pruinelli, MSN, RN, PhD-C; Pranjul Yadav, PhD-C;
Andrew Hangsleben; Jakob Johnson; Sanjoy Dey, PhD;
Maribet McCarty, PhD, RN; Vipin Kumar, PhD; Connie W. Delaney, PhD, RN, FAAN, FACMI
Support for this study is provided by NSF grant IIS-1344135 , National Center for Research Resources
of the NIH 1UL1RR033183.
cwd 2019
AimThe overall aim is to evaluate and extend evidence-based guidelines for patients with health disparities for the prevention and management of sepsis complications
1. Map EHRs data to SSC guideline recommendations
2. Estimate the compliance with the SSC guideline recommendations; and
3. Estimate the effect of the SSC individual recommendations on the prevention of in-hospital mortality and sepsis-related complications
cwd 2019
SSC guideline - Interventions
cwd 2019
Compliance with SSC GuidelinesRules Description Patient Count / %
Y N % Compl N/A
1. Was Blood Culture done? (BCulture) 126 51 71 0
2. Was Antibiotic given after Blood Culture? (Antibiotic) 99 27 79 51
3. Was Lactate checked? (Lactate) 127 50 72 0
4. Was Fluid Resuscitation done if Lactate > 4? (LactateFluid) 36 0 100 141
5. Was Blood Glucose checked? (BGlucose) 132 45 75 06. Was Insulin given if two Blood Glucose measures were > 180?
(GlucoseInsulin)
38 8 83 131
7. Was MAP checked? (MAP) 177 0 100 0
8. Was Fluid Resuscitation give if MAP < 65? (MAPFluids) 160 6 96 11
9. Was Vasopressor given if MAP < 65 after Fluid
Resuscitation? (Vasopressor)26 140 16 11
10. Was CVP checked? (CVP) 121 56 68 011. Was Fluid Resuscitation done if CVP < 2? (CVPFluids) 15 162 9 0
12. Was Albumin given if CVP < 2 after Fluid Resuscitation? (Albumin) 4 11 27 162
13. Was a Diuretic given if CVP above 12? (Diuretic) 10 71 12 96
14. Was there Respiratory Distress*? (RespDistress) 167 10 94 015. Was a ventilator given if there was Respiratory Distress?
(Ventilator)
92 75 55 10
cwd 2019
Results - Complications
Cardiovascula
r
Respiratory Kidney Cerebrovascu
lar
Death
BCulture (-0.11, 0.15) (-0.16, 0.12) (-0.15, 0.11) (-0.09, 0.20) (-0.14, 0.09)
Antibiotic (-0.16, 0.10) (-0.23, 0.13) (-0.08, 0.26) (-0.09, 0.28) (-0.21, 0.10)
Lactose (-0.05, 0.19) (-0.20, 0.07) (-0.08, 0.18) (-0.04, 0.21) (-0.12, 0.10)
BGlucose (-0.02, 0.25) (-0.02, 0.28) (-0.16, 0.14) (-0.06, 0.18) (-0.19, 0.09)
Vasopressor (-0.11, 0.27) (0.04, 0.35) (-0.20, 0.17) (-0.32, -0.07) (-0.10, 0.21)
CVP (-0.03, 0.16) (-0.06, 0.17) (-0.10, 0.14) (-0.08, 0.16) (-0.08, 0.13)
RespDistress (-0.25, 0.36) (-0.36, 0.37) (-0.14, 0.40) (-0.30, 0.37) (-0.25, 0.14)
Ventilator (0.04, 0.19) (0.08, 0.32) (-0.11, 0.09) (-0.08, 0.11) (0.03, 0.20)
CI (0.04,
0.35)
CI (0.04,
0.19)
CI (0.08,
0.32)CI (-0.32, -
0.07)
cwd 2019
Conclusions
• EHR data can be used to estimate compliance with
individual guideline recommendations
• EHR can be used to estimate the effect of the guideline
adherence on sepsis-related complications
• Some guideline recommendations are protective for
patients for certain outcomes
• Other variables may be needed to control for variation in
severity of illness or variation in practice
cwd 2019
38
z.umn.edu/bigdata
References & Resources
• NIH Big Data to Knowledge (BD2K) Workshops: https://datascience.nih.gov/bd2k/events/bd2kworkshops
• NINR Advancing Nursing Research through Data Science http://www.ninr.nih.gov/training/online-developing-nurse-scientists#.VtdHJvkrLIU
• University of Minnesota School of Nursing. Nursing Knowledge: Big Data Conference 2016: http://www.nursing.umn.edu/icnp/center-projects/big-data/2016-nursing-knowledge-big-data-science-conference/index.htm
• American Medical Informatics Association: https://www.amia.org/
• Health Information and Management Systems Society (HIMSS): http://www.himss.org/aboutHIMSS/
• Coursera: Six courses on data science: https://www.coursera.org/
• Health Catalyst Knowledge Center: https://www.healthcatalyst.com/knowledge-center/
cwd 2019
• D3 Data Driven Documents. (2016). https://d3js.org/
• Hey, T., Tansley, S., & Tolle, K. (2009). The fourth paradigm: Data intensive scientific discovery. Redmond, WA:
Microsoft Research.
• Huber D, Delaney C. The American Organization of Nurse Executives (AONE) research column. the Nursing
Management Minimum Data Set. Appl Nurs Res. 1997;10:164-165
• Kim, E., Monsen, K. A., Pieczkiewicz, D. S. (2013). Visualization of Omaha System data enables data-driven
analysis of outcomes. American Medical Informatics Association Annual Meeting, Washington D.
• Mayer-Schonberger, V. & Cukier, K. (2013) Big Data: A revolution that will transform how we live, work, and think.
Houghton Mifflin Harcourt, Boston.
• Monsen, K. A., McNaughton, D. B., Savik, K., & Farri, O. (2011). Problem stabilization: A metric for problem
improvement in home visiting clients. Applied Clinical Informatics, 2, 437-446 http://dx.doi.org/10.4338/ACI-2011-06-
RA-0038
• Monsen, K. A., Areba, E. M., Radosevich, D. M., Brandt, J. K., Lytton, A. B., Kerr, M. J., Johnson, K. E., Farri, O, &
Martin, K. S. (2012). Evaluating effects of public health nurse home visiting on health literacy for immigrants and
refugees using standardized nursing terminology data. Proceedings of NI2012: 11th International Congress on
Nursing Informatics, 614.
• Monsen, K.A., Peterson, J. J. , Mathiason, M. A., Kim, E., Lee, S., Chi, C. L., Pieczkiewicz, D. S. (2015). Data
visualization techniques to showcase nursing care quality. Computers, Informatics, Nursing, 33(10), 417-426. doi:
10/1097/CIN.000000000000190
• Tableau (2016). http://www.tableau.com/
• Werley HH. Nursing minimum data: abstract tool for standardized comparable, essential data. Am J Public Health.
1991;81(4):421–6. doi: 10.2105/AJPH.81.4.421.
cwd 2019
References & Resources
Connie White Delaney, PhD, RN, FAAN, FACMI, FNAP
• Professor & Dean | University of Minnesota School of Nursing
• [email protected] | 612.624.5959
• @conniewdelaney | @UMNNursing | LinkedIn: conniewhitedelaney
cwd 2019