This talk presents and explains Health Web Science, Health Web Observatories, and the technologies needed to create and utilize them as an approach towards preferable health outcomes in the 21st century. Health Web Science (HWS), which impact of the Web on health and wellbeing, aims towards a preventative, participatory, personalized, and predictive (P4) model of healthcare. HWS posits this can be achieved by the leveraging of the Web’s data, resources and nature. In studying the Web, it is impossible to ignore the evolving social, political, economic, policy questions that emerge as a result of the use of the Web. Health Web Observatories play a role by enabling the study of these data, make available the metadata, and thereby enable it as a feedback mechanism for preferable futures.
💎VVIP Kolkata Call Girls Parganas🩱7001035870🩱Independent Girl ( Ac Rooms Avai...
Luciano informs healthcare_2015 Nashville, TN USA July 30 2015
1. Health Web Observatories:
Creating Preferable Health Outcomes
through
Health Web Science
Joanne S. Luciano, PhD
Predictive Medicine, Inc., Belmont, MA (predmed.com)
Rensselaer Polytechnic Institute, Troy, NY
30 July 2015
INFORMS Healthcare Conference 2015
Nashville, Tennessee, USA
7/30/15
1
2. PRESENTER
Joanne S. Luciano
Enable
Health and
Wellbeing
through
Knowledge
Technology
BS, MS Computer Science
PhD Cognitive and Neural Systems
(Computational Neuroscience)
Wang Labs
Harvard Medical School
MITRE
Lotus Development
Predictive Medicine, Inc.
Rensselaer Polytechnic Institute
GE Global Research Labs
Interests
Flying planes, rocks: climbing,
balancing and photographing them
Community
BioPathways Consortium, BioPAX, W3C
HCLSIG, Yosemite Project, FIBO
Email:
jluciano@rpi.edu
jluciano@predmed.com
Always open to exploring opportunities.
7/30/15
2
3. Multidisciplinary International Team
7/30/15
3
Grant Cumming, Medical Doctor, NHS Grampian,
Honorary Professor, University of the Highlands and
Islands, AB24 2ZN, Aberdeen, United Kingdom,
grant.cumming@nhs.net
Tara French,Research Fellow, Institute of Design
Innovation, The Glasgow School of Art, Horizon Scotland,
Digital Health Institute, Forres IV36 2AB, United
Kingdom, tara.french@dhi-scotland.com
Eva Kahana,Distinguished University Professor and The
Pierce T. and Elizabeth D. Robson Professor of the
Humanities, Case Western Reserve University, Mather
Memorial Building 231B, Cleveland OH 44106, United
States of America, eva.kahana@case.edu
David Molik,Computational Developer, Cold Spring
Harbor Laboratories, One Bungtown Road, Cold Spring
Harbor NY 11724, United States of America,
dmolik@cshl.edu
4. Objectives
— Formulating Healthcare for the 21st Century
— Are we where we should be?
— What’s missing?
— How do we use the Web?
— How can we use the Web?
— How do we know what will work?
— What are the tools, technologies, and resources
needed?
— How do we evaluate effectiveness?
7/30/15
4
5. Brendan Ashby
Master’s Thesis (RPI)
Actively
SEEKING FUNDING
Nightingale
Research to Practice Timeline(earlier work: 10 years in Software Research & Development and Product Development)
20091993
World Congress on
Neural Networks,
July 11-15, 1993,
Portland, Oregon SIG
Mental Function and
Dysfunction
Sam Levin
Jackie Samson,
Mc Lean Hospital
Depression
Research
1996
1995
20081994
Patents Sold
to Advanced
Biological
Laboratories
Belgium
Patents Offered at
Ocean Tomo
Auction Chicago, IL
US Patent No.
6,317,73
Awarded
US Patents
No. 6,063,028
Awarded
2001
2000
PhD
Thesis Proposal
Approved
Workshop Neural Modeling of
Cognitive and Brain Disorders
BioPAX
?
Linked Data
W3C HCLS
BioDASH
EPOS
2006
EMPWR
Poster Presented
ISMB 1997
PSB 1998
1997
2010
Rensselaer
(RPI)
2011 2012
2013
U Pitt
Greg Siegle
Depression
Collaboration
Yuezhang
Xiao
Master’s
Thesis
(RPI)
Failed to get
Funding for
Proactive
Multimodal
Depression
Treatment
Health Web
Science
7/30/15
5
2014 2015
Is 15-20 years too long to get from research to practice?
6. Healthcare Singularity
and the age of Semantic Medicine
http://research.microsoft.com/en-us/collaboration/fourthparadigm/4th_paradigm_book_part2_gillam.pdf
2,300 years
after the first
report of
angina for the
condition to
be commonly
taught in
medical
curricula,
modern
discoveries
are being
disseminated
at an
increasingly
rapid pace.
7/30/15
6
7. Healthcare Singularity
and the age of Semantic Medicine
http://research.microsoft.com/en-us/collaboration/fourthparadigm/
4th_paradigm_book_part2_gillam.pdf
Focusing on the last 150 years, the trend still appears to be linear,
approaching the axis around 2025.
7/30/15
7
8. Times have changed
— Aging population (end of life costly)
— More people with chronic illnesses
(increased cost)
— The end of the blockbuster era (decrease
in revenues, increase in drug development
cost)
— Need lower drug development cost
— Personalized Medicine (right treatment to
the right patient at the right time)
— Improved patient response to treatment
(Evidence Based)
— Web and Mobile
— The technology (ubiquitous, monitor)
— Patient engagement increasing
8
Photos: http://www.flickr.com/photos/sepblog/4014143391/
http://allthingsd.com/files/2013/07/photo-12.jpg
7/30/15
9. Data Driven Medicine:
3 Shifts in thinking and practice:
— Data, Not Programs (reuse!)
— Sharing, Not Hoarding (or hiding)
— Personal, Not (only) Population
9
7/30/15
12. 7/30/15
12
The impact of the personal computer and internet on an individuals
potential to influence society.
13. 7/30/15
13
Health Web Science recognizes the revolutionary impact of the
Internet, made possible through the Web, with the potential to
change health behaviors and health care worldwide. This impact on
changing the practice of medicine can be considered in three areas:
power, experience and speed.
14. 7/30/15
14
Web Science (WS)
Web Science is about investigating how human behavior co-constitutes
the Web. People who impose regulations, engineer the Web, produce
content, or even just click on links change the Web how other people will
see it. Vice versa, what people see and do on the Web will change their
behavior. Web Science is about understanding this cycle.
SteffenStaab
15. 7/30/15
15
1/3 world’s population use the Web [1]
80% look for health information online [2]
• Studies impact of the Web on health and wellbeing
• Aims towards a preventative, participatory, personalized,
and predictive (P4) model of healthcare.
• Posits P4 can be achieved by the leveraging of the Web’s
data, resources and nature.
• Studies the evolving social, political, economic, policy
health related questions that emerge as a result of the use
of the Web.
Health Web Science (HWS)
[1] Miniwatts Marketing Group 2012
[2] California Healthcare Foundation, Fox, S. 2011
17. 7/30/15
17
The World Wide Web
• Directly influences conscious behavior (Kahneman, System 2) through imparting information
• Indirectly influences unconscious behavior (Kahneman, System 1) through social interactions
• “co-conscious” interactions are the emergent collective consciousness of the networ
The Web and Human Behavior Influence Health Outcomes
HWS seeks to understand the dynamics
of these behavioral influences in order
to support users in achieving better
health outcomes
18. 7/30/15
18
Instruments for Web Study – what works and what doesn’t,
i.e. when to use technology, policy, transparency?
• Enable data to be found
• Make the metadata available for use by others
• Study the data in context using metadata
• Aggregation and presentation of observations enable
a feedback mechanism for preferable futures.
A health Web Observatory is a system that gathers and
links to health data on the Web in order to answer
questions about the Web, the users of the Web and the
way that they affect each other within the context of
healthcare.
Health Web Observatory (HWO)
19. How?
Technologies Needed to enable Health Web Science and the
vision for 21st Century Medicine
It’s all about the meaning!
— Semantic Enabling: Web Observatories
— Semantic Interoperability:
— Shared Meaning: Yosemite Project
— Inference: Ontologies and OWL
— Linked Data: RDF, HTTP, URIs as
terms
7/30/15
19
21. How?
Technologies Needed to enable Health Web Science and the
vision for 21st Century Medicine
It’s all about the meaning!
— Semantic Enabling: Web Observatories
— Semantic Interoperability:
— Shared Meaning: Yosemite Project
— Inference: Ontologies and OWL
— Linked Data: RDF, HTTP, URIs as
terms
7/30/15
21
23. Unified Medical Language System
Knowledge Sources
The UMLS has three tools, called the
UMLS Knowledge Sources:
— Metathesaurus: Terms and codes from many
vocabularies, including CPT®, ICD-10-CM, LOINC®,
MeSH®, RxNorm, and SNOMED CT®
— Semantic Network: Broad categories (semantic
types) and their relationships (semantic relations)
— SPECIALIST Lexicon and Lexical Tools: Natural
language processing tools
7/30/15
23
27. How?
Technologies Needed to enable Health Web Science and the
vision for 21st Century Medicine
It’s all about the meaning!
— Semantic Enabling: Web Observatories
— Semantic Interoperability:
— Shared Meaning: Yosemite Project
— Inference: Ontologies and OWL
— Linked Data: RDF, HTTP, URIs as
terms
7/30/15
27
29. Ontology Spectrum
Reuse of terminological resources for efficient ontological
engineering in Life Sciences
by Jimeno-Yepes, Antonio; Jiménez-Ruiz, Ernesto; Berlanga-Llavori,
Rafael; Rebholz-Schuhmann, Dietrich
Journal: BMC Bioinformatics Vol. 10 Issue Suppl 10
DOI: 10.1186/1471-2105-10-S10-S4
http://www.mkbergman.com/wp-content/themes/ai3v2/
images/2007Posts/070501d_SemanticSpectrum.png
Existing formalisms
Strong
Semantics
Weak
Semantics
7/30/15
29
30. Application vs. Reference
Ontology
Reference Ontology
— Intended as an authoritative source
— True to the limits of what is known (this changes!)
— Used by others
— Application Ontology
— Built to support a particular application (use case)
— Reused rather than define terms
— Skeleton structure to support application
— Terms defined refine or create new concepts directly or
through new classes based on inference
http://www.nlm.nih.gov/research/umls/presentations/2004-medinfo_tut.pdf
7/30/15
30
31. Healthcare and Life Science
Goal: a suite of orthogonal interoperable reference ontologies
Barry Smith U Buffalo, NCBO
From: Nat Biotechnol. 2007 November; 25(11): 1251.
doi: 10.1038/nbt1346
The Open Biological and Biomedical Ontologies
http://www.obofoundry.org
7/30/15
31
32. How?
Technologies Needed to enable Health Web Science and the
vision for 21st Century Medicine
It’s all about the meaning!
— Semantic Enabling: Web Observatories
— Semantic Interoperability:
— Shared Meaning: Yosemite Project
— Inference: Ontologies and OWL
— Linked Data: RDF, HTTP, URIs as
terms
7/30/15
32
33. The Open Biological and Biomedical
Ontologies
From: Nat Biotechnol. 2007 November; 25(11): 1251. doi: 10.1038/nbt1346
http://www.obofoundry.org
7/30/15
33
34. Translational Medicine
Ontology
Overview of selected types, subtypes
(overlap) and existential restrictions
(arrows) in the Translational Medicine
Ontology.
7/30/15
34The Translational Medicine Ontology and Knowledge Base: driving personalized medicine by bridging the gap between bench and bedside
Luciano et al. Journal of Biomedical Semantics 2011, 2(Suppl 2):S1 http://www.jbiomedsem.com/content/2/S2/S1
Bridge the Gap Between “Bench and Bedside”
35. Translational Medicine
Knowledge BaseTranslational
Medicine Ontology
with mappings to
ontologies and
terminologies listed
in the NCBO
BioPortal.
The TMO provides a
global schema for
Indivo-based
electronic health
records (EHRs) and
can be used with
formalized criteria
for Alzheimer’s
Disease. The TMO
maps types from
Linking Open Data
sources.
7/30/15
35
36. Individuals, Not Populations
36
Photo: http://www.flickr.com/photos/sepblog/4014143391/
http://safety-code.org/
Quickly retrieve
pharmacogenomic
markers of
patients when
needed
No central storage
of data is
necessary, giving
patients full
control over their
personal health
information.
7/30/15
39. Conclusion
Creating Preferable Health Outcomes through Health
Web Science
— Web Science
— Health Web Observatories as web tools
— Semantic Technologies
— Standards and Interoperability
Web Observatories are
VERY EARLY STAGE in HEALTH
— Health Web Sciences Needs your help!
7/30/15
39
https://www.baby-connect.com/images/baby2.gif
https://encrypted-tbn3.gstatic.com/images?q=tbn:ANd9GcTFXOU0CsGM8pddeiadAbtTirgIv-
_3KeaL_fhKIYYFAMPEOTy3
41. What is UMLS?
The UMLS, or Unified Medical Language System
Enables Interoperability between computer systems
— Files
— Software
that brings together many health and biomedical
— vocabularies and standards
You can use the UMLS to enhance or develop
applications, such as electronic health records,
classification tools, dictionaries and language
translators.
http://www.nlm.nih.gov/research/umls/presentations/2004-medinfo_tut.pdf
http://www.nlm.nih.gov/research/umls/quickstart.html
7/30/15
41
42. Unified Medical Language System
Access to the UMLS
The UMLS Terminology Services (UTS) provides three ways to
access the UMLS:
— Web Browsers You can search the data through UTS
applications:
— Metathesaurus Browser - Retrieve UMLS concept information,
including CUIs, semantic types, and synonymous terms.
— Semantic Network Browser - View the names, definitions, and
hierarchical structure of the Semantic Network.
— Local Installation download, customize and load into your
database system, or browse your data using the
MetamorphoSys RRF browser.
— Web Services APIs You can use NLM’s application
programming interfaces (APIs) to query the UMLS data within
your own application.
7/30/15
42
43. Unified Medical Language System
License Required
— Request a license (FREE)
— Sign up for a UMLS Terminology Services (UTS)
account.
— UMLS licenses are issued only to individuals
— NLM is a member of the
IHTSDO (owner of SNOMED CT), and there is no charge
for SNOMED CT use in the United States and other
member countries. Some uses of the UMLS may require
additional agreements with individual terminology
vendors.
The UTS account allows you to browse, download, and
query the UMLS.
7/30/15
43
44. Unified Medical Language System
Use UMLS to link health information, medical terms, drug
names, and billing codes across different computer systems.
Some examples:
— Linking terms and codes between doctor, pharmacy, and
insurance company
— Patient care coordination among several departments within a
hospital
— SNOMED, ICD-9, LOINC, RxNorm – clinical setting, more
about this later in the next part of the tutorial
The UMLS has many other uses, including search engine
retrieval, data mining, public health statistics reporting, and
terminology research.
http://www.nlm.nih.gov/research/umls/presentations/2004-medinfo_tut.pdf
7/30/15
44
45. Overview
Introduction (10 minutes)
1. Background
1. BioMed Domain – Health care and Life Science
2. Reference and Application
3. Ontology Granularity and Layout
2. Examples: (40 minutes)
1. Reference Ontology Examples
1. UMLS – High level across biomedicine (5)
2. BioPAX – Mid level – biological pathways (10)
3. Gene Ontology (“GO”) – Gene annotation (5)
2. Application Ontology Examples
1. Influenza Ontology (5)
2. Best Practices (10)
3. Conclusion (5 minutes)
1. Process: Start with Use Case, develop prototype, Evaluation
2. Standards: BioMedical Ontology Best practices (BioPortal, BFO, SIO)
3. Conferences
7/30/15
45
49. 49
Metabolic PathwaysBioPAX
Level 1
Biological Pathways of the Cell
BioPAX
A series of chemical reactions, catalyzed by enzymes
The products of one are the reactants of the next
e.g. Conversion, Transport 7/30/15
50. 50
BioPAX
Level 2
BioPAX
Biological Pathways of the Cell
Cells are complex systems whose physiology is governed by an
intricate network of Molecular Interactions (MIs) of which a relevant
subset are protein–protein interactions (PPIs).
Molecular Interaction Networks
http://www.estradalab.org/research/
7/30/15
51. 51
BioPAX
Biological Pathways of the Cell
Molecular Interaction Networks
http://www.estradalab.org/research/
Human Protein Interaction Network (PIN)
7/30/15
BioPAX
Level 2
52. Biological Pathways of the Cell
Adapted from Cell Signalling Biology - Michael J. Berridge - www.cellsignallingbiology.org - 2012
and http://www.hartnell.edu/tutorials/biology/signaltransduction.html
52
Signaling
Pathways
BioPAX
Level 3
BioPAX
Signaling
molecules
trigger
cellular
responses.
Molecules
bind to
the
cell surface
causing
a cascade
of activation
Reactions
A activates B activates C….
7/30/15
53. 53
Gene
Regulation
BioPAX
Biological Pathways of the Cell
The modulation of any of the stages of gene
expression that control:
which genes are switched on and off
when, how long, and how much
Gene regulation may occur many
stages:
Transcription
Post-transcriptional modification
RNA transport
Translation
mRNA degradation
Post-translational modifications
among many others (more recently discovered!)
http://www.biology-online.org/dictionary/Gene_regulation
http://en.wikipedia.org/wiki/Regulation_of_gene_expression
7/30/15
57. Before BioPAX With BioPAX
Common “computable semantic” enables scientific
discovery
>200 DBs and tools
Database
Application
User
BioPAX - Simplify
7/30/15
57
59. The Open Biological and Biomedical
Ontologies
From: Nat Biotechnol. 2007 November; 25(11): 1251. doi: 10.1038/nbt1346
http://www.obofoundry.org
7/30/15
59
60. Gene Ontology (GO)
Standard
representations:
— Gene and
gene product
attributes
— Across
species and
databases
7/30/15
60
[1] Rhee, S.Y, Wood, V., Dolinski, K. and Draghici, S. 2008. Use and misuse of the gene ontology
annotations. Nature Reviews Genetics 9:509-515.
[2] http://people.oregonstate.edu/~knausb/rna_seq/annot.pdf
Structured controlled vocabularies
organized as 3 independent Ontologies
— Molecular Interactions
— Biological Processes
— Cellular Location
61. Gene Ontology
Two Key Uses:
— Resource: to look up genes with
similar functionality or location
within the cell to help characterize
the function of a sequence or
structure
— Use to annotate genomes to
enable the analysis of the genome
through the annotation terms.
7/30/15
61
62. Gene Ontology
Evidence Codes
Adapted from: http://people.oregonstate.edu/~knausb/rna_seq/annot.pdf
Rhee, S.Y, Wood, V., Dolinski, K. and Draghici, S. 2008. Use and misuse of the gene ontology annotations. Nature Reviews Genetics
9:509-515. See also: http://www.geneontology.org/GO.evidence.shtml
Manually-assigned
evidence codes fall
into
Four categories:
Experimental
Computational
analysis
Author
statements,
Curatorial
statements
7/30/15
62
Inferred from Electronic Annotation (IEA) is not assigned by a curator.
63. Sequence Ontology
Sequence Ontology (SO) ‘terms and relationships
used to describe the features and attributes of
biological sequence.’ (E.g., binding_site, exon, etc.)
SO http://www.sequenceontology.org/
sequence_attribute
feature_attribute
polymer_attribute
sequence_location
variant_quality
sequence_feature
junction
region
sequence_alteration
sequence_variant
functional_variant
structural_variant
Relationship (lots!)
7/30/15
63
(snuck this one in as another example)
64. Overview
Introduction (10 minutes)
1. Background
1. BioMed Domain – Health care and Life Science
2. Reference and Application
3. Ontology Granularity and Layout
2. Examples: (40 minutes)
1. Reference Ontology Examples
1. UMLS – High level across biomedicine (5)
2. BioPAX – Mid level – biological pathways (10)
3. Gene Ontology (“GO”) – Gene annotation (5)
2. Application Ontology Examples
1. Influenza Ontology (5)
2. Best Practices (10)
3. Conclusion (5 minutes)
1. Process: Start with Use Case, develop prototype, Evaluation
2. Standards: BioMedical Ontology Best practices (BioPortal, BFO, SIO)
3. Conferences
7/30/15
64
66. Application vs. Reference
Ontology
Reference Ontology
— Intended as an authorative source
— True to the limits of what is known
— Used by others
— Application Ontology
— Built to support a particular application (use case)
— Reused rather than define terms
— Skeleton structure to support application
— Terms defined refine or create new concepts directly or
through new classes based on inference
http://www.nlm.nih.gov/research/umls/presentations/2004-medinfo_tut.pdf
7/30/15
66
71. Overview
Introduction (10 minutes)
1. Background
1. BioMed Domain – Health care and Life Science
2. Reference and Application
3. Ontology Granularity and Layout
2. Examples: (40 minutes)
1. Reference Ontology Examples
1. UMLS – High level across biomedicine (5)
2. BioPAX – Mid level – biological pathways (10)
3. Gene Ontology (“GO”) – Gene annotation (5)
2. Application Ontology Examples
1. Influenza Ontology (5)
2. Best Practices (10)
3. Conclusion (5 minutes)
1. Process: Start with Use Case, develop prototype, Evaluation
2. Standards: BioMedical Ontology Best practices (BioPortal, BFO, SIO)
3. Conferences
7/30/15
71
72. Best Practices
Semantic Web Methodology & Technology Development Process
Fox, Peter & McGuinness, Deborah 2008
http://tw.rpi.edu/web/doc/TWC_SemanticWebMethodology 7/30/15
72
73. Generalized Ontology Evaluation
Framework (GOEF)
73
Two stages:
1. Recast use case into its components:
Three Levels of Evaluation
2. Evaluate components using objective metrics
74. BioPortal
http://bioportal.bioontology.org/
Provides access to commonly used biomedical ontologies and to tools for
working with them. BioPortal allows you to
— Browse
— the library of ontologies
— mappings between terms in different ontologies
— a selection of projects that use BioPortal resources
— Search
— biomedical resources for a term
— for a term across multiple ontologies
— Receive recommendations
— on which ontologies are most relevant for a corpus
— Annotate text
— with terms from ontologies
All information available through the BioPortal Web site is also available
through the NCBO Web service REST API. Please see REST API
documentation for more information.
http://www.bioontology.org/wiki/index.php/NCBO_REST_services
7/30/15
74
76. Conclusion
Tutorial sources
— BioPortal
— W3C HCLSIG
Consortia to join
— W3C HCLSIG
— OpenPHACTS
— Identifiers.org
— Pistoia Alliance
— BioPAX (check for new name)
7/30/15
76
77. THANK YOU!
RPI Tetherless World Constellation
RPI Web Science Research Center
Predictive Medicine, Inc.
W3C Health Care & Life Science SIG
BioPathways Consortium
BioPAX
Harvard Medical School, Mass General Hospital
Abha Moitra, Petr Haug, Larry Hunter, Bob Powers, Scott
Marshall, Matthias Samwald, Michel Dumontier, Ted Slater,
Eric Neumann, Lynette Hirschman, Lynn Schriml,
Rick Lathrop and many many others!
NSF, NIH, NIST, IEEE and many others!
7/30/15
77
80. Personalized Medicine
Components
• Understand disease heterogeneity
— Comprehend disease progression
• Determine genetic and environmental contributors
— Create treatments against relevant targets
— drugs against relevant targets (molecular structures)
— Yoga against stress
— Exercise against obesity
— Elimination against food intolerance or allergy
• Develop markers to predict response
• Identify concrete endpoints to measure response
7/30/15
80
81. Scope
Ontology Uses
— Knowledge Management
— Annotate data (such as genomes)
— Access information (search, find, and access)
— Map across ontologies relate
— Data integration and exchange
— Model dynamic cellular processes
— Identify Drug Interactions
— Decision support
— SafetyCodes
— Diabetic Care
— Lab Alerts
(Bodenreider YBMI 2008)
http://themindwobbles.wordpress.com/2009/05/04/olivier-bodenreider-nlm-
best-practices-pitfalls-and-positives-cbo-2009/ 7/30/15
81
82. Unified Medical Language System
Metathesaurus
NLM uses the Semantic Network and Lexical Tools to
produce the Metathesaurus.
Metathesaurus production involves:
— Processing the terms and codes using the Lexical Tools
— Grouping synonymous terms into concepts
— Categorizing concepts by semantic types from the
Semantic Network
— Incorporating relationships and attributes provided by
vocabularies
— Releasing the data in a common format
They can be accessed separately or in any combination
according to your needs.
7/30/15
82