healthcare data: visual discovery and governance on any device
Post on 05-Aug-2015
541 Views
Preview:
TRANSCRIPT
© 2015 Health Catalystwww.healthcatalyst.com
July 7, 2015
Hosted by Dale Sanders with guest speaker Donald Farmer of Qlik
Healthcare Data: Visual Discovery and Governance on Any Device
Creative Commons Copyright – Attribution Required
2
Agenda
• What do Qlik and Donald Farmer have to say about visual discovery and governance of data?
• The Three Truths of next generation healthcare analytics
• What’s my reaction to these truths?
• What’s the future for visual data discovery in healthcare look like?
© 2015 Health Catalystwww.healthcatalyst.comProprietary and Confidential
Proven global market leader with over 33,000 customers in over 105 countries.
Extensive partner network over 1,700 partners strong.
Active community leveraging the expertise of more than 100,000 members.
More than 1,000 healthcare organizations globally have chosen to deploy Qlik
Qlik data analytic solutions accelerate the adoption of data-driven analysis by fostering natural exploration and discovery of insights.
An introduction to Qlik
© 2015 Health Catalystwww.healthcatalyst.comProprietary and Confidential
Visual analytics at the point of decision
Agility through Innovation
Collaboration and Conversation for better
decisions
Our Core BeliefsHarness the collective human intelligence of an organization for better decision-making
Deliver naturally intuitive solutions that bring the best out of the people that use them
Innovate to allow people to constantly adapt to changing environments
3 Truths Of Next Generation Healthcare Analytics
The “intelligent organization” derives value by
analyzing data from multiple sources,
and multiple views on multiple devices, at the point of
decision.
© 2015 Health Catalystwww.healthcatalyst.comProprietary and Confidential
3 Truths Of Next Generation Healthcare Analytics
The power of discovery comes from new insights
that were not even contemplated in the original
design process.
© 2015 Health Catalystwww.healthcatalyst.comProprietary and Confidential
3 Truths Of Next Generation Healthcare Analytics
Line of business users always need flexibility to add data, add
visualizations, and "what-if" to their hearts content.
This requires not only powerful self-service, but governed self-
service.
© 2015 Health Catalystwww.healthcatalyst.comProprietary and Confidential
Qlik Products
Proven, market leading data
discovery platform
Used to develop and deploy rich
guided analytics applications
for exploration
and discovery
Next-generation self-service
data visualization application
Empowers everyone to
create and explore flexible,
interactive visualizations
using their intuition
Associative Data Indexing Engine enables users to naturally follow their intuition and explore data relationships across many sources that
would be hidden in hierarchical or query-based approaches.
© 2015 Health Catalystwww.healthcatalyst.comCreative Commons Copyright – Attribution Required
Truth #1: The “intelligent organization” derives value by analyzing data from multiple sources, and multiple views on multiple devices, at the point of decision.
10
Imagine if your physician could say this to you…
I can make a health optimization recommendation to you, informed not only by the latest clinical trials, but also by our local and regional data about patients like you; the real-world health outcomes over time of every patient like you who has had your illness; and the level of your interest and ability to engage in your own care -- and in turn I can tell you within a specified range of confidence, which treatment has the greatest chance of success for a patient specifically like you and how much that treatment will cost.
This is Health Catalyst’s aspirational statement for our products and services, inspired by the Learning Healthcare System
Consortium, but modified by Dale Sanders
11
Healthcare data ecosystem
Health Catalyst has a library of connectors to 94 different source systems of data in healthcare
On average, mid-to-large size health systems can expect to integrate over 150 different sources of data in their enterprise data warehouse, within five years.
Complex, very diverse, and expanding
12
Data at the point of decision making
• Physicians are 15x more likely to change their protocol for a patient if presented with substantiating data at the point of care vs. presented with the same data in a clinical quality meeting (BMJ, 2007)
• 50M smart meters installed in the US– no change in consumer consumption of electricity
• Where’s the decision support data at the light switch and thermostat– i.e., the point of decision making?
• Lifestyle determines 70-80% of healthcare outcomes
• Where’s the decision support data at the restaurant, grocery store, and other lifestyle decision points?
© 2015 Health Catalystwww.healthcatalyst.comProprietary and Confidential
Embedded best practices, decision support & care team coordination that support the Triple Aim
EHR embedded popula-tion analytics tailored for personalized medicine at the point of care
EHRClinical Decision Support
EDWClinical Quality Analytics
Define clinical best practices & requirements for embed-ded decision support & care team coordination
Use aggregate views of clinical data for case mix & protocol optimization
Derive population-based health system models for predicting demand
5
8
11
6
9
12
i ii
Executive & Clinical Leadership
Create a cultural expectation for evidence based medicine and use of clinical pathways & standard protocols
10
Enterprise Clinical Teams
Act on process & outcome data using protocol-based practice standards Identify new cohorts & gauge practice variations
Clinical, EHR & Analytical Teams
Generate comparative & outcomes data, implement order sets, protocols and decision support rules. Develop & validate clinical models 4
7
Start Here
Closed Loop Analytics
Information Systems
Supporting Data
Decisions & Actions
© 2015 Contributing authors, listed alphabetically: Eggert C, Moselle K, Protti D, Sanders D.
Align practice informed by analytics
Tailor protocols using better data
Man
age
Serv
ices
Opti
miz
e Ca
paci
tyD
eliv
er C
are
Loop A: Patients
Loop B: Protocols
External Evidence Literature, Research
Other Data SourcesExternal, Financial
iv
Internal Evidence
Internal Evidence
EHR: Electronic Health RecordEDW: Enterprise Data WarehouseMTTI:Mean time to improvementSOPA:
Span of providers affected
COptimize system on quality & cost
Loop C: Populations
Internal Evidence
iii
Confidential DraftMar 21, 2015
Previous Box 6: Assess data quality, cohorts & interventions linked to outcomes
Include socio-economic determinants of health in clinical care management best practices
CLINICAL QUALITY GOVERNANCESet improvement priorities 1
Closed Loop AnalyticsMean Time To Improvement (MTTI) and Span of Population Affected (SPA)
Loop C: Populations
● MTTI: Years, decades
● SPA: Millions, several hundred thousand
● Analytic consumers: Board of Directors, executive leadership team, Strategic
plans and policy
‒ Heat maps, bar charts, histograms, network diagrams, etc.
Loop B: Protocols
● MTTI: Weeks, months
● SPA: Subsets of patients– hundreds, thousands
● Analytic consumers: Care improvement teams, clinical service lines
‒ Control charts, line charts, scatter plots, etc.
Loop A: Patients
● MTTI: Seconds, minutes, hours
● SPA: Individual patients
● Analytic consumers: Physicians and patients at the point of care and decision making
‒ Algorithms with minimal, precise data
14
15
Simple visualization, complex algorithms
• Institute for Clinical Systems Improvement• Reduce overuse of inappropriate imaging in Minnesota• $84M in savings
16
Ambient, suggestive analytics
Substitutable Medical Apps and Reusable Technology (SMART)This is going to enable closed loop analytics with EHRs
Two major goals:• A user interface that allows “iPhone-like” substitutability for medical apps• A set of services that enables efficient data capture, storage, and effective data retrieval and analytics, which will be scalable to the national level but nonetheless respectful of institutional autonomy and patient privacy.
© 2015 Health Catalystwww.healthcatalyst.comCreative Commons Copyright – Attribution Required
Truth #2:The power of discovery comes from new insights that were not even contemplated in the original design process.
19
Design forward, not backward
Sanders’ Third Postulate
● In the design of analytic and big data systems, aka, enterprise data warehouses, the thickness of a requirements document is inversely proportional to the success of the system
When was the last time we asked a librarian to write a requirements document that encompassed all the possible use cases of the books and periodicals in a library?
● You stock the shelves with as many books on as many topics as you can afford and store, then evolve from there
Current data emphasis in healthcare… • Healthcare providers are scrambling to meet current, basic
reporting requirements
• To payers, federal and state government, industry accreditation, professional affiliations… US News and World Report Hospital Ratings
• Vendors are designing data warehouses and data models to meet current needs… the known requirements
• Need a balanced design and strategy… address the known and prepare capacity for the unknown
• Allow for local data exploration… hire staff and vendors that allow for this!
20
Surprises of data
“When we designed Navstar [aka, GPS], we were mainly concerned about a precise understanding of current location– where are we now? What we didn’t expect is how it has been used to explore the unknown with greater confidence and safety.”
--Roger L. Easton, principal inventor and designer of the Global Positioning System (GPS)
21
© 2015 Health Catalystwww.healthcatalyst.comCreative Commons Copyright – Attribution Required
Truth #3:Line of business users always need flexibility to add data, add visualizations, and "what-if" to their hearts content. This requires not only powerful self-service, but governed self-service.
23
As in a democratic, free society
Personal freedom does not usurp personal responsibility to the common good
Same applies to the future of data governance
As we release and decentralize more and more data and we all become participants in the healthcare decision making process, we must become data governors, and encourage a culture of data literacy, data quality, and data utilization
24
Surprise… you are now data governors
“Data governance refers to the plans, processes and
principles that are proactively applied to ensure that
an organization’s data is managed in such a way to
maximize the value of that data to the mission of the
organization.”
• The Triple Aim of Data Governance
• Data Quality
• Data Literacy
• Data Utilization
© 2015 Health Catalystwww.healthcatalyst.comCreative Commons Copyright – Attribution Required
What’s the Future Look Like for Healthcare Data Discovery and Visualization?
26
What makes for good visualization of data?
• Hanspeter Pfister, Wang Professor of Computer Science, Harvard; Michelle Borkin and Caroline Perry, Harvard School of Engineering and Applied Sciences
• 2013 IEEE Information Visualization Conference
“A visualization will be instantly and overwhelmingly more memorable if it
incorporates an image of a human-recognizable object—if it includes a
photograph, people, cartoons, logos—any component that is not just an abstract
data visualization,” says Pfister. “We learned that any time you have a graphic
with one of those components, that’s the most dominant thing that affects the
memorability.”
“You’d think the types of charts you’d remember best are the ones you learned in
school—the bar charts, pie charts, scatter plots, and so on,” Borkin says. “But it
was the opposite.” Unusual types of charts, like tree diagrams, network diagrams,
and grid matrices, were actually more memorable.
27
What’s this mean for the future?Appeal to the foundations of human cognition• Infographics for your data
• The Advisory Board Company is a great role model for merging memorable graphics with meaningful data
• What would your corporate dashboard look like as an infographic?
• “Unusual” diagrams and charts
• Next slides
28Thank you, Harshit Pandey, at YeCode
29
Word trees & text data*This word tree depicts a tree of phrases, with the size of the words proportional to their usage. In this set of phrases, "cats eat mice" occurs four times, and "cats eat" occurs six times (four times with "mice", and twice with "kibble").
*Thank you, Google Charts
30
OECD quality of care indicators vs. Canadian province
Thank you, Canadian Institute for Health Information
31Thank you, Washington Post
Incredibly cool project
32
Examples on following side
Patient & clinician friendly dataA sampling of 54 chart types, research-validated as effective
33
For communicating likelihood of side effects, severity of side effects, changes in side effect risks over time, based on treatment protocols
34
35
36
37
Becoming a “mobile first” worldSmartphones are becoming the first choice for computing
38
Device choice depends on time
You have to support multiple tools and platforms
39
Additional, good references• Health Intelligence
• http://healthintelligence.drupalgardens.com/content/resources/data-and-visualization-sites
• Jenn Underwood
• http://www.jenunderwood.com/
• “Worth a Thousand Words: How to Display Healthcare Data”, California Healthcare Foundation
• http://www.chcf.org/~/media/MEDIA%20LIBRARY%20Files/PDF/W/PDF%20WorthThousandWordsDataViz.pdf
• Visually
• http://visual.ly/
• Chart Porn
• http://chartporn.org/
• Google Charts
• https://developers.google.com/chart/interactive/docs/
• Data Wrapper
• https://datawrapper.de/
40
Healthcare Analytics Summit 15
Here’s a sneak preview …Industry-leading Speakers
Jim CollinsBest-selling author of Good to Great, Great by Choice, Built to Last, and How the Mighty Fall
Ed CatmullCo-founder of PixarPresident of Pixar and Walt Disney Animation Studios
Daryl MoreyHouston RocketsGeneral Manager and Managing Director of Basketball Operations
Amir RubinStanford Health CarePresident and CEO
Timothy G. Ferris, MD, MPHPartners HealthCareSenior Vice President ofPopulation Health Management
Timothy Sielaff, MD, PhD, FACSAllina HealthChief Medical Officer
Summit highlights3-day AgendaWe’ve increased the time of this year’s summit to allow for more sessions, topics, and networking.
CME Accreditation for CliniciansThis activity has been approved for AMA PRA Category 1 Credits™.
More Case Study SessionsHealth system case studies addressing even more clinical, technical, operational, and financial examples.
Hands-On Experiences Examples, vignettes, and audience-based activities demonstrate principles in fun and memorable ways.
Analytics-Driven EngagementReal-time polling, networking, Q&A, and gamification experiences; plus,i-beacon location technology.
NetworkingExperience networking options that use analytics creatively to help you find and connect with others.
Pre-Summit Classes and TrainingAn early half-day of pre-session classes and training options specifically for Health Catalyst clients.
3X the sessions8 keynotes, 25 breakouts, 25-40 analytics walkabout mini-sessionsf
Early Registration Pricing, Optimized For Teams
Buy 1(save $300)
$395/Pass(through May 31)
Buy 3(save $1,098)
$329/Pass(through May 31)
Buy 5(save $2,000)
$295/Pass(through May 31)
Thank you!Please complete your satisfaction
survey for this webinar.
top related