This is the next evolution in health information exchanges and data warehouses, specifically designed to support analytics, transaction processing, and third party application development, in one platform, the Data Operating System.
The Data Operating System: Changing the Digital Trajectory of Healthcare
1. The Data Operating System
Changing the Digital Trajectory of Healthcare
Dale Sanders
Health Catalyst
May 2017
2. Selling vs. Not
In these webinars, I never sell Health Catalyst.
⢠I offer advice from past experience
⢠Advocate change
In this webinar, Iâll âsellâ Health Catalyst, but only as
evidence that we practice what we preach, in this case,
development of the Data Operating System
There is also advice buried in the âsellingâ⌠if weâre
building a Data Operating System, maybe other folks and
vendors should, too
3. The Story of Todayâs Meeting
⢠Whatâs a Data Operating System?
⢠Why do we need one now in healthcare?
⢠How can it be implemented?
⢠Is it real or just another buzz phrase?
4. First, ThanksâŚ
⢠Our entire product development team for their incredible
performance
⢠Iâve never been associated with as much change and productivity in
18 months
⢠For the brainstorming, engineering & implementation of the Data
Operating SystemâŚ
⢠Bryan Hinton
⢠Imran Qureshi
⢠Sean Stohl
⢠Rus Tabet, one of our UI and graphics experts
⢠For his illustrations and cartoons in this slide deck. Youâll be able to
tell the difference between his and mine. ď
⢠Many other better artists than me whose work inspired many of the
doodles in these slides
5. Weâre not satisfied with the
current trajectory of digital health
But, at Health Catalyst, weâre not
satisfied with ourselves, either. We
are far from perfect.
6. Fair Warning to the Executives in the Audience
⢠Get ready to dive into topics that you need to
understand
⢠The most expensive capital purchase in the
history of your healthcare system wasnât a new
hospital⌠it was your EHR
⢠Software runs your company, for better or worse
⢠Case in point: The ransomware impact on the UK National
Health System last week
⢠The healthcare CEOs who thrive going forward, will
understand their software technology and data. They
will rise to the top.
7. Sanders Version 1.0 Definition of a
Data Operating System (DOS)
A data operating system combines real-time, granular data; and
domain-specific (e.g. healthcare), reusable analytic and computational
logic about that data, into a single computing ecosystem for
application development. A data operating system can support the
real-time processing and movement of data from point-to-point, as well
as batch-oriented loading and computational analytic processing on
that data.
8. Health Catalyst Data Operating System
Data Platform
Data Ingest
Real-time
Streaming
Source
Connectors
Catalyst Analytics Platform Core Data Services
Real time
Processing
Fabric
Registries Terminology
& Groupers
Apps
FHIR
Data Quality
Data
Governance
Pattern
Recognition
Hadoop/
Spark
Data Export
3rd Party
Applications
Registry
Builder
Leading
Wisely
Care
Management
SAMD &
SMD
Atlas
Hospital IT
Applications
EHR
Integration
Machine Learning
Models
Patient & Provider
Matching
Real time Data Services
NLP
Lambda
Architecture
CAFĂ
Benchmarks
Choosing
Wisely
Patient
Safety
Measures
Builder
ACO
Financials
Patient
Engagement and more âŚ
HL7
Data Pipelines
ML Pipelines
Security, Identity
& Compliance
Metadata
Data Lake
9. Apps and Fabric Run on Any Data Platform
Fabric & Machine Learning
Apps
Data to FHIR mapping
Various Data Platforms
HadoopHealth Catalyst
Open APIs (FHIR etc)
Epic CernerTeradata Home grownIBM
3rd Party
Applications
Registry
Builder
Leading
Wisely
Care
Management
Hospital IT
Applications
CAFĂ
Benchmarks
Choosing
Wisely
Patient
Safety
Measures
Builder
ACO
Financials
Patient
Engagement and more âŚ
Registries Terminology
& GroupersFHIR
SAMD &
SMD
EHR
Integration Models
Patient & Provider
Matching ML Pipelines
Security, Identity
& Compliance
Oracle
10. Seven Attributes of the Healthcare Data Operating System
1. Reusable clinical and business logic: Registries, value sets, and other data logic lies on top of the raw data and
can be accessed, reused, and updated through open APIs, enabling 3rd party application development.
2. Streaming data: Near or real-time data streaming from the source all the way to the expression of that data through
the DOS, that can support transaction-level exchange of data or analytic processing.
3. Integrates structured and unstructured data: Integrates text and structured data in the same environment.
Eventually, incorporates images, too.
4. Closed loop capability: The methods for expressing the knowledge in the DOS include the ability to deliver that
knowledge at the point of decision making, for example back into the workflow of source systems, such as an EHR.
5. Microservices architecture: In addition to abstracted data logic, open microservices APIs exist for DOS operations
such as authorization, identity management, data pipeline management, and DevOps telemetry. These
microservices also enable third party applications to be built on the DOS.
6. Machine Learning: The DOS natively runs machine learning models and enables rapid development and utilization
of ML models, embedded in all applications.
7. Agnostic data lake: Some or all of the DOS can be deployed over the top of any healthcare data lake. The
reusable forms of logic must support different computation engines; e.g. SQL, Spark SQL, SQL on Hadoop, et al.
13. Content is King, the Network is Kong
⢠If you look at modern businesses, data content is becoming the
driving force behind their business strategy, e.g., GE, Tesla,
Google, Facebook, Delta Airlines, UnitedHealth, Amazon, etc.
⢠The network of people around this data content creates valueâ
think of Metcalfeâs Lawâ and sticky relationships
14. âHealthcare CEO, what is your Digitization Index?â
Data Assets x Data Usage x Data Skilled Labor
Healthcare is one of the
least digital sectors, and it
shows in profit-margin
growth.
Source: McKinsey Corporate Performance
Analysis Tool; BEA; McKinsey Global Institute
analysis
15. C-level Advice for a Digital Healthcare Future
1. Population health, value based care, and precision medicine are all
about DATA
⢠You need a strategic data acquisition strategyâ What data do you need
for population health, risk contracting, and precision medicine? How do
you acquire it?
⢠You need a Chief Analytics or Chief Data Officerâ is that your CIO or
not?
2. Your physicians and nurses are over-measured and under-valued, in
large part because they are slaves to data entry and poor software
⢠You need to push all vendors to follow modern, open software APIs,
including but not limited to FHIR
3. You need a Data Operating System-- leverage and expand the
capability of your Enterprise Data Warehouse
16. DOS Need #1: The âShark Tankâ Story
20+ Healthcare IT startups
Pitching great software
applications and creative
ideas
No solution or appreciation for the underlying healthcare data that they
needed
In my head: âWe must give these great ideas and applications the data
they need. They cannot possibly afford to build the data infrastructure
and skills that we have in Health Catalyst. The industry canât afford it.â
18. DOS Need #2: Mergers & Acquisitions
⢠The new company is not integrated until the data is integrated
⢠HIEâs are not sufficient for data integration⌠not even close
⢠Rip and replacing EHRs with a single, common vendor is not an
affordable strategy
⢠Besides, hybrid vigor is a good thing⌠you should not put all of your digital eggs in
one basket
19. Rip and Replace is Not the Answer for M&A
Hundreds of millions of $$ in additional costs and lost time
Keep the disparate, existing source systemsâ
Finance, supply chain, registration, scheduling, A/R, EHRs, etc.
Virtually Integrated with the Data Operating System
Share transaction-level data.
Integrate data for common metrics around finance, clinical quality, utilization, etc.
20. DOS Need #3: Enable a Personal Health Record
Updated, integrated, shareable, downloadable, transportable
Healthcare data is currently locked in
the cage of the health system and the
technology of the EHR
DOS
21. DOS Need #4: Scaling Existing, Home Grown Data
Warehouses
⢠Home grown data warehouses are easy to start and build, but
expensive to evolve and maintain
⢠There are many of these in healthcare
⢠But they are also hard to retire⌠what do you do?
⢠Rip and replace with a vendor solution? Not attractive.
⢠That was the only answer Health Catalyst had to these scenarios, and that
answer does not sell
⢠Not good for Health Catalyst, not good for the industry. We both
need better options.
22. Selfishly Speaking, Health Catalyst Had to Solve This
But the industry will benefit, too. Thatâs the beauty of capitalism. ď
The DOS Fabric and our new applications addresses this need
23. DOS Need #5: The Human
Health Data Ecosystem
And, by th
e way, we donât have much of
any data on healthy patients
Precision medicine &
population health need more
data than we currently collect
in the ecosystem⌠WAY
more data
Only 8% of the data we need
for precision medicine and
population health resides in
todayâs EHRs
24. Healthcare Data
⢠Ingesting healthcare data into a data lake or data
warehouse is now essentially a commodity, thanks to
open source technology and a late binding, schema-on-
read approach to data models
⢠Whatâs not a commodity?
⢠Understanding the data content, data models, and insanely
complicated nuances of healthcare data
⢠The analytic logic or âdata bindingsâ to apply to that data
⢠The technology and skills to deliver this data to the right
person, at the right time, in the right modality
⢠Keeping up with the changes in the source system data, aka,
change data capture
⢠Data quality management and governance
⢠Scaling all of this for a single healthcare system
25. For dramatic impact, let me share with you the data
content sources in the Health Catalyst libraryâŚ
34. Other Sources of Healthcare-Related Data
34
1. 2010 US Census Detail for
State of Colorado
2. Affiliate Provider Database
3. All Payer All Claims (certain
States) ---In process UT, CO,
MA
4. Alliance Decision Support
5. Allscripts - Ambulatory
Practice Management
6. Allscripts - Patient Flow
7. Allscripts EHRQIS - Quality
8. Avaya
9. Axis (MDX)
10.Bed Ready - Other
11.Cerner Signature
12.CMS Standard Analytical Files
13.Daptiv
14.Echo Credentialing - Provider
Management
15.ePIMS
16.First Click-Wellness
17.FlightLink
18.GE (IDX) Centricity - Practice
Management
19.HCUP (NRD, NIS, NED
Sample sets)
20.Health Trac
21.HealtheIntent
22.Hyperion
23.InitiateEMPI
24.Innotas
25.IVR Outreach Detail
26.MIDAS - Credentialing Module
27.Morrisey Medical Staff Office
for Web (MSOW)
28.National Ambulatory Care
Reporting System (NACRS)
29.Nextgate EMPI
30.Onbase
31.PHC Legacy EDW
32.QXNT/Cactus - Provider
33.SMS Legacy - Other
34.Truven Quality
35.University HealthSystem
Consortium - Clinical and
Operational Resource
Database
36.University HealthSystem
Consortium - Regulatory
35. Master Reference & Terminology Data Content
35
1. AHRQ Clinical Classification Software (CCS)
2. Charlson Deyo and Elixhauser Comorbidity
3. Clinical Improvement Grouper (Care Process Hierarchy)
4. CMS Hierarchical Condition Category
5. CMS Place Of Service
6. LOINC
7. National Drug Codes (NDC)
8. NPI Registry
9. Provider Taxonomy
10.Rx Norm
11.CMS/NQF Value Set Authority Center
36. Thatâs the data we have in the US healthcare ecosystem,
today; but we are barely getting started on the digitization of
the industry, so imagine what the future data ecosystem
looks like.
37. DOS Need #6: Providers becoming payers
⢠The insurance industry is the tail wagging the
healthcare dog
⢠Does anyone, other than those in the insurance
industry, seriously believe that the current
payer/insurance economic model is working?
⢠Critical to the improvement of this situation is the
ability for providers to model and assume financial
risk, and compete with, or completely disintermediate,
insurance companies.
⢠With a Data Operating System, providers have
more and better data to model and manage risk
than the insurers.
38. DOS Need #7: Extend the life and value of current
EHR investments
39. Good News, Bad News
Healthcare is using âinformation technology from the last century.â
⢠Dr. Robert Pearl, CEO, Permanente Medical Group; CNBC Interview, 16 May 2017
⢠9,000 physicians, 34,000 staffers
⢠Given that weâve invested $30B in tax money, plus billions more
out-of-pocket, on that information technology, what do we do
now?
⢠Replace? Not a good idea to spend tens or hundreds of millions of
dollars on incrementally better products, at best
⢠We can make what we have, better, while new products emerge
We are more digitized in healthcare than ever before, butâŚ
40. The inevitable curve for technology products is stretched or compressed by market
demand and the pace of technological commoditization associated with the product
The demand for EHRs
was stretched by
federal incentives.
Thatâs over.
The underlying software
and database
technology of EHRs
was commoditized a
long time ago.
We can stretch the
lifecycle of
EHRs with DOS and
open APIs, e.g. FHIR.
41. Role Model Vendors in Silicon Valley
⢠Google, Facebook, Amazon, Microsoft, Twitter
⢠Not Apple, by the way
⢠Apache, W3C, Internet Engineering Task Force, Open Compute
Project, et al
⢠How do healthcare vendors stack up? Terribly. The evidence is
clear.
⢠Even some of the vendor âapp storesâ that appear to support open
APIs, like FHIR, are contractually worded to take your IP and profit
from it, if you contribute to the app store
Collaborate on standardization, compete on innovation
43. These are the
tools available
for modern
software
development.
We are at the
beginning of a
software
technology
renaissance.
Most of these
tools are, in one
form or another,
open source.
44. With Open, Standard Software APIsâŚ
âEHRs would become commodity components in a larger platform that
would include other transactional systems and data warehouses
running myriad apps, and apps could have access to diverse sources
of shared data beyond a single health systemâs records.â
âA 21st-Century Health IT System â Creating a Real-World Information Economyâ, Kenneth D. Mandl, MD,
MPH; Isaac S. Kohane, MD, MPH; NEJM, 18 May 2017.
45. Why we can do this,
technically, like never
before
46. A Partial History of my Experience with
Open Systems Standards
At the risk of jinxing myself, I think I know the major patterns of success and failure
47. At Northwestern Memorial Healthcare, 2005-2009
We didnât call it a
DOS, but we had what
amounts to an early
version of it, over 10
years ago.
Supported analytics
and near-real time
exchange of single
records, before HIEs.
Technology options
are much better now.
48. Hybrid Big Data-SQL Architectures
Gartner: Hybrid Transactional/Analytical Processing (HTAP)
âBecause traditional data warehouse practices will be outdated by the end of 2018,
data warehouse solution architects must evolve toward a broader data management
solution for analytics.â
49. The Hadoop, Big
Data ecosystem
gives us all sorts of
options that we never
had before,
technically and
financially
Note of thanks to Ben Stopford
at Confluent
New Technology, New Data Capabilities, at a
Fraction of Past Cost
50. Lambda Architecture: Two Streams of Data
One stream for batch computations, one for real time transactions and computations
Two different code sets
51. Kappa Architecture: One Stream of Data
One stream for batch and real-time computations in the serving layer
One code set
Both architectures can be
implemented with a combination
of open source tools like Apache
Kafka, Apache HBase, Apache
Hadoop (HDFS, MapReduce),
Apache Spark, Apache Drill,
Spark Streaming, Apache Storm,
and Apache Samza.
Note of thanks to Julian Forgeat of Google
52. Health Catalyst Data Operating System
Data Platform
Data Ingest
Real-time
Streaming
Source
Connectors
Catalyst Analytics Platform Core Data Services
Real time
Processing
Fabric
Registries Terminology
& Groupers
Apps
FHIR
Data Quality
Data
Governance
Pattern
Recognition
Hadoop/
Spark
Data Export
3rd Party
Applications
Registry
Builder
Leading
Wisely
Care
Management
SAMD &
SMD
Atlas
Hospital IT
Applications
EHR
Integration
Machine Learning
Models
Patient & Provider
Matching
Real time Data Services
NLP
Lambda
Architecture
CAFĂ
Benchmarks
Choosing
Wisely
Patient
Safety
Measures
Builder
ACO
Financials
Patient
Engagement and more âŚ
HL7
Data Pipelines
ML Pipelines
Security, Identity
& Compliance
Metadata
Data Lake
53. Apps and Fabric Run on any Data Platform
Fabric & Machine Learning
Apps
Data to FHIR mapping
Various Data Platforms
HadoopHealth Catalyst
Open APIs (FHIR etc)
Epic CernerTeradata Home grownIBM
3rd Party
Applications
Registry
Builder
Leading
Wisely
Care
Management
Hospital IT
Applications
CAFĂ
Benchmarks
Choosing
Wisely
Patient
Safety
Measures
Builder
ACO
Financials
Patient
Engagement and more âŚ
Registries Terminology
& GroupersFHIR
SAMD &
SMD
EHR
Integration Models
Patient & Provider
Matching ML Pipelines
Security, Identity
& Compliance
Oracle
54. Seven Attributes of the Healthcare Data Operating System
1. Reusable clinical and business logic: Registries, value sets, and other data logic lies on top of the raw data and
can be accessed, reused, and updated through open APIs, enabling 3rd party application development.
2. Streaming data: Near or real-time data streaming from the source all the way to the expression of that data through
the DOS, that can support transaction-level exchange of data or analytic processing.
3. Integrates structured and unstructured data: Integrates text and structured data in the same environment.
Eventually, incorporates images, too.
4. Closed loop capability: The methods for expressing the knowledge in the DOS include the ability to deliver that
knowledge at the point of decision making, including back into the workflow of source systems, such as an EHR.
5. Microservices architecture: In addition to abstracted data logic, open microservices APIs exist for DOS operations
such as authorization, identity management, data pipeline management, and DevOps telemetry. These
microservices also enable third party applications to be built on the DOS.
6. Machine Learning: The DOS natively runs machine learning models and enables rapid development and utilization
of ML models, embedded in all applications.
7. Agnostic data lake: Some or all of the DOS can be deployed over the top of any healthcare data lake. The
reusable forms of logic must support different computation engines; e.g. SQL, Spark SQL, SQL on Hadoop, et al.
55. Health Catalyst Initial Fabric Services
Fabric.Identity & Fabric.Authorization microservices
⢠Fabric.Identity provides authentication i.e., verifying the user is who he/she is claiming to be. Fabric.Authorization stores permissions for various user groups
and then given a user returns the effective permissions for that user.
Fabric.MachineLearning microservice
⢠A micro-service that plugs into a data pipeline (like ours) and runs machine learning models written in R, Python and TensorFlow. It encapsulates all the ML
tools inside so all you need to do is supply a ML model.
Fabric.EHR set of microservices
⢠Enables SQL bindings, ML models and application code to show data and insights inside the EHR workspace using SMART on FHIR.
Fabric.PHR set of microservices
⢠Provides the ability to download, share, and update a Personal Health Record. Integrates data from all available EMRs in a patientâs health ecosystem.
Fabric.Terminology set of microservices
⢠Provides the ability for application developers to leverage local and national terminology mapping and update services.
Fabric.FHIR microservice
⢠A data service that sits on top of any data platform (HC EDW, Data Lake, Hadoop etc). Applications using this data service become portable to any other
data platform. It uses data to FHIR mappings (written in Sql, HiveSql etc) to map data and implements an Analytics on FHIR API using a cache based on
Elastic Search.
Fabric.Telemetry
⢠Provides infrastructure to web and mobile applications to send telemetry data to our Azure cloud and provides tools to analyze it using ElasticSearch.
Default: Build in the FHIR framework, unless itâs not possible
56. FHIR Mappings (SQL version)
<DataSource><Sql>
SELECT PatientID AS EDWPatientID, CASE GenderCD WHEN 'Female' THEN 'female' WHEN 'Male'
THEN 'male' ELSE 'unknown' END AS gender,BirthDTS as birthDate
FROM [Person].[SourcePatientBASE]
</Sql></DataSource>
<DataSource Path="condition.code" type="object"><Sql>
SELECT PatientID AS EDWPatientID, CONCAT(DiagnosisSourceID,'-',RowSourceDSC,'-
',DiagnosisTypeDSC) as KeyLevel1, CONCAT(DiagnosisSourceID,'-',RowSourceDSC,'-',DiagnosisTypeDSC)
as KeyLevel2, CASE CodeTypeCD WHEN 'ICD9DX' THEN 'http://hl7.org/fhir/sid/icd-9-cm' WHEN
'ICD10DX' THEN 'http://hl7.org/fhir/sid/icd-10-cm' ELSE NULL END AS system, DiagnosisCD as code,
DiagnosisDSC as text
FROM [Clinical].[DiagnosisBASE]
</Sql></DataSource>
56
This is a real world example of how we are converting our relational data models into FHIR information models
58. Sampling of the 200+ Health Catalyst Reusable Value Sets
These, along with the CMS/NQF/MACRA values sets are being ported to the Measures Builder Library (MBL)
content management system, for reuse in Health Catalyst and 3rd party applications.
Acute Coronary Syndrome (ACS)
Blood Utilization Dashboard
Breast Milk Feeding
Catheter Associated Urinary Tract Infection (CAUTI)
Prevention
Central Line Associated Blood Stream Infections (CLABSI)
Prevention
Colorectal Surgery
Early Mobility in the ICU
Glycemic Control in the Hospital
Heart Failure
Joint Replacement - Hip & Knee
Labor and Delivery
Patient Flight Path - Diabetes
Patient Safety Explorer
Pediatric Appendectomy Pediatric Asthma
Pediatric Explorer
Pediatric Sepsis Pneumonia
Population Explorer
Readmission Explorer
Sepsis Prevention
Spine Surgery
Stroke (Acute Ischemic & TIA)
Surgical Site Infection Prevention
Venous Thrombo-Embolism (VTE) Prevention
Coronary Artery Bypass Graft Surgery
Diabetes - Adult
Chronic Obstructive Pulmonary Disease (COPD)
59. Central line-associated bloodstream infection (CLABSI) Risk â Clinical Analytics and Decision Support
Congestive Heart Failure, Readmissions Risk â Clinical Analytics and Decision Support
COPD, Readmissions Risk â Clinical Analytics and Decision Support
Respiratory (COPD, Asthma, Pneumonia, & Resp. Failure), Readmission Risk â Clinical Analytics and Decision Support
Forecast IBNR claims/year-end expenditures â Financial Decision Support
Predictive appointment no shows â Operations and Performance Management
Pre-surgical risk (Bowel) â Clinical Analytics and Decision Support and client request
Propensity to pay â Financial Decision Support
Patient Flight Path, Diabetes Future Risk â Clinical Analytics and Decision Support
Patient Flight Path, Diabetes Future Costâ Clinical Analytics and Decision Support
Patient Flight Path, Diabetes Top Treatments â Clinical Analytics and Decision Support
Patient Flight Path, Diabetes Next Likely Complications (Glaucoma) â Clinical Analytics and Decision Support
Patient Flight Path, Diabetes Next Likely Complications (Retinopathy) â Clinical Analytics and Decision Support
Patient Flight Path, Diabetes Next Likely Complications (ESRD) â Clinical Analytics and Decision Support
Plus several more⌠(Nephropathy, Cataracts, CHF, CAD, Ketoacidosis, Erectile Dysfunction, Foot Ulcers)
Machine Learning Models in DOS
In Development
Built
Planned
Patients Like This â Clinical Analytics and Decision Support
Sepsis Risk â Clinical Analytics and Decision Support
Readmission Risk â Clinical Analytics and Decision Support
Post-surgical risk (Hips and Knees) â Clinical Analytics and Decision Support
INSIGHT socio-economic based risk â Clinical Analytics and Decision Support and client request
Native SQL/R predictive framework and standard package - Platform
Feature selection, Parallel Models, Rank and Impact of Input Variables â Platform
Predictive ETL batch load times â Platform
Composite Health Risk â Clinical Analytics and Decision Support
Composite All Cause Harm Risk â Clinical Analytics and Decision Support
Early detection of CLABSI, CAUTI, Clostridium difficile (c. diff) hospital infections â Clinical Analytics and Decision Support
Early detection of Sepsis/Septicemia (Blood Infection) â Clinical Analytics and Decision Support
Hospital Census Prediction - Operations and Performance Management
Hospital Length of Stay Prediction â Operations and Performance Management
Public data sets, benchmarks, âCatalyst Riskâ, expected mortality, length of stay â CAFĂ collaboration
Clusters of population risk (near term risk/cost) â Population Health and Accountable Care
60. Managing and Reusing the Explosion of Measures
and Value Sets
Measures Builder Library (MBL) is a content management system and set of APIs that allows registries, value sets, and other
measures to be consistently managed, verified, governed, and reused for application development
61. Role Model Software Development for the Fabric
1. Open Source & Collaborative Development: All code is available on
github.com/HealthCatalyst. External developers can submit enhancements.
2. Open & Modular: All APIs will be publicly published. Customers can pick and choose from the
Health Catalyst components or replace any component with their own or from a third party
3. Secure by Design: Security services make it easy to build security into any application
4. Microservices architecture: REST-based services that can be called from web, mobile or BI
tools
5. Big Data: Leverages Big Data technologies to provide high-speed and reliable platform
6. Easy Install & Updates: All services install via Docker
7. Scalable: All services are designed to run in multiple nodes and cluster themselves automatically
Why canât healthcare be the role model, instead of Silicon Valley?
Should we aspire to something less? Is that acceptable?
62. How Will We Know if We are a Role Model?
1. Successfully implementing the Data Operating System
2. Fast, simple releases every 2 weeks. Constant improvement of our apps.
3. Analytics driven UI and applicationsâintelligent user interfaces, driven by situational awareness of the
physician, nurse, patient, etc.
4. Constantly consuming and expanding the ecosystem of data as the enabler to great apps, not apps as the
enabler of data
5. Machine learning and pattern recognition that clearly amazes all of us with its value to humanity
6. Economic scalability-- we're so efficient with our products, which work across multiple OS and data
topologies, that it's economically efficient to constantly deploy
7. Auto-fill analyticsâa play on words, but how do we, through pattern recognition and machine learning,
anticipate next steps in our clientsâ decision making?
8. When Google, Facebook, Amazon, and Microsoft come to us for advice about software success and value
These are Health Catalystâs software development vital signs
63. For Health Catalyst Clients
63
Join and explore the Health Catalyst Community
to learn more and engage with our team
community.healthcatalyst.com
64. Health Catalyst Platform Community
64
Ask Questions about DOS
Request Features
Review Roadmaps and
Release Notes
Contact our Community Manager,
Kate Weaver, to request access
kate.weaver@healthcatalyst.com
65. Summary Thoughts
There will be people who hope we fail.
There will be people who expect us to fail.
There are many more people who hope we donât.
Thatâs who weâre working for.
66. Healthcare Analytics Summit 17
ERIC J. TOPOL
Author, The Patient Will
See You Now and The
Creative Destruction of
Medicine. Director,
Scripps Translational
Science Institute
DAVID B. NASH,
MD. MBA
Dean, Jefferson
School of
Population
Health
JOHN MOORE
Founder and Managing
Partner, Chilmark Research
ROBERT A. DEMICHIEI
Executive Vice President and
Chief Financial Officer, University
of Pittsburgh Medical Center
THOMAS D.
BURTON
Co-Founder, Chief
Improvement Officer,
and Chief Fun Officer,
Health Catalyst
DALE SANDERS
Executive Vice
President, Product
Development,
Health Catalyst
THOMAS DAVENPORT
Author , Consultant
Competing on Analytics*, ,
Analyitcs at Work, Big Data at
Work, Only Humans Need
Apply:Winners and Losers in the
Age of Smart Machines.
*Recognized by Harvard
Business Review editors as one
the most important management
ideas of the past decade, one of
HBRâs ten must-read articles in
that magazineâs 90-year history.
Summit highlights
Industry Leading Keynote Speakers
Weâll hear from well-known healthcare visionaries. Weâll also
hear from two C-level executives leading large healthcare
organizations.
CME Accreditation For Clinicians
HAS 17 will again qualify as a continuing medical education
(CME) activity.
30 Educational, Case Study, and Technical
Sessions
We have the most comprehensive set of breakout sessions of
any analytics summit. Our primary breakout session focus is
giving you detailed, practical âhow toâ learning examples
combined with question and opportunities.
The Analytics Walkabout
Back by popular demand, the Analytics Walkabout will feature
24 new projects highlighting a variety of additional clinical,
financial, operational, and workflow analytics and outcomes
improvement successes.
Analytics-driven, Hands-on Engagement for
Teams and Individuals
Analytics will continue to flow through the three-day summit
touching every aspect of the agenda.
Networking and Fun
Weâll provide some new innovative analytics-driven
opportunities to network while keeping our popular fun run and
walk opportunities and dinner on the down.
Early Bird
PricingSINGLE ENTRY
1 Pass -
$595
Save $300
BEST VALUE
3 PACK
3 Passes -
$545/each
Save
$1,000+5 PACK
5 Passes -
$495/each
Save
$2,000+
Sept. 12-14, 2017
Grand America Hotel
Salt Lake City, UT
Editor's Notes
To deliver to this future vision we are announcing a broad expansion of what we have previously called the Catalyst Analytics Platform. The Health Catalyst Data Operating System will include all the data ingest, processing, and distribution capabilities and software services needed to build rich, immersive healthcare applications needed.
At the core of the Health Catalyst Data Operating System will be Catalystâs Metadata driven Analytics Engine.
The Analytics engine will add real-time data ingestion and analytics computation to its existing capabilities and provide a significant expansion of its machine learning capabilities. We will provide deep support for NLP as well. This builds on top of the support it provides to connect and ingest to 140+ of the most common data sources in healthcare with many more to come.
We will also add a layer of services to the kernel of the data operating system that will allow you to integrate with the Metadata, Data Processing Pipeline, and the raw data in the analytics system.
On top of that kernel we will introduce a suite of healthcare specific services that expose healthcare data in a way that has never been done before in the industry. Historically healthcare data has been walled off by vendors for their use only. The Health Catalyst Data Operating System will allow applications to start data rich rather than data poor. Over the next day and half we will be presenting on the various services we are building in this layer. No longer will analytics be relegated to the realm of dashboards and reports.
In the app layer these we are taking two approaches to close the usability and information gap and deliver these next generation experiences. First we will do the work to enable you to integrate the information directly into your EHR screens so that information is provided in context to those who need it â where they need it. In addition to that we are building a suite of applications that are built with usability and analytics in mind and at the forefront. Like EMRs should have been from the beginning.
Over the next couple of days you will be learning more about these experiences we are building and why we chose them to start with and this is only the beginning of what we will do.
We will also be opening up these same services for third parties to leverage.
To deliver to this future vision we are announcing a broad expansion of what we have previously called the Catalyst Analytics Platform. The Health Catalyst Data Operating System will include all the data ingest, processing, and distribution capabilities and software services needed to build rich, immersive healthcare applications needed.
At the core of the Health Catalyst Data Operating System will be Catalystâs Metadata driven Analytics Engine.
The Analytics engine will add real-time data ingestion and analytics computation to its existing capabilities and provide a significant expansion of its machine learning capabilities. We will provide deep support for NLP as well. This builds on top of the support it provides to connect and ingest to 140+ of the most common data sources in healthcare with many more to come.
We will also add a layer of services to the kernel of the data operating system that will allow you to integrate with the Metadata, Data Processing Pipeline, and the raw data in the analytics system.
On top of that kernel we will introduce a suite of healthcare specific services that expose healthcare data in a way that has never been done before in the industry. Historically healthcare data has been walled off by vendors for their use only. The Health Catalyst Data Operating System will allow applications to start data rich rather than data poor. Over the next day and half we will be presenting on the various services we are building in this layer. No longer will analytics be relegated to the realm of dashboards and reports.
In the app layer these we are taking two approaches to close the usability and information gap and deliver these next generation experiences. First we will do the work to enable you to integrate the information directly into your EHR screens so that information is provided in context to those who need it â where they need it. In addition to that we are building a suite of applications that are built with usability and analytics in mind and at the forefront. Like EMRs should have been from the beginning.
Over the next couple of days you will be learning more about these experiences we are building and why we chose them to start with and this is only the beginning of what we will do.
We will also be opening up these same services for third parties to leverage.
I like the polygon graphic in the upper right, but there is a big long horizontal part that I would like to change to be more interesting.
I like the polygon graphic in the upper right, but there is a big long horizontal part that I would like to change to be more interesting.