Chapter 8: Clinical Decision Support
Robert Hoyt MD
Harold Lehmann MD PhD
After reviewing these slides, the viewer should be able to:
Define electronic clinical decision support (CDS)
Enumerate the goals and potential benefits of CDS
Discuss the government and private organizations supporting CDS
Discuss CDS taxonomy, functionality and interoperability
List the challenges associated with CDS
Enumerate CDS implementation steps and lessons learned
Learning Objectives
Definition: “Clinical decision support (CDS) provides clinicians, staff, patients or other individuals with knowledge and person-specific information, intelligently filtered or presented at appropriate times, to enhance health and health care.” (ONC)
Keep in mind that any resource that aids in decision making should be considered CDS. We will only consider electronic CDS.
We define clinical decision support systems (CDSSs) as the technology that supports CDS
Introduction
Early on, CDS was thought of only in terms of reminders and alerts. Now we must include diagnostic help, cost reminders, calculators, etc.
In spite of the fact that we can use the Internet’s potent search engines to answer questions, many organizations promote CDS as a major strategy to improve patient safety
Most CDS strategies involve the 5 rights (next slide)
Introduction
The right information (what): should be based on the highest level of evidence possible and adequately referenced.
To the right person (who): the person who is making the clinical decision, the physician, the patient or some other team member
In the right format (how): should the information appear as part of an alert, reminder, infobutton or order set?
Through the right channel (where): should the information be available as an EHR alert, a text message, email alert, etc.?
At the right time (when) : new information, particularly in the format of an alert should appear early in the order entry process so clinicians are aware of an issue before they complete the task
Five Rights of CDS
As early as the 1950s scientists predicted computers would aid medical decision making
CDS programs appeared in the 1970s and were standalone programs that eventually became inactive
De Dombal’s system for acute abdominal pain: used Bayes theorem to suggest differential diagnoses
Internist-1: CDS program that used IF-THEN statements to predict diagnoses
Mycin: rule-based system to suggest diagnosis and treatment of infections
Historical perspective
DxPlain: 1984 program that used clinical findings to list possible diagnoses. Now a commercial product
QMR: began as Internist-1 for diagnoses and ended in 2001
HELP: began in the 1980s at the University of Utah that includes diagnostic advice, references and clinical practice guidelines
Iliad: diagnostic program, also developed by the University of Utah in the 1980s
Historical perspective
Isabel: commercial differential diagnosis tool wit.
1. Chapter 8: Clinical Decision Support
Robert Hoyt MD
Harold Lehmann MD PhD
After reviewing these slides, the viewer should be able to:
Define electronic clinical decision support (CDS)
Enumerate the goals and potential benefits of CDS
Discuss the government and private organizations supporting
CDS
Discuss CDS taxonomy, functionality and interoperability
List the challenges associated with CDS
Enumerate CDS implementation steps and lessons learned
Learning Objectives
2. Definition: “Clinical decision support (CDS) provides
clinicians, staff, patients or other individuals with knowledge
and person-specific information, intelligently filtered or
presented at appropriate times, to enhance health and health
care.” (ONC)
Keep in mind that any resource that aids in decision making
should be considered CDS. We will only consider electronic
CDS.
We define clinical decision support systems (CDSSs) as the
technology that supports CDS
Introduction
Early on, CDS was thought of only in terms of reminders and
alerts. Now we must include diagnostic help, cost reminders,
calculators, etc.
In spite of the fact that we can use the Internet’s potent search
engines to answer questions, many organizations promote CDS
as a major strategy to improve patient safety
Most CDS strategies involve the 5 rights (next slide)
Introduction
3. The right information (what): should be based on the highest
level of evidence possible and adequately referenced.
To the right person (who): the person who is making the clinical
decision, the physician, the patient or some other team member
In the right format (how): should the information appear as part
of an alert, reminder, infobutton or order set?
Through the right channel (where): should the information be
available as an EHR alert, a text message, email alert, etc.?
At the right time (when) : new information, particularly in the
format of an alert should appear early in the order entry process
so clinicians are aware of an issue before they complete the task
Five Rights of CDS
As early as the 1950s scientists predicted computers would aid
medical decision making
CDS programs appeared in the 1970s and were standalone
programs that eventually became inactive
De Dombal’s system for acute abdominal pain: used Bayes
4. theorem to suggest differential diagnoses
Internist-1: CDS program that used IF-THEN statements to
predict diagnoses
Mycin: rule-based system to suggest diagnosis and treatment of
infections
Historical perspective
DxPlain: 1984 program that used clinical findings to list
possible diagnoses. Now a commercial product
QMR: began as Internist-1 for diagnoses and ended in 2001
HELP: began in the 1980s at the University of Utah that
includes diagnostic advice, references and clinical practice
guidelines
Iliad: diagnostic program, also developed by the University of
Utah in the 1980s
Historical perspective
Isabel: commercial differential diagnosis tool with information
5. inputted as free text for from the EHR. Inference engine uses
natural language processing and supported by 100,000
documents
SimulConsult: diagnostic program based on Bayes probabilities.
Predictions can also include clinical and genetic information
SnapDx: free mobile app that performs diagnostic CDS for
clinicians. It is based on positive and negative likelihood ratios
from medical literature. App covers about 50 common medical
scenarios
Historical perspective
CDS Benefits and GoalsBenefits and GoalsDetailsImprovement
in patient safetyMedication alerts
Improved orderingImprovement in patient careImproved patient
outcomes
Better chronic disease management
Alerts for critical lab values, drug interactions and allergies
Improved quality adjusted life years (QALY)Reduction in
healthcare costsFewer duplicate lab tests and images
Fewer unnecessary tests ordered
Avoidance of Medicare penalties for some readmissions
Fewer medical errors
Increased use of generic drugs
Reduced malpractice
6. 9
CDS Benefits and GoalsCDS Benefits and
GoalsDetailsDissemination of expert knowledgeSharing of best
evidence
Education of all staff, students and patientsManagement of
complex clinical issuesUse of clinical practice guidelines, smart
forms and order sets
Interdisciplinary sharing of information
Case managementMonitoring clinical detailsReminders for
preventive services
Tracking of diseases and referralsImprovement of population
healthIdentification of high-cost/needs patients
Mass customized messagingManagement of administrative
complexitySupports coding, authorization, referrals and care
managementSupport clinical researchAbility to identify
prospective research subjects
Institute of Medicine (IOM): they promoted “automated clinical
information and CDS”
AMIA: developed 3 pillars of CDS in 2006—best available
7. evidence, high adoption and effective use and continuous
improvement.
ONC: has funded research to promote excellent CDS and
sharing possibilities
AHRQ: also funded multiple CDS research projects and
initiatives
Supporting Organizations
HL7: has a CDS working group and developed FHIR standards,
discussed later
National Quality Forum (NQF): developed a CDS taxonomy
Leapfrog: they have promoted both CPOE and CDS
HIMSS: Their EMR Adoption Model rates EMRs from 0-7. Full
use of CDS qualifies as level 6
CMS: Meaningful Use, Stage 1 and 2 includes CDS measures
Supporting Organizations
8. Two phases of CDS: knowledge use and knowledge management
Knowledge Use. Involves these sequential steps:
Triggers are an event, such as an order for a medication >>
Input data refers to information within, for example the EHR,
that might include patient allergies >>
Interventions are the CDS actions such as displayed alerts >>
Action steps might be overriding the alert or canceling an order
for a drug to which the patient is allergic
CDS Methodology
Knowledge management involves:
Knowledge acquisition: acquire expert internal (EHR data) or
external data (e.g. Apache scores) for CDS
Knowledge representation. Use expert information, integrate it
with an inference engine and communicate it to the end user,
e.g. an alert (next slide)
Knowledge management (to follow)
CDS Methodology
9. Knowledge representation:
Configuration: knowledge is represented by choices made by the
institution
Table-based: rules are stored in tables, such that if a current
drug on a patient is in one row and an order for a second
inappropriate drug is stored in the same row, an alert is
triggered for the clinician
Rules based: knowledge base has IF-THEN statements; if the
patient is allergic to sulfa and sulfa is order then an alert is
triggered. Earlier CDS programs, such as Mycin, were rule
based
CDS Methodology
Knowledge representation (Cont.)
Bayesian networks: based on Bayes Theorem of conditional
probabilities it predicts future (posterior) probability based on
pre-test probability or prevalence. In spite of assuming that the
findings are supposed to be independent (such as signs and
symptoms), the Bayesian approach works very well and is
commonly employed in medicine. Formula is included below
CDS Methodology
10. The previous knowledge representation methods were based on
known data so they would be labelled “knowledge based CDS”.
If CDS is based on data mining-related techniques it would be
referred to as “non-knowledge based CDS”
Data mining (machine learning) algorithms have to be
developed and validated ahead of actual implementation. This
approach is divided into supervised and unsupervised learning
(next slide)
CDS Methodology
Supervised learning: assumes the user knows the categories of
data that exist, such as gender, diagnoses, age, etc. If the target
(outcome or dependent variable) is categorical (nominal, such
as lived or died) the approach will be called a classification
model. If the target is numerical (such as size of tumor, income,
etc.) the this is a regression model (see chapter on Introduction
11. to Data Science)
CDS Methodology
Supervised learning:
Neural networks: configured like a human neuron. The model is
trained until the desired target output is close to the desired
target. This is not intuitive and requires great expertise. See
figure to the right
CDS Methodology
Supervised learning:
Logistic regression: in spite of the name regression it is most
commonly used where the desired output/target is binary
(cancer recurrence, no cancer recurrence). Multiple predictors
are inputted, such as age, gender, family history, etc. and odds
ratios are generated. This is the gold standard for much of
predictive analytics
12. CDS Methodology
Decision trees: can perform classification or regression and are
the easiest to understand and visualize. Trees are used by both
statisticians and machine learning programs. Below is a contact
lens decision tree
CDS Methodology
Unsupervised learning: means data is analyzed without first
knowing the classes of data to look for new patterns of interest.
This has been hugely important in looking at genetic data sets.
Cluster analysis is one of the most common ways to analyze
large data sets for undiscovered trends. It is also more complex,
requiring more expertise
Association algorithms look for relationships of interest
CDS Methodology
13. Knowledge maintenance: means there is a need to constantly
update expert evidence based information. This task is difficult
and may fall to a CDS committee or technology vendor
CDS Methodology
CDS developers have struggled for a long time with how to
share knowledge representation with others or how to modify
rules locally. Standards were developed to try to overcome
these obstacles:
Arden syntax: represented by medical logic modules (MLMs)
that encode decision information. Ironically, the information
can’t be shared because institution specific coding resides
within curly braces { } in the MLM. This approach was doomed
and is known as the “curly brace problem”
CDS Standards
14. GELLO: can query EHRs for data to create decision criteria.
Part of HL7 v. 3
GEM: permits clinical practice guidelines to be shared in an
XML format, as an ASTM standard
GLIF: enables sharable and computable guidelines
CQL: draft HL7 standard to be used in XML format for
electronic clinical quality measures (eCQMs)
Infobuttons: can be placed in workflow where decisions are
made with recommendations
CDS Standards
Fast Healthcare Interoperability Resources (FHIR): developed
by HL7 there is great hope that this standard will solve many
interoperability issues.
It is a RESTful API (like Google uses) that uses either JSON or
XML for data representation
It is data and not document centric; so a clinician could place a
15. http request to retrieve just a lab value from EHR B, instead of
e.g. a CCDA. EHR can also request decision support from
software on a CDS server
Approximately, 95 resources have been developed to handle the
most common clinical data issues
CDS Standards
CDSSs can be classified in multiple ways:
Knowledge and non-knowledge based systems
Internal or external to the EHR
Activation before, during or after a patient encounter
Activated automatically or on demand
Alerts can be interruptive or non-interruptive
The next slides show a taxonomy based on CDS goals and
benefits mentioned earlier
CDS Functionality
CDS Functionality
16. CDS Functionality
(Function and Examples cont.)
Ordering facilitators:
Order sets are EHR templated commercial or home grown orders
that are modified to follow national practice guidelines. For
example, a patient with a suspected heart attack has orders that
automatically include aspirin, oxygen, EKG, etc.
Therapeutic support include commercial products such as
TheradocⓇ and calculators for a variety of medical conditions
CDS Functionality
17. Order facilitators (cont.)
Smart forms are templated forms, generally used for specific
conditions such as diabetes. They can include simple check the
boxes with evidence based recommendations
Alerts and reminders are the classic CDS output that usually
reminds clinicians about drug allergies, drug to drug
interactions and preventive medicine reminders. This is
discussed in more detail in the chapter on EHRs and the chapter
on patient safety
CDS Functionality
Relevant information displays
Infobuttons, hyperlinks, mouse overs: common methods to
connect to evidence based information
Diagnostic support: most diagnostic support is external and not
integrated with the EHR; such as SimulConsult
Dashboards: can also be patient, and not population level, so
they can summarize a patient’s status and thereby summarize
and inform the clinician about multiple patient aspects
CDS Functionality
18. Currently, there is no single method for CDS knowledge can be
universally shared. The approach has been to either use
standards to share the knowledge or use CDS on a shared
external server
Socratic Grid and OpenCDS are open source web services
platforms that support CDS
The FHIR standard appears to have the greatest chance for
success, but it is still early in the CDS game to know
CDS Sharing
CDS Implementation steps
19. CDS Implementation steps (cont.)
CDS Implementation steps (cont.)
General: exploding medical information that is complicated and
evolving. Tough to write rules
Organizational support: CDS must be supported by leadership,
IT and clinical staff. Currently, only large healthcare
organizations can create robust CDSSs
Lack of a clear business case: evidence shows CDS helps
improve processes but it is unclear if it affects behavior and
20. patient outcomes. Therefore, there may not be a strong business
case to invest in CDSSs
CDS Challenges
37
Unintended consequences: alert fatigue
Medico-legal: adhering to or defying alerts has legal
implications. Product liability for EHR vendors
Clinical: must fit clinician workflow and fit the 5 Rights
Technical: complex CDS requires an expert IT team
Lack of interoperability: must be solved for CDS to succeed
Long term CDS benefits: requires long term commitment and
proof of benefit to be durable
CDS Challenges
38
Lessons Learned
21. Lesson Learned (cont.)
This table came from multiple references found in the textbook
The future of Meaningful Use is unclear so there is no obvious
CDS business case for clinicians, hospitals and vendors
If the FHIR standard makes interoperability easier we may see
new CDS innovations and improved adoption
Future Trends
22. CDS could potentially assist with clinical decision making in
multiple areas
While there is widespread support for CDS, there are a
multitude of challenges
CDS is primarily achieved by larger healthcare systems
The evidence so far suggests that CDS improves patient
processes and to a lesser degree clinical outcomes
Conclusions
Marketing Analysis
BASKETBALLS AT BROOKLYN RETAIL STORE
Basketball 1
WI LSON COU RTS I DE B ROOKLYN
N ETS OUTDOOR RU B B E R
BAS KETBALL
Show off your love for the Brooklyn Nets
23. with this official Nets branded basketball.
This ball is constructed from rubber for
maximum bounce, making it ideal for street
ball. It has an exclusive dual-density cover
for a soft, cushioned feel with wrap-around
channels designed for outdoor use. The ball
measures 29.5 inches and is slightly lighter
than an official NBA ball.
Basketball 2
S PALDI NG I N DOOR/OUTDOOR
BAS KETBALL
Built using a composite leather cover, the
Spalding official-size NBA basketball looks
and feels like an official NBA ball. The ball
also includes a foam-backed design with
full ball pebbling, helping it stand up to the
challenge of competitive play while
maintaining a soft, tacky feel. Best of all,
the ball is designed for use both indoor and
outdoor use, so you can bring it to the
YMCA or the playground.
PRODUCT DESCRIPTIONS
Basketball 3
26. I like to investigate numerous
options prior to purchasing
I prefer to see, touch and test a
product prior to purchasing
I typically remain attached to
one product versus shopping for
alternatives
Target Customers (%)
STRONG LY
DISAG RE E
DISAG RE E
N E ITH E R AG RE E
NOR DISAG RE E
AG RE E
STRONG LY
AG RE E
18 36 21 17 8
8 28 38 14 12
12 16 23 32 17
12 14 18 21 35
28. WI LSON COU RTS I DE B ROOKLYN
N ETS OUTDOOR RU B B E R
BAS KETBALL
$19.99
WI LSON COU RTS I DE B ROOKLYN
N ETS OUTDOOR RU B B E R
BAS KETBALL
$9.99
S PALDI NG I N DOOR/OUTDOOR
BAS KETBALL
$29.99
S PALDI NG I N DOOR/OUTDOOR
BAS KETBALL
$39.99
S PALDI NG I N DOOR/OUTDOOR
BAS KETBALL
$44.99
S PALDI NG OF F ICIAL N BA
BAS KETBALL
$89.99
S PALDI NG OF F ICIAL N BA
BAS KETBALL
30. Most brands design basketballs for indoor and light outdoor use.
Few brands have designed basketballs around the
outdoor, street ball culture embodied in many American cities
and emulated across the country.
Brand Direction 1
REC LEAGUE
LET’S BALL.
Brand Direction 2
RUCKER PARK
WE GOT NEXT.
Rec League represents the wide array of informal basketball
cultures and
captures the essence of impromptu basketball games all across
America.
Inspired by the famous court in Harlem, Rucker Park embodies
the iconic
culture of pick-up games and their influence on basketball
culture.
Designed by Patrickss - Freepik.com Designed by Freepik
NAME:
INSTUCTOR:
DATE:
31. Assignment 3
MARKETING – MARKETING Manager Analysis
Due Date: Week 7
Note: While representative of possible situations faced by the
Brookly Nets, all scenarios in this assignment are fictional.
Real Business
For a large discount retail store like Target and Walmart, it can
be difficult to get the marketing mix just right for a given
product. There are so many products in the store fighting for the
attention of customers. There is also the challenge of helping
the suppliers of each product maximize their profits while
making sure the store is making money. With so many things to
consider, working in marketing for such a large business can be
a challenge.
Your Role
This week, you’ll be acting as a Marketing Manager in the
sporting goods section.
What Is a MARKETING Manager?
Marketing Managers are responsible for developing,
implementing and executing marketing plans, either for an
entire organization or for particular categories or products
within the organization, in order to attract potential customers
and keep existing ones.
Their day-to-day tasks include managing and coordinating
marketing and creative staff, leading market research to
improve existing products and services, working with
advertising agencies, and determining the best way to get
products in front of customers.
32. As a marketing manager for a discount retail store in Brooklyn,
you have been asked to evaluate a marketing plan for
basketballs to ensure that the 4 P’s of marketing are being
applied well. Using your knowledge of the 4 P’s and the best
approach to generating sales, you’ll take a look at a number of
marketing recommendations and choose the approach that you
believe will sell the most products.
Instructions
Step 1: Product Life Cycle
In the Marketing Analysis Presentation provided by your
marketing team, you’ll see three different basketballs that need
to be included in the product display on Slide 2. Each product
has unique features.
· Based on the information provided about the customers that
shop at the store location on Slide 3, choose the basketball that
you think will sell the most.
Underline your selection:
Basketball 1
Basketball 2
Basketball 3
Explain the rationale for your decision.
Step 2: PLACE
On Slide 4 of the Marketing Analysis Presentation, you’ll see
the results of a survey that asked potential buyers about where
they are most likely to purchase these products.
On Slide 4 of the Marketing Analysis Presentation, you’ll see
the results of a survey that asked potential buyers about where
they are most likely to purchase these products. Underline your
selection:
Traditional Stores
33. Online
Explain the rationale for your decision.
Step 3: PROMOTION
Slide 5 of the Marketing Analysis Presentation shows three
recommended advertisements, including a special deal
promotion, for the product that is expected to sell the best.
Based on the information provided about the customers that
shop at this store location on Slide 3, determine which
promotional activity will sell the most product at this particular
store. Underline your selection:
Promotion 1
Promotion 2
Promotion 3
Explain the rationale for your decision.
Step 4: PRICE
Look at the pricing options available for each of the three
products together on Slide 6.
Based on your knowledge of the Pricing Strategies discussed on
pages 186-187 in the textbook, choose the option that has the
best pricing mix for all three products. Refer to the customer
information on Slide 3, if needed. Underline your selection:
Pricing Mix 1
Pricing Mix 2
Pricing Mix 3
34. Explain the rationale for your decision.
Note: You should complete Steps 5 & 6 after reading the
material in Week 7.
Step 5: BRAND & SALES PITCH
The company that makes one of the basketballs is looking to
rebrand the product. They have asked for your input on possible
brands ideas.
First, read the Brand Vision statement which summarizes the
goal for the new brand. Then, look at the logo, name, and
tagline recommendations. Which of the two brand directions do
you think best meets the goals of the brand vision? Underline
your selection:
Brand Direction 1
Brand Direction 2
Please support your decisions.
Second, write a 2-3 sentence sales pitch that you would use to
try to convince someone to purchase this product.
Step 6: MARKET SEGMENTATION
The marketing plan for the basketballs at the Brooklyn store has
been in place now for four months, and the marketing team has
assembled a report reviewing sales data and customer feedback
for the last quarter’s basketball sales. Overall, the results are
lower than you expected and you are concerned that your
marketing and creative staff have not properly segmented your
35. target customers.
Remember, like many products in the marketplace, the
basketball’s marketing campaigns must target two different
groups of customers: (1) adults who purchase the item as a gift
and, therefore, do not actually use the product; and (2) adults
and teenagers who purchase the item for their own use and
enjoyment. Both groups have different reasons and expectations
surrounding the item in question, and those reasons and
expectations will have significant impacts on the buyers’
purchasing decisions.
· Review the five customer segments detailed on pages 194-195
of your textbook: Behavioral, Sociographic, Psychographic,
Geographic and Demographic. Select one focus area of each
segment that you feel is most relevant to the sale of basketballs
at this store location.
· Keeping in mind the 4 P’s, write 1-2 questions for each focus
area that will guide your staff as they investigate these aspects
of your campaign.
Example:
· Segment: Geographic
· Focus Area: Neighborhood
· Questions: What combination of marketing and media
channels did we use to reach current and potential customers?
How are we gathering information on where current customers
live who purchased a basketball?
1 BUS508: CONTEMPORARY BUSINESS
Chapter 7: Healthcare Data Analytics
Bill Hersh MD
36. After reviewing this presentation, viewers should be able to:
Discuss the difference between descriptive, predictive and
prescriptive analytics
Describe the characteristics of “Big Data”
Enumerate the necessary skills for a worker in the data analytics
field
List the limitations of healthcare data analytics
Discuss the critical role electronic health records play in
healthcare data analytics
Learning Objectives
37. One of the promises of the growing clinical data in electronic
health record (EHR) systems is secondary use (or re-use) of the
data for other purposes, such as quality improvement and
clinical research
Interest in healthcare data has grown exponentially due to EHR
incentives after the HITECH Act and the addition of genomic
information that will eventually be integrated with EHRs
Introduction
The term analytics is achieving wide use both in and out of
healthcare. A leader in the field defines analytics as “the
extensive use of data, statistical and quantitative analysis,
explanatory and predictive models, and fact-based management
to drive decisions and actions”
IBM defines analytics as “the systematic use of data and related
business insights developed through applied analytical
disciplines to drive fact-based decision making for planning,
management, measurement and learning
Introduction
38. Descriptive – standard types of reporting that describe current
situations and problems (how many uninsured patients do we
have with type 2 diabetes?)
Predictive – simulation and modeling techniques that identify
trends and portend outcomes of actions taken (can we predict
who will be readmitted for heart failure in the next 30 days?)
Prescriptive – optimizing clinical, financial, and other outcomes
(of those patients identified as high risk for readmission for
heart failure is it more cost effective to case manage in the
hospital or at home?)
Different Types of Analytics
Increasing functionality and value
Machine learning is the area of computer science that aims to
build systems and algorithms that learn from data
Data mining is defined as the processing and modeling of large
amounts of data to discover previously unknown patterns or
relationships
Text mining, a sub-area, applies data mining techniques to
mostly unstructured textual data
Analytics Concepts
39. Provenance, which is where the data originated and how
trustworthy it is for large-scale processing and analysis
Business intelligence, which in healthcare refers to the
“processes and technologies used to obtain timely, valuable
insights into business and clinical data”
Learning health system, where data can be used for continuous
learning to allow the healthcare system to better carry out
disease surveillance and response, targeting of healthcare
services, improving decision-making, managing misinformation,
reducing harm, avoiding costly errors, and advancing clinical
research
Analytics Concepts
Another related term is big data, which describes large and
ever-increasing volumes of data that adhere to the following
attributes:
Volume – ever-increasing amounts
Velocity – quickly generated
Variety – many different types
40. Veracity – from trustable sources
While big data is considered a buzz word by some, we are
having to deal with terabytes and petabytes of information
today. With the addition of genomics big data will escalate
Big Data
Healthcare organizations are generating an ever-increasing
amount of data. In all healthcare organizations, clinical data
takes a variety of forms, from structured (e.g., images, lab
results, etc.) to unstructured (e.g., textual notes including
clinical narratives, reports, and other types of documents)
For example, it was estimated by Kaiser-Permanente in 2013
that its current data store for its 9+ million members exceeds 30
petabytes (petabyte = 1024 terabytes) of data
Big Data
Another example is CancerLinQ that will provide a
41. comprehensive system for clinicians and researchers consisting
of EHR data collection, application of clinical decision support,
data mining and visualization, and quality feedback
Lastly, IBM’s Watson is now focusing on healthcare,
specifically Oncology so that massive amounts of cancer
information/research can be analyzed and applied to individual
patient decision making
Big Data
The Analytics Big Data Pipeline
According to Kumar et al
One begins with multiple data sources, that are extracted and
cleansed and normalized
Statistical processing prepares the data for output
Finally, the data helps generate descriptive, predictive and
prescriptive analytics
42. Accountable care organizations (ACOs) provide incentives to
deliver high-quality care in cost-efficient ways that will require
a robust IT architecture, health information exchange (HIE)
plus analytics. This approach would be used to predict and
quickly act on excess costs
As one pundit put it: ACOs = HIE + Analytics
Big Data
Big Data will Drive ACOs
Data generated in the routine care of patients may be limited in
its use for analytical purposes. For example, data may be
inaccurate or incomplete. It may be transformed in ways that
undermine its meaning (e.g., coding for billing priorities)
It may exhibit the well-known statistical phenomenon of
censoring, i.e., the first instance of disease in record may not be
when it was first manifested (left censoring) or the data source
may not cover a sufficiently long time interval (right censoring)
Challenges to Data Analytics
43. Data may also incompletely adhere to well-known standards,
which makes combining it from different sources more difficult
Clinical data mostly allows observational and not experimental
studies, thus raising issues of cause-and-effect of findings
discovered
Research questions asked of the data tend to be driven by what
can be answered, as opposed to prospective hypotheses
Challenges to Data Analytics
Data are not always as objective as one might like, and
“bigger” is not necessarily better
There are ethical concerns over how the data of individuals is
used, the means by which it is collected, and the possible divide
between those who have access to data and those who do not
Who owns the data and who can use it?
Challenges to Data Analytics
44. There is an emerging base of research that demonstrates how
data from operational clinical systems can be used to identify
critical situations or patients whose costs are outliers
There is less research, however, demonstrating how this data
can be put to use to actually improve clinical outcomes or
reduce costs. Studies using EHR data for clinical prediction
have been proliferating
Research and Application of Analytics
One common area of focus has been the use of data analytics to
identify patients at risk for hospital readmission within 30 days
of discharge. The importance of this factor comes from the US
Centers for Medicare and Medicaid Services (CMS)
Readmissions Reduction Program that penalizes hospitals for
excessive numbers of readmissions
This has led to research using EHR data to predict hospital
readmissions. Thus far, the results are mixed and several
examples of trials are included in the textbook chapter
Research and Application of Analytics
45. Research and Application of Analytics
Scenarios for EHR Data Analysis
Predicting 30-day risk of readmission and death among HIV-
infected inpatients
Identification of children with asthma
Risk-adjusting hospital mortality rates
Detecting postoperative complications
Measuring processes of care
Determining five-year life expectancy
Detecting potential delays in cancer diagnosis
Identifying patients with cirrhosis at high risk for readmission
Predicting out of intensive care unit cardiopulmonary arrest or
death
Identifying patients who might be eligible for participation in
clinical studies
Determining eligibility for clinical trials
Identifying patients with diabetes and the earliest date of
diagnosis
Predicting diagnosis in new patients
Research and Application of Analytics
46. Identifying Patients for Research Using EHR Data
Virtual Data Warehouse (VDW) Project was able to demonstrate
a link between childhood obesity and hyperglycemia in
pregnancy
United Kingdom General Practice Research Database
(UKGPRD), a repository of longitudinal records of general
practitioners, was able to demonstrate the ability to replicate the
findings of the Women’s Health Initiative and RCTs of other
cardiovascular diseases
Research and Application of Analytics
Use EHR Data to Replicate Randomized Controlled Trials
Other data repositories have helped to predict a variety of
cancers, risk for venous thromboembolism (blood clots) and
even rare medical disorders
Note the info box in the next slide that discusses data analytics
by the Veterans Health Administration (VHA)
47. Research and Application of Analytics
Use EHR Data to Replicate Randomized Controlled Trials
Case Study: Veterans Health Administration (VHA)
The VHA is a large healthcare system with a long track record
of EHR use (VistA). In 2013, the VHA had 30 million unique
electronic patient records with 2 billion clinical notes (100,000
notes added daily). They also have had a corporate data
warehouse (CDW) of structured data which allows them to
analyze clinical and administrative data for patients at risk of
hospital admission (from falls, coronary disease, PTSD, etc.).
Analytics are run once weekly on all primary care patients
looking for “at risk” patients who would likely require more
coordinated care using care managers, home health and
telehealth. In 2012, VHA researchers reported in the American
Journal of Cardiology on the use of predictive analytics on heart
failure patients. Specifically, using six categories of risk
factors derived from the EHR they could successfully predict
which patients were at risk of hospitalization and death.
According to Dr. Stephen Fihn, Director of Analytics and
Business Intelligence for the VHA, the VHA is embarking on a
24-month pilot project to expand the use of healthcare data
analytics. They will use natural language processing and
machine learning to analyze patient records to aid in diagnosis,
identify dangerous drug-drug interactions and optimally design
treatment strategies.
48. Research and Application of Analytics
Using Genomic Information and EHRs
Researchers have carried out genome-wide association studies
(GWAS) that associate specific findings from the EHR (the
“phenotype”) with the growing amount of genomic and related
data (the “genotype”) in the Electronic Medical Records and
Genomics (eMERGE) Network
eMERGE has demonstrated the ability to identify genomic
variants associated with atrioventricular conduction
abnormalities, red blood cell traits, white blood cell count
abnormalities, and thyroid disorders
More recent work has “inverted” the paradigm to carry out
49. phenome-wide association studies (PheWAS) that associated
multiple phenotypes with varying genotypes
Genome-wide and phenome-wide association studies are also
discussed in the chapter on bioinformatics
Research and Application of Analytics
Using Genomic Information and EHRs
There has been little focus on the human experts who will carry
out analytics, to say nothing of those who will support their
efforts in building systems to capture data, put it into usable
form, and apply the results of analysis
Where will these workers come from and what will be the
education of those who work in this emerging area, that some
call data science?
We do know that data analytics experts are in high demand
Role of Informaticians in Analytics
From basic biomedical scientists to clinicians and public health
50. workers, those who are researchers and practitioners are
drowning in data, needing tools and techniques to allow its use
in meaningful and actionable ways
Dr. Hersh believes that a strong background in Health
Informatics or Biomedical Informatics is the best preparation
for the healthcare data analytics field
Role of Informaticians in Analytics
Data science is more than statistics or computer science applied
in a specific subject domain. It requires an understanding of
data, its varying types, and how to manipulate and leverage it
The field requires skills in machine learning, a strong
foundation in statistics (especially Bayesian), computer science
(representation and manipulation of data), and knowledge of
correlation and causation (modeling)
Role of Informaticians in Analytics
51. A report by McKinsey consulting states that there will soon be a
need in the US for 140,000-190,000 individuals who have “deep
analytical talent” and an additional 1.5 million “data-savvy
managers needed to take full advantage of big data”
An analysis by SAS estimated that by 2018, there will be over
6400 organizations that will hire 100 or more analytics staff
Another report found that data scientists currently comprise less
than 1% of all big data positions, with more common job roles
consisting of developers (42% of advertised positions),
architects (10%), analysts (8%) and administrators (6%)
The Need for Data Analytics Experts
The technical skills most commonly required for big data
positions as a whole were NoSQL, Oracle, Java and SQL
PriceWaterhouseCoopers noted that healthcare organizations
need to acquire talent in systems and data integration, data
statistics and analytics, technology and architecture support,
and clinical informatics
Business knowledge is also useful
The Need for Data Analytics Experts
52. Programming - especially with data-oriented tools, such as SQL
and statistical programming languages
Statistics - working knowledge to apply tools and techniques
Domain knowledge - depending on one's area of work,
bioscience or health care
Communication - being able to understand needs of people and
organizations and articulate results back to them
The Need for Data Analytics Experts
What Skill Sets Should Universities Train For?
Healthcare data has proliferated greatly, in large part due to the
accelerated adoption of EHRs
Analytic platforms will examine data from multiple sources,
such as clinical records, genomic data, financial systems, and
administrative systems
Analytics is necessary to transform data to information and
knowledge
Accountable care organizations and other new models of
healthcare delivery will rely heavily on analytics to analyze
financial and clinical data
There is a great demand for skilled data analysts in healthcare;
expertise in informatics will be important for such individuals
Conclusions