1
Using Data Science to Influence Population HealthSession #NI3, February 19, 2017
Karen A. Monsen, PhD, RN, FAAN, Associate Professor
University of Minnesota School of Nursing
2
Speaker Introduction
Karen A. Monsen, PhD, RN, FAANAssociate Professor
University of Minnesota School of Nursing
• Co-director, Center for Nursing Informatics
• Director, Omaha System Partnership
• DNP Specialty Coordinator, Nursing Informatics
• Affiliate faculty, Institute for Health Informatics
3
Conflict of Interest
Karen A. Monsen, PhD, RN, FAAN
Has no real or apparent conflicts of interest to report.
4
Agenda
• Population Health, Data Science, and the Voice of Nursing
• Robust nursing information
• Cutting edge methods
• Value of nursing
• Questions
5
Learning Objectives
• Outline how large, robust, well-coordinated data sets can be used to
influence outcomes in populations
• Describe how pattern visualization and other data science methods can be
used by nurses to affect outcomes
• Illustrate the importance and value of nurses in managing the care of patient
populations
6
Population Health Value and Health IT
During this session you'll hear how nurses
can use and analyze large data sets to
influence outcomes in patient populations.
T: Treatment/clinical nursing data capture
E: Electronic data use in population health
P: Population management potential
S: Savings r/t improved data management
7
Part 1: Population Health, Data Science, and the Voice of Nursing
8
Population Health, Data Science, and the
Voice of Nursing• What is Population Health?
Population Health (or Total Population Health) is the health outcomes of a group of individuals, including the distribution of such outcomes within the group. It is an approach to health that aims to improve the health of an entire human population.
Experts offer different perspectives about referring to patient populations; some suggest we should use the term population health management.
Research using large datasets reflect patient populations; however, some may be population based if they capture an entire population of interest (e.g. all women of childbearing age in a jurisdiction).
Kindig, D. (2015). Health Affairs Blog: What are we talking about when we talk about population health? Available
at: http://healthaffairs.org/blog/2015/04/06/what-are-we-talking-about-when-we-talk-about-population-health/
9
Population Health, Data Science, and the
Voice of Nursing• What is Data Science?
• Leveraging technology in research design and methods
• Inform hypothesis generation and testing
• Able to handle large datasets
• Requires teams of individuals with clinical domain expertise as methods and statistical skills
Image from Abdelbarre Chafik available at https://www.quora.com/What-is-data-science
10
Population Health, Data Science, and the
Voice of Nursing• What is the Voice of Nursing?
• In the 1960s and 70s, the advent of computerization in healthcare sparked a quest to codify nursing knowledge for purposes of giving voice to nursing in the EHR
• Implementation of standardized nursing languages in EHRs remains a national priority
11
Part 2: Robust Nursing Information
12
Nursing Data Nursing Context DataNursing Minimum Data Sethttp://www.nursing.umn.edu/prod/groups/nurs/@pub/@nurs/documents/asset/nurs_71413.pdf
a minimum set of elements of information with uniform definitions and categories concerning the specific dimensions of nursing, which meets the information needs of multiple data users in the health care system.
• Client characteristics & outcomes
• Nursing assessments & interventions
Nursing Management Minimum Data Sethttp://www.nursing.umn.edu/icnp/usa-nmmds/
core essential data needed to support the administrative and management information needs for the provision of nursing care. The standardized format allows for comparable nursing data collection within and across organizations.
• Nurse and health system characteristics
• Nurse and health system credentials 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. 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.
Robust nursing information
13
Recognized Nursing TerminologiesAmerican Nurses Association
Terminology Nursing Specific Items from the NMDS
Nursing Problem Nursing Intervention Nursing Outcome Nursing Intensity
Nursing Specific Terminologies
NANDA (1992) x
NIC (1992) x
NOC (1997) x
The above three terminologies must be used together to obtain information about the nursing problem (diagnosis), intervention and outcome. The below terminologies all
have terms for the nursing problem, intervention, and outcome.
CCC (HHCC) (1992) x x x
PNDS (1997) x x x
ICNP (2000) x x x
Interdisciplinary Terminologies
SNOMED-CT (1999) x x x
SNOMED-CT Nursing Subset x
LOINC (2002) x
Omaha System (1992) x x x
Sewell, J. P. & Thede, L. Q. (2012). Nursing and Informatics: Opportunities and Challenges. Nursing Documentation in the
Age of the EHR. Available at: http://dlthede.net/informatics/Chap16Documentation/anarecterm.html
Robust nursing information
14
Martin KS. (2005). The Omaha System: A key to practice, documentation, and information
management(Reprinted 2nd ed.). Omaha, NE: Health Connections Press.
Robust nursing information
15
Big Data Laboratory• 2010: Dean Delaney invited the Omaha System Partnership for
Knowledge Discovery and Healthcare Quality within the University of Minnesota Center for Nursing Informatics
– Scientific teams
– Affiliate members
– Data warehouse
• 2010: Dean Delaney invited the Omaha System
Partnership for Knowledge Discovery and Healthcare
Quality within the University of Minnesota Center for
Nursing Informatics
– Scientific teams
– Affiliate members
– Data collaborative
Robust nursing information
16
Prototype Dashboard of SBDH Data for a Single Patient (copyright Kesler & Monsen, 2016)
Robust nursing information
17
Robust nursing information
Prototype Dashboard of SBDH Data for a Patient Population (copyright Kesler & Monsen, 2016)
18
Part 3: Cutting Edge Methods
19
Using Data Visualization to Detect Client Risk Patterns
Key:• Colors = problems
• Shading = risk
• Rings = Knowledge, Behavior, and Status
• Tabs = signs/symptoms
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.
• Documentation patterns suggest
a comprehensive, holistic nursing
assessment.
• The presence of mental health
signs and symptom tends to be
associated with more problems
and worse outcomes
Cutting edge methods
20
Using Data Visualization to Detect Nursing Intervention Patterns
Key:
• Colors = problems
• Shading = actions (categories)
• Height = frequency
• Point on x-axis = one month
Monsen, K. A., Peterson, J. J., Mathiason, M. A., Kim, E., Votova, B., & Pieczkiewicz, D. S. (2017). Discovering public health nurse–specific
family home visiting intervention patterns using visualization techniques. Western Journal of Nursing Research, 39, 127-146. Streamgraph
development funded by a gift from Jeanne A. and Henry E. Brandt.
Cutting edge methods
21
PHN Signature Styles?
Cutting edge methods
22
Data Quality Issue vs. Signature?
Cutting edge methods
23
Heatmap Visualization of SBDH IndexSB
DH
Item
Su
bgr
ou
ps
Pro
po
rtio
n o
f th
e sa
mp
le (
N=
42
63
)
mar
ried
(n
=9
14
)
min
ori
ty (
n=
24
35
)
low
/no
inco
me
(n=
28
12
)
able
to
bu
y o
nly
nec
essi
ties
(n
=3
40
)
dif
ficu
lty
bu
yin
g n
eces
siti
es (
n=
37
4)
sad
nes
s/h
op
eles
snes
s/d
ecre
ased
sel
f-
este
em (
n=
66
9)
loss
of
inte
rest
/in
volv
emen
t in
acti
viti
es/s
elf-
car
e (n
=1
94
)
dif
ficu
lty
man
agin
g st
rss
(n=
51
)
atta
cked
ver
bal
ly (
n=
12
9)
fear
ful/
hyp
ervi
gila
nt
beh
avio
r (n
=3
8)
con
sist
ent
neg
ativ
e m
essa
ges
(n=
80
)
assa
ult
ed s
exu
ally
(n
=6
8)
wel
ts/b
ruis
es/b
urn
s/o
ther
inju
ries
(n
=3
4)
abu
ses
alco
ho
l (n
=9
0)
smo
kes/
use
s to
bac
co p
rod
uct
s (n
=4
8)
0 0.07 0.17
1 0.20 0.32 0.13 0.09 0.03 0.01 0.02 0.03 0.01 0.03
2 0.32 0.36 0.31 0.35 0.11 0.09 0.14 0.07 0.06 0.07 0.03 0.03 0.03 0.06 0.17 0.01
3 0.25 0.10 0.34 0.34 0.33 0.26 0.29 0.23 0.10 0.14 0.13 0.15 0.29 0.03 0.24 0.01
4 0.10 0.03 0.15 0.15 0.35 0.35 0.03 0.29 0.35 0.29 0.16 0.24 0.23 0.29 0.23 0.31
5 to 10 0.05 0.02 0.08 0.08 0.19 0.29 0.25 0.39 0.49 0.48 0.68 0.59 0.46 0.44 0.34 0.46
Substance useIncome Mental health Abuse
Cutting edge methods
Monsen, K. A., Brandt, J. K., Brueshoff, B., Chi, C. L., Mathiason, M. A., Swenson, S. M., & Thorson, D. R. (in press). Social determinants and
health disparities associated with outcomes of women of childbearing age receiving public health nurse home visiting services. JOGNN.
24
Pattern Discovery: Health Disparities
Pattern Discovery: Alcohol Abuse
Cutting edge methods
Monsen, K. A., Brandt, J. K., Brueshoff, B., Chi, C. L., Mathiason, M. A., Swenson, S. M., & Thorson, D. R. (in press). Social determinants and
health disparities associated with outcomes of women of childbearing age receiving public health nurse home visiting services. JOGNN.
25
Data-DrivenInterventionClustersRelationships between
four intervention
grouping/clustering
methods for
wound care.
Monsen, K. A., Westra, B. L., Yu, F., Ramadoss, V. K., & Kerr, M. J. (2009). Data
management for intervention effectiveness research: Comparing deductive and
inductive approaches. Research in Nursing and Health, 32(6), 647-656.
Cutting edge methods
26
Part 4: The Value of Nursing
27
Examining the Value of Nursing by Comparing Intervention Modeling Approaches for Elderly Home Care Patients
Monsen, K. A., Westra, B. L., Oancea, S. C., Yu, F., & Kerr, M. J. (2011). Linking home care interventions and hospitalization outcomes
for frail and non-frail elderly patients. Research in Nursing and Health, 34(2), 160-168.
Value of nursing
28
Examining the Value of Nursing for Hospitalization Outcomes Using Logistic Regression
• Too little care may result in hospitalization when patients have more intensive needs
– Frail elders are more likely to be hospitalized if they have low frequencies of four skilled nursing intervention clusters
– Policy implications: advocate for additional care at home to avoid re-hospitalization
Monsen, K. A., Westra, B. L., Oancea, S. C., Yu, F., & Kerr, M. J. (2011). Linking home care interventions and hospitalization
outcomes for frail and non-frail elderly patients. Research in Nursing and Health, 34(2), 160-168.
Value of nursing
29
Examining the Value of Nursing Using a Logistical Mixed-effects Model with Nursing Data
• How do nurses and interventions contribute to variability in patient and population health?
This research is partially supported by the National Science Foundation under grant # SES-0851705, and by the Omaha System
Partnership. Monsen, K. A., Chatterjee, S. B., Timm, J. E., Poulsen, J. K., & McNaughton, D. B. (2015). Factors explaining variability in
health literacy outcomes of public health nursing clients. Public Health Nursing, 32(2), 94-100.
• Nurse (17%)
• Client (50%)
• Problem (17%)
• Intervention (17%)
• Client age was significantly positively associated with knowledge benchmark attainment in all models
Value of nursing
30
Examining the Value of Nursing Using Generalized Estimating Equations for Cohort Comparison
• Mothers with intellectual disabilities have twice as many problems as mothers without intellectual disabilities
• Receive more public health nursing service
– Twice as many encounters and interventions
• Show improvement in all areas
– Do not reach the desired health literacy benchmark in Caretaking/parenting
• Policy implications: allocate sufficient funding for services
Monsen, K. A., Sanders, A. N., Yu, F., Radosevich, D. M, & Geppert, J. S. (2011). Family home visiting outcomes for
mothers with and without intellectual disabilities. Journal of Intellectual Disabilities Research, 55(5), 484-499.
Value of nursing
31
Examining the Value of Nursing for Health Literacy Using Pattern Comparison Pre- and Post-Intervention
• 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).
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..
Value of nursing
32
Examining the Value of Nursing for Women of Childbearing Age Related to SBHD
Value of nursing
Outcomes worsen, interventions increase
Monsen, K. A., Brandt, J. K., Brueshoff, B., Chi, C. L., Mathiason, M. A., Swenson, S. M., & Thorson, D. R. (in press). Social determinants and
health disparities associated with outcomes of women of childbearing age receiving public health nurse home visiting services. JOGNN.
All subgroups show improvement
33
Examining the Value of Nursing for Problem Stabilization among Home Visiting Clients
Surv
ival D
istr
ibution F
unction
0.00
0.25
0.50
0.75
1.00
Time_To_Stab
0 250 500 750 1000 1250 1500 1750
0
00 00000
0000000
00 00 00
00000 00000 0 0 0
000
0 0 0 00 0 0 0 0 0
000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000 0000 000000000000000000000000 000 0000 00000 000 00 0000 00 0 0 000 0 0 0 0 00 0 0
0
000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000 00000000000000000000000000000000000000000000000000000000000000000000000000 0 0 000
000 000000000 0 0 00 00 0 00 0 0 00 0 0 0 00 0
000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000
0000000000000
00000000 00000 000
0000
0000000000 0
0000000 00
00 0 00 0 0
0 0 0 0 0 0
0
00000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000
0000 000000000000000000000
0 00000000 00000
000 0 0 0 00 0 0
0 0 0
0
0
00000000
0 0 0000000 0
000 0 00 000000 00 00 0 000 000000
0 0000 00
0 0 0
0 0 0
0
00000000000000000000000000000
000000000000000000000000000000000000000 0000000000000000000000 000000 0000000000000000 000000
00000 000 0000000000000 000 000000 0 00
00 0 0 0 00
0 0 0
00
000
0000000000000000000000000000000000000000000
0000 00000000000000000000000000000000000000000000000000000 0 000000000 0 0000000
00 00000000 00 00000
00 0
0 0 0 0 0
STRATA: probname=Abuse Censored probname=Abuse probname=Antepart
Censored probname=Antepart probname=Caretaki Censored probname=Caretaki
probname=Family P Censored probname=Family P probname=Income
Censored probname=Income probname=Mental H Censored probname=Mental H
probname=Residenc Censored probname=Residenc probname=Substanc
Censored probname=Substanc
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
Value of nursing
34
Correlations• Knowledge, behavior, and status
are positively correlated (p<.001)
• Signs/symptoms and
interventions are positively
correlated (p=.002)
Patterns• As interventions increase,
KBS ratings increase
• As signs/ symptoms increase,
KBS ratings decrease
Value of nursing
Examining the influence of Interprofessional Services for Adults with Complex Health Problems
35
Population Health, Data Science, and Health IT
During this session we heard how nurses can use and analyze large data sets to influence outcomes in patient populations.
T: Treatment/clinical nursing data capture is a critical first step
E: Electronic nursing data use in population health is feasible and desirable
P: Population management potential is beginning to be realized
S: Savings r/t improved data management must be measured over the long term
36
Questions
• For further information please contact me at [email protected]
• Reminder: please complete online session evaluation - thank you!