HI-FIVE (Health Informatics For Innovation, Value & Enrichment) Training is a 12-hour online course designed by Columbia University in 2016, with sponsorship from the Office of the National Coordinator for Health Information Technology (ONC). The training is role-based and uses case scenarios. Also, it has additional, optional modules on other topics of interest or relevance. Although we suggest to complete the course within a month's timeframe, the course is self-paced and so you can start and finish the course at anytime during a month's time period. No additional hardware or software are required for this course. Our nation’s healthcare system is changing at a rapid pace. Transformative health care delivery programs depend heavily on health information technology to improve and coordinate care, maintain patient registries, support patient engagement, develop and sustain data infrastructure necessary for multi-payer value-based payment, and enable analytical capacities to inform decision making and streamline reporting. The accelerated pace of change from new and expanding technology will continue to be a challenge for preparing a skilled workforce so taking this training will help you to stay current in the dynamic landscape of health care. This course is one of three related courses in the HI-FIVE training program, which has topics on population health, care coordination and interoperability, value-based care, healthcare data analytics, and patient-centered care. Each of the three courses is designed from a different perspective based on various healthcare roles. This first course is from a clinical perspective, geared towards physicians, nurse practitioners, physician assistants, nurses, clinical executives and managers, medical assistants, and other clinical support roles. However, we encourage anyone working in healthcare, health IT, public health, and population health to participate in any of the three trainings. If you would like to obtain continuing medical education (CME) or continuing nursing education (CNE) credits, you will need to have eligible credentials, complete the entire course, and complete the evaluation survey at the end. The HI-FIVE team verifies after each month that these requirements have been met and then a separate certificate (fee may apply) is distributed to you from our accreditation office. Please allow time for processing. If you have any further questions about continuing education, please see our website at www.hi-fivetraining.org. Accreditation Statement The College of Physicians and Surgeons of Columbia University is accredited by the Accreditation Council for Continuing Medical Education (ACCME) to provide continuing medical education for physicians. AMA Credit Designation Statement The College of Physcians and Surgeons designates this enduring material for 12.0 AMA PRA Category 1 Credits™. Physicians should claim only the credit commensurate with the extent of their participation in the activity. The planning committee members are: Rita Kukafka, DrPH, MA, FACMI; Bruce Forman, MD; Gil Kuperman, MD, PhD; Virginia Lorenzi, MS, CPHIMS, FHL7, and Victoria Tiase, MSN, BN. None of the members of the committee, who planned this CME Activity, have any relevant financial relationships to disclose. The release date is 2/1/17 and the expiration date is 1/31/18. This activity is eligible for 12 continuing nursing education (CNE) credits. Columbia University School of Nursing, Continuing Nursing Education Program is accredited as a provider of continuing nursing education by the American Nurses Credentialing Center's Commission on Accreditation.
Data Analytics in Clinical Settings: Measurement Issues-Tools, Approaches, and Governance
Loading...
From the course by Columbia University
HI-FIVE: Health Informatics For Innovation, Value & Enrichment (Clinical Perspective)
101 ratings
Columbia University
101 ratings
From the lesson
Role-Based Content (OPTIONAL) - Physicians / Nurse Practitioners / Physician Assistants / Clinical Executives / Clinical Managers / Public Health Professionals
This module is optional, but has additional topics that you may be interested based on your role. We encourage you to explore any of these topics and there are also quizzes to test your learning.
Meet the Instructors
Rita KukafkaAssociate Professor
Biomedical Informatics
Welcome to Health Care Data Analytics, Data Analytics in Clinical Settings.
This is Lecture b, the component, Health Care Data Analytics,
covers the topic of health care data analytics which applies the use of data,
statistical and quantitative analysis, and explanatory and
predictive models to drive decisions and actions in health care.
The learning objectives for data analytics and clinical settings are to describe
the current state of analytics in clinical settings, identify key tools and
approaches to improve analytics capabilities in clinical settings,
describe different governance and
operations strategies in analytics in clinical settings.
Discuss value based payment systems and
the role of data analytics in achieving their potential, and
analyze data used in population management and value-based care systems.
In this lecture, we'll provide some examples of how to address complex issues
related to data and measurement for data analytics for clinical settings.
First, we'll describe a case where data is diverse and fragmented, and
how data needs to be integrated to perform effective analysis.
Then, we'll describe the importance of using detailed measure specifications and
standard measures to ensure that your analytics are predicting what is important
and related to broader health and health care goals.
This messy diagram is intended to show the information flow, as Ms.
Viera, a person with five complex chronic conditions,
interacts with the health care system over the course of one year.
If we were to estimate outcomes for, we will find out that she 90 times the rate
of hospitalization as someone with no chronic conditions.
That she takes on average 14 medications,
and that she'll see 12 specialists during that one year.
How can analytics help us measure her risks?
And whether her care is of high quality and safe.
Where does the system break down when we're trying to measure
the quality of her care and predict her needs?
First, the more interaction with the health care system she has,
the more likely her data is to be fragmented.
Often, when someone is hospitalized,
the hospital's information system is not the same as the out-patient system.
So, the information about her previous care is not available to the hospital.
And if the hospital changes to drugs,
then the primary care setting may not get a notification about that.
In fact, the primary care setting may never know she's in the hospital.
The only complete source of data about her healthcare utilization maybe in the bills
that go to health insurance companies or the federal government for medicare.
These bills are stored in so called claims databases and
are not integrated back to EHRs in most cases.
This can cause serious problems as we try to
analyze data to understand Miss Viera's care and health outcomes.
Let's explore this data measurement issue in a different way, by data sets.
EHR data in our example is stored by the primary care providers.
It has a longitudinal record of all the data collected at the clinic and
associated laboratory.
This information can be useful in analysis when on going patient factors are needed.
For instance, when we are predicting risk of re-admissions,
comorbidities are helpful to understand the patient's health is complicated by
multiple other diseases.
The claims data, which are the set of bills for healthcare,
may contain other equally important information.
Information about ED visits, the acuity of the hospitalization, and
final diagnosis may only be available through these claims since the hospital
may be on a different system.
Finally, other data usually not stored in either the EHR or
the claims data may be helpful such as social, behavioral and environmental data.
Environmental in this case, means information about where people live.
The availability of healthy food for
instance may be low in certain urban settings.
The lack of integration of this data leads to poor prediction in health care
settings.
And Miss Viera may be re-admitted because the system did not adapt.
It is possible however to integrate data from these sources or
at least exchange it as in health information exchange programs.
To truly analyze risk, the data can be integrated into an analytic data warehouse
where all relevant and available data can be processed then, a more accurate and
complete risk score can be calculated, and programs like transitional care
coaching or the care transitions intervention can be targeted to her needs.
These programs can reduce re-admission risk by working with patients
more closely before and upon discharge, this is an ideal version.
In the real world, there are still many issues to be dealt with.
For instance, claims data often takes a long time to be available.
Sometimes more than a year.
Quicker access to the information is needed in many cases and so
communities may exchange information electronically.
Similarly, data that means the same thing is not stored in the same way across
settings.
We must strive for semantic interoperability,
where we can recognize when things mean the same thing.
Finally, we have the issue that, even electronically, most data is stored
as unstructured notes or reports, which makes it difficult to predict issues.
Another kind of data that is increasingly important but
is not integrated is genomic data.
We have rapidly increased our ability to process genomic information but we can't
exchange it easily and it's not integrated into most analytic or health care systems.
The Implementing Genomics in Practice, or IGNITE Network, was funded by
the National Institutes of Health to improve the integration of this data.
Shown are the more than a dozen sites involved in the Network.
Two examples are given from the Network.
Mt. Sinai in New York is looking at why
African-Americans with hypertension have more kidney failure or
end stage renal disease.
They found that particular alleles from the APOL one locus vary by race and
may help predict risk and provide insight into different approaches to treatments.
Similarly, Indiana is using what we know about how people
process drugs based on their genetics.
Known as pharmacogenomics, to help people pick both the right drugs, and
the right doses to avoid costly complications.
The IGNITE network wants to see if providing this information
reduces overall health care costs.
Data about where a person lives and how they live can be more important than
the health care they receive in many cases.
For instance, your day to day behaviors,
such as how much you walk or what you eat, may effect your risk
of hospitalization from heart failure more than medications of health care.
Similarly, the walkability of your neighborhood and availability of healthy
foods may also affect your health more than particular treatments or procedures.
We have not previously had good ways to integrate this data into health and
health care, but that's changing as people recognize this data's value.
Similarly, the outcomes they perceive, such as the amount of pain they feel or
the things they can do, are more important than many lab tests or
other study results.
There are a number of new standards and methods to record and
integrate information about patient outcomes and environmental data.
For instance, patient reported outcomes are stored and
can be retrieved from a measurement information system known as PROMIS.
This system provides structured, validated ways for
patients to report on outcomes that may be important to them,
such as their depression symptoms or their overall function for daily activities.
Now, let's think about measures of healthcare quality and
how they help us to better analyze the care we deliver and the help it provides.
Let's think about a particular person, Mr. Smythe.
At 68 years old, he's out gardening in 2001 when suddenly he has chest pain.
He is rushed to the hospital where the EKG shown is demonstrating ST wave
elevations that definitely show something going on with his heart.
Within echocardiogram that shows his heart is not pumping well and
with other ongoing symptoms.
The medical team notice having an active heat attack, many people assume that he'll
get the exactly the treatment he needs in the vast majority of cases.
What evidence do we have about what are effective treatments for heart attack?
And what about his congestive heart failure, where his heart can no longer
pump efficiently enough to meet the needs of his body.
There is very good evidence from a variety of clinical trials
that he needs medications to limit the damage from the heart attack and
improve the function of his heart.
The medications are shown here, along with their related studies and
reduction in deaths from affectively using them.
Other treatments are important too, such as cardiac rehabilitation.
With this number of life saving treatments available,
we anticipate he'll get the great care he needs.
But to be sure, we must measure how well we did.
Now pause, and think to yourself, how often would a patient like Mr.
Smthe receive these treatments in 2001?
How about more recently in 2010?
Or 2012?
100% of the time?
95% of the time?
Perhaps 80%?
In 2001, the answer is just a bit less than two thirds of the time,
65% for Ace Inhibitor use and 80% for Beta-blocker use.
We've seen significant improvements over time in part because people started to
measure their rate of providing these medications and
reporting them to each other and to various quality measurement programs.
We can calculate an achievable benchmark of 95% for Ace inhibitor use.
About 30% higher than when Mr. Smythe had his heart attack.
And the benefit of this treatment is decreasing deaths.
In 2000, about 10% of patients died in the hospital when
they came in with a heart attack, now it's just above 4%.
These are the effects better quality measurement and
better quality care can achieve.
We haven't had the ability or drive to focus on analytics in the United States
before in part, because we couldn't measure or change care effectively.
Now, programs like Accountable Care Organizations benefit from predicting what
treatments are best for which patients and which may not be helpful or useful.
To be effective, one must measure what will be analysed carefully.
Historically, one had to define the measures of interest based on the goals
and related concepts, then define how to measure them through
indicators which had to be defined, and then data was collected and analyzed.
In each clinical setting, the information technology and
informatics staff had to define their own metrics, based on their available data and
the goals of the project.
This long list of steps would be needed to start
to measure anything you wanted to analyze.
Instead of a numbered list of steps to start measuring, many measurement
definitions and specifications come from large collaboratives that define
the measures for you based on evidence, feasibility and expert input.
Some measures for analysis will still be local, however,
most of them come from these collaboratives.
For instance, the Health and Human Services, or HHS branch of the government,
uses a highly standardized set of definitions for their measures to pay for
high quality care, or to reduce payments for
certain care such as when re-admissions could have been potentially been avoided.
Philosophy is still important however, measuring quality of care feels very
different to those being measured, then fee for service medicine.
That is, normally a clinical team decides to provide a treatment or
service and then bills for it.
Quality measurement tries to measure whether that service would
be recommended by the medical evidence.
And whether all services recommended were provided.
Thus, establishing your measurement philosophy in a clinical setting is
important.
A key part of a good measurement philosophy is a culture that is fell to
encourage learning, not judging.
But that when people truly and repeated make errors,
that there is justice in the way they are treated.
Cultures of pathology blame the person solely, and not the system of care.
And bureaucracy forms committees without acting on the information directly.
If you're starting an analytics effort, it's worthwhile to explore what you truly
want to measure and then look at the specifications for yourself.
The HHS measure inventory at AHRQ has a number of worthwhile measures.
If we go to the site listed on the previous slide,
this screen shot shows us how a search might lead to specific measures.
Here we've looked at admissions and re-admissions for heart failure as well as
some of the medication measures we were discussing before.
If you drill down into the measures, you can compare the reason for the measure,
the detailed definitions, and even where else it's used.
Here, we see the rationale of one of the measures in the registry.
It focuses on the detailed information about the measure.
Note that this version of the measure has been withdrawn, but
the link can show related measures.
In this measure, they outline the reasons for admissions and re-admissions and
offer some suggestions on how people might use the measure.
Some of the measures are now electronic clinical quality measures, or eCQMs.
These require electronic data from clinical sources such as EHRs.
They have very specific sets of codes and logic that should be used.
The Value Set Authority Center or
VSAC allows you to drill down into these specifications.
Here is the link to the VSAC.
The following slides will show images of it.
These images show the work flow of using the specifications.
Here is shown an example of a measure definition component.
These value sets have one or
more codes that are important to the analysis of the measure.
Here, a foot exam code, measured in the SNOMED CT taxonomy, is shown.
In this value set, there's only one eligible code.
So, those wishing to report on this measure would need to map their workflow
for a foot exam for patients with diabetes to this code to have it count as complete.
Here is another example.
The broad definition of diabetes used in several measures.
Here, 173 codes from three different taxonomies may be used.
There are a number of useful sources to check for measure specifications.
There are many organizations that develop measures, and you can learn a great
deal from looking at their websites to understand how they developed them and
how they're intended to be used.
For instance, the Commonwealth fund has measures that compare healthcare systems
across countries.
These are helpful to understand how other counties with very different systems do in
promoting healthy populations, and meeting expectations of care.
One example is the American Geriatric Society,
focused on the needs of older adults.
To find this article, point your web browser to the URL on the screen.
When the National Quality Measures Clearinghouse site opens,
type American Geriatric Society in the search box, then click the search button.
Look for the item titled "Geriatrics: percentage of female patients aged 65
years and older who were assessed for the presence or absence or
urinary incontinence within 12 months".
This looks at whether female patients over 65 were assessed for
involuntary urine loss, or urinary incontinence.
Is this a good measure?
Look at the rationale and evidence.
Sometimes, as in this measure, it requires additional reading to understand
the purpose of the measure in healthcare.
How do we know if measures are good?
We can ask ourselves if they're important.
As many of our heart failure measures were,
do they measure something that has a real and true effect on health and well-being?
We can look at scientific acceptability.
These mean that we're truly measuring what we mean to measure, also called validity.
And that if we measure twice in the same situation we get the same result,
also called reliability.
We also need people to understand the measure, use it and
be able to calculate the measures reasonably, also called feasibility.
How did these strategies help jump start your analytics program?
First, quality and
safety measures may already need to be reported at your institution.
And therefore, you can leverage that infrastructure to select measures that
relate to your analytic goals.
It can also be more efficient in that it aligns efforts,
reduces maintenance, and avoids duplicating work.
Finally, the validation work done on the quality measures, if done at all,
may help your analytics efforts be more effective.
And this concludes Lecture b of the unit on Data Analytics in Clinical Settings.
in summary, this lecture focused on how to jump start your analytics process by
better integrating data, by using standard measures rather than making up your
own and by validating the measures you implement.
These are very important tools and
approaches to enhance your analytic processes.
Explore our Catalog
Join for free and get personalized recommendations, updates and offers.
Coursera provides universal access to the world’s best education,
partnering with top universities and organizations to offer courses online.
© 2018 Coursera Inc. All rights reserved.
