SlideShare ist ein Scribd-Unternehmen logo
1 von 40
Downloaden Sie, um offline zu lesen
Personalized Health Knowledge Graph1
Ohio Center of Excellence in Knowledge-Enabled Computing
Amelie Gyrard, Manas Gaur,
Krishnaprasad Thirunarayan, Amit Sheth
Kno.e.sis Research Center
Department of Computer Science and Engineering,
Wright State University, Dayton, Ohio (USA)
Saeedeh Shekarpour
University of Dayton, Ohio
Problem
• World Health Organization (WHO) estimates that the number of
people suffering from asthma, obesity and Parkinson’s disease are
respectively 235 million, 650 million, 4-6 million.
=> Need of “Personalized Preventive Coach Applications”
to support physicians in understanding asthma symptoms
2
Introduction
DIKW pyramid: Data >
Information > Knowledge >
Wisdom/Actionable Insight
3Sheth, A., Anantharam, P., Henson, C.: Physical-cyber-social computing: An early 21st century approach. IEEE Intelligent
Systems (2013), Slides: Semantic Web: introduction & overview [Sheth 2012]
Agenda
• The needs of Digital Health application
̶ Reasoner to derive meaningful information from health and IoT datasets
̶ Contextualization & Personalization
• Limitations of the Related Work
• Research Challenges
• kHealth Project
̶ Use case for Asthma, Obesity and Parkinson diseases
• Our solution: Personalized Healthcare Knowledge Graph
̶ Architecture
̶ Rule-based inference engine
̶ KAO ontology: Integration of knowledge from Ontology Catalogs
• Conclusion and Future Work
4
Definitions
• Context-Awareness refers to the use of external
data that can impact the user's situation.
̶ E.g., for Asthma: air pollution, pollen level
• Personalization adjusts the treatment to each
patient's condition.
̶ E.g., for Asthma patient: patient is allergic to a specific
type of pollen
5
Literature Survey: Limitations
6
Authors Publication
date
Topic KG ML Health KG
Paulheim et al. 2016 Survey KG Yes No No
Guha et al.
Schema.org
2016 KG Yes No No
Shi et al. 2017 Health KG Yes Yes Yes
Yu et al. 2017 KG TCM
Visualization
Yes No Yes
Ruan et al. 2017 KG TCM Yes No Yes
Weng et al. 2017 KG TCM Yes No Yes
Nickel al. 2016 KG + ML Yes Yes No
Wilcke et al. 2017 KG + ML Yes Yes No
Rotmensch et al. 2017 Health KG + EMR Yes Yes Yes
Dong et al. 2014 Knowledge Vault - Google KG Yes No No
No personalization
No IoT datasets exploited to
understand the surrounding
environment of the patient
KHealth Asthma:
kit + cloud-based analysis + visual analytics dashboard
7Source: Augmented Personalized Health - URL (slide 21)
Data Sources
Heterogeneous data and
collection method
Smart Data
Actionable meaningful information
from the data collected
Active and
passive sensing
KHealth Dataset
•
8Source: Augmented Personalized Health - 23 parameters - URL (slide 25)
Research Challenges (RC)
• (RC1) How to model a knowledge graph for healthcare and
chronic disease management?
• (RC2) How to model personalization and context-awareness to represent
patient's symptoms and derive actionable insights?
• (RC3) How to analyze datasets generated by IoT devices to deduce
information that is actionable?
• (RC4) How to promote reproduceable experiments from previous projects
(e.g., datasets, data models, and reasoning mechanisms)?
• (RC5) How to customize and instantiate relevant knowledge from existing
publicly available health knowledge bases to obtain insights from
health-related social media text?
9
RC
RC 1
RC 2
RC 3
RC 4
RC 5
Our Solution: Personalized Healthcare Knowledge Graph
Personalized Healthcare Knowledge Graph (PHKG) is a
solution which explicitly describes and integrates both
medical knowledge and personal health data, and can serve
as a foundation for (deductive and abductive) reasoning.
10
PHKG Architecture
•
11
Reusing domain knowledge from Ontology Catalogs
• BioPortal for biomedical ontologies [1]
• Linked Open Vocabularies (LOV) [2]
• Linked Open Vocabularies for Internet of Things (LOV4IoT) [3]
[1] https://bioportal.bioontology.org/, [2] https://lov.linkeddata.es/dataset/lov/, [3] http://lov4iot.appspot.com/
RC 1, 2, 4
Symptom Ontology
http://bioportal.bioontology.org/ontologies/SYMP/
SNOMED-CT
• Knowledge is already
encoded!
• Example: Cough and
Pollen concepts have rich
taxonomies
Pollen: http://purl.bioontology.org/ontology/SNOMEDCT/256259004
Cough: http://purl.bioontology.org/ontology/SNOMEDCT/49727002
Kno.e.sis Alchemy API
•
15
RC 2, 5
http://wiki.knoesis.org/index.php/Knoesis_Alchemy_of_Healthcare
KAO Ontology
• KAO: KHealth Asthma Ontology [1]
• Integration of several ontologies relevant to interpret kHealth datasets
̶ W3C SOSA/SSN
̶ Asthma from BioPortal
̶ Weather and smart home ontologies [Staroch 2013] [Kofler et al. 2011]
• More and more ontologies to integrate:
̶ SNOMED-CT from BioPortal (e.g., Cough, Pollen concepts)
̶ Symptoms Ontology
̶ Etc.
[1] http://wiki.knoesis.org/index.php/KHealthAsthmaOntology
KAO Ontology Evaluation
• How to evaluate an ontology?
̶ So many tools to evaluate ontologies
̶ PerfectO [1] a platform to assist ontology developers in evaluating and improving
ontologies
• Set of ontology best practices executed with kao [2]
[1] http://perfectsemanticweb.appspot.com/?p=ontologyValidation
[2] http://wiki.knoesis.org/index.php/KHealthAsthmaOntology
KAO Ontology Quality with PerfectO
•
http://perfectsemanticweb.appspot.com/documentation/SemanticWebBestPracticesForDummies.pdf
http://wiki.knoesis.org/index.php/KHealthAsthmaOntology
KAO Ontology Quality with PerfectO
•
http://perfectsemanticweb.appspot.com/documentation/SemanticWebBestPracticesForDummies.pdf
http://wiki.knoesis.org/index.php/KHealthAsthmaOntology
KAO Ontology Quality with PerfectO
•
http://perfectsemanticweb.appspot.com/documentation/SemanticWebBestPracticesForDummies.pdf
http://wiki.knoesis.org/index.php/KHealthAsthmaOntology
KAO Ontology Quality with PerfectO
•
http://perfectsemanticweb.appspot.com/documentation/SemanticWebBestPracticesForDummies.pdf
http://wiki.knoesis.org/index.php/KHealthAsthmaOntology
KAO Ontology Quality with PerfectO
•
http://perfectsemanticweb.appspot.com/documentation/SemanticWebBestPracticesForDummies.pdf
http://wiki.knoesis.org/index.php/KHealthAsthmaOntology
KHealth Reasoner
23
Raw
kHealth
Dataset
kHealth
Reasoner
kHealth ontologies
Semantic Dataset
(RDF Triple Store)
Example:
pollen=11
rdf:type AO:Pollen
rdf:type kao:HighPollenLevel
3) Update the triple store
with more contextually
relevant triples
2) Executing the
reasoner1) Semantic
Annotation
Example:
Asthma dataset
pollen=11
Example: knoesis Asthma Ontology (kAO)
Example:
rdf:type kao:HighPollenLevel
RC 2, 3
KHealth Reasoner
24
RC 2, 3
Rule Example for Air Quality
25
• Rule implementation compliant with:
̶ Jena inference engine
̶ Ontologies: kao, W3C SOSA/SSN, etc
• Code example:
<= Usage of W3C SOSA/SSN ontology
<= Usage of kao ontology
Rule Example for Pollen Level
26
=>Change the thresholds with other parameters to
achieve the personalization
Rule Example for Heart Beat
27
=>?measurement = heart beat patient data
Personalization
Demo: Health Reasoner
28
=> 6 scenarios supported by the health reasoner (pollen
data, air quality, outside humidity, heart beat, room
temperature and peak expiratory flow).
http://linkedopenreasoning.appspot.com/
Demo: Health Reasoner
29
=> Enriched information
=> Automatic
Semantic
Annotation
http://linkedopenreasoning.appspot.com/
Completeness and Correctness of the KG
30
http://sensormeasurement.appspot.com/documentation/NomenclatureSensorData.pdf
● Correctness means that are no incompatibility with other rules
● Completeness means that all sensor values are covered by an high level
information
Overall Challenge Research Impact
31
Knowledge
Extraction
Internet of
Things
Natural
Language
Processing
Web of
Things
Medical
Text
Analysis
Semantic
Web
Knowledge
Graphs
Conclusion & Future Work
● Context-specific and personalized knowledge
● Reasoning mechanisms to deduce high-level abstractions from data
and replace domain experts
● Challenge of integrating heterogeneous data from:
○ Healthcare, IoT data, Web of Data
• Future work:
̶ More disease use cases (e.g., asthma, obesity, Parkinson)
̶ Dynamic PKG (continuous evolution based on incoming streams of
observations)
32
Acknowledgments
● This work is partially funded by:
○ Hazards SEES NSF Award EAR 1520870
○ KHealth NIH 1 R01 HD087132-01.
● Thanks to the kHealth team for fruitful discussions and feedback.
● The opinions expressed are those of the authors and do not reflect those
of the sponsors.
33
Questions
34
Personalized Health Knowledge Graph
Ohio Center of Excellence in Knowledge-Enabled Computing
Amelie Gyrard, Manas Gaur,
Krishnaprasad Thirunarayan, Amit Sheth
Kno.e.sis Research Center
Department of Computer Science and Engineering,
Wright State University, Dayton, Ohio (USA)
Saeedeh Shekarpour
University of Dayton, Ohio
Annexe: Modeling the Patient
36
● Modeling the Person/Patient
● Body Mass Index Scenario: weight, height, age
● Challenges:
○ Property vs. class
○ Incomplete information
Annexe: Modeling the Weight - BioPortal
37
• Results from BioPortal when looking
for weight property
Annexe: Modeling the Weight - LOV
38
• Query the LOV ontology catalog to find a weight property to describe
the patient, sometimes concepts and not properties, decide among
148 results
Annexe: Modeling the Weight - Schema.org
39
• Schema.org provides the Person concept, and
its properties such as height, weight, but not
the property age that would we need for
computer BMI and since we do not have the
birthdate for privacy reasons.
• https://schema.org/weight
Annexe: Modeling the Weight - DBpedia
40
• Weight description from DBpedia, notice that
range must be in kilogram
• http://dbpedia.org/ontology/Person/weight

Weitere ähnliche Inhalte

Was ist angesagt?

The Roots: Linked data and the foundations of successful Agriculture Data
The Roots: Linked data and the foundations of successful Agriculture DataThe Roots: Linked data and the foundations of successful Agriculture Data
The Roots: Linked data and the foundations of successful Agriculture DataPaul Groth
 
Combining Explicit and Latent Web Semantics for Maintaining Knowledge Graphs
Combining Explicit and Latent Web Semantics for Maintaining Knowledge GraphsCombining Explicit and Latent Web Semantics for Maintaining Knowledge Graphs
Combining Explicit and Latent Web Semantics for Maintaining Knowledge GraphsPaul Groth
 
Elsevier’s Healthcare Knowledge Graph
Elsevier’s Healthcare Knowledge GraphElsevier’s Healthcare Knowledge Graph
Elsevier’s Healthcare Knowledge GraphPaul Groth
 
Introduction to data science
Introduction to data scienceIntroduction to data science
Introduction to data scienceSampath Kumar
 
Research Data Management for Econometrics
Research Data Management for EconometricsResearch Data Management for Econometrics
Research Data Management for EconometricsPeter Löwe
 
Pistoia Alliance Demystifying AI & ML part 2
Pistoia Alliance Demystifying AI & ML part 2Pistoia Alliance Demystifying AI & ML part 2
Pistoia Alliance Demystifying AI & ML part 2Pistoia Alliance
 
Knowledge graph construction for research & medicine
Knowledge graph construction for research & medicineKnowledge graph construction for research & medicine
Knowledge graph construction for research & medicinePaul Groth
 
Citrination-MRS Fall Meeting 2015
Citrination-MRS Fall Meeting 2015Citrination-MRS Fall Meeting 2015
Citrination-MRS Fall Meeting 2015bmeredig
 
Introduction to Data Science
Introduction to Data ScienceIntroduction to Data Science
Introduction to Data ScienceANOOP V S
 
Machines are people too
Machines are people tooMachines are people too
Machines are people tooPaul Groth
 
Introduction to Data Science and Large-scale Machine Learning
Introduction to Data Science and Large-scale Machine LearningIntroduction to Data Science and Large-scale Machine Learning
Introduction to Data Science and Large-scale Machine LearningNik Spirin
 
Myths about data science and big data analytics
Myths about data science and big data analyticsMyths about data science and big data analytics
Myths about data science and big data analyticsChulalongkorn University
 
Hattrick-Simpers MRS Webinar on AI in Materials
Hattrick-Simpers MRS Webinar on AI in MaterialsHattrick-Simpers MRS Webinar on AI in Materials
Hattrick-Simpers MRS Webinar on AI in MaterialsJason Hattrick-Simpers
 
Data science presentation
Data science presentationData science presentation
Data science presentationMSDEVMTL
 
Materials Data in the 21st Century: From Mishmash to Moneyball
Materials Data in the 21st Century: From Mishmash to MoneyballMaterials Data in the 21st Century: From Mishmash to Moneyball
Materials Data in the 21st Century: From Mishmash to Moneyballbmeredig
 
MMDS 2014: Myria (and Scalable Graph Clustering with RelaxMap)
MMDS 2014: Myria (and Scalable Graph Clustering with RelaxMap)MMDS 2014: Myria (and Scalable Graph Clustering with RelaxMap)
MMDS 2014: Myria (and Scalable Graph Clustering with RelaxMap)University of Washington
 

Was ist angesagt? (20)

The Roots: Linked data and the foundations of successful Agriculture Data
The Roots: Linked data and the foundations of successful Agriculture DataThe Roots: Linked data and the foundations of successful Agriculture Data
The Roots: Linked data and the foundations of successful Agriculture Data
 
Combining Explicit and Latent Web Semantics for Maintaining Knowledge Graphs
Combining Explicit and Latent Web Semantics for Maintaining Knowledge GraphsCombining Explicit and Latent Web Semantics for Maintaining Knowledge Graphs
Combining Explicit and Latent Web Semantics for Maintaining Knowledge Graphs
 
Elsevier’s Healthcare Knowledge Graph
Elsevier’s Healthcare Knowledge GraphElsevier’s Healthcare Knowledge Graph
Elsevier’s Healthcare Knowledge Graph
 
Introduction to data science
Introduction to data scienceIntroduction to data science
Introduction to data science
 
Research Data Management for Econometrics
Research Data Management for EconometricsResearch Data Management for Econometrics
Research Data Management for Econometrics
 
Pistoia Alliance Demystifying AI & ML part 2
Pistoia Alliance Demystifying AI & ML part 2Pistoia Alliance Demystifying AI & ML part 2
Pistoia Alliance Demystifying AI & ML part 2
 
Knowledge graph construction for research & medicine
Knowledge graph construction for research & medicineKnowledge graph construction for research & medicine
Knowledge graph construction for research & medicine
 
Citrination-MRS Fall Meeting 2015
Citrination-MRS Fall Meeting 2015Citrination-MRS Fall Meeting 2015
Citrination-MRS Fall Meeting 2015
 
Introduction to Data Science
Introduction to Data ScienceIntroduction to Data Science
Introduction to Data Science
 
Machines are people too
Machines are people tooMachines are people too
Machines are people too
 
Introduction to Data Science and Large-scale Machine Learning
Introduction to Data Science and Large-scale Machine LearningIntroduction to Data Science and Large-scale Machine Learning
Introduction to Data Science and Large-scale Machine Learning
 
Myths about data science and big data analytics
Myths about data science and big data analyticsMyths about data science and big data analytics
Myths about data science and big data analytics
 
Hattrick-Simpers MRS Webinar on AI in Materials
Hattrick-Simpers MRS Webinar on AI in MaterialsHattrick-Simpers MRS Webinar on AI in Materials
Hattrick-Simpers MRS Webinar on AI in Materials
 
Data science presentation
Data science presentationData science presentation
Data science presentation
 
Materials Data in the 21st Century: From Mishmash to Moneyball
Materials Data in the 21st Century: From Mishmash to MoneyballMaterials Data in the 21st Century: From Mishmash to Moneyball
Materials Data in the 21st Century: From Mishmash to Moneyball
 
Enabling simultaneous analysis of multiple cohort studies: A BRISSKit use case
Enabling simultaneous analysis of multiple cohort studies: A BRISSKit use caseEnabling simultaneous analysis of multiple cohort studies: A BRISSKit use case
Enabling simultaneous analysis of multiple cohort studies: A BRISSKit use case
 
Introduction to Data Science by Datalent Team @Data Science Clinic #9
Introduction to Data Science by Datalent Team @Data Science Clinic #9Introduction to Data Science by Datalent Team @Data Science Clinic #9
Introduction to Data Science by Datalent Team @Data Science Clinic #9
 
Big data road map
Big data road mapBig data road map
Big data road map
 
Unit 3 part 2
Unit  3 part 2Unit  3 part 2
Unit 3 part 2
 
MMDS 2014: Myria (and Scalable Graph Clustering with RelaxMap)
MMDS 2014: Myria (and Scalable Graph Clustering with RelaxMap)MMDS 2014: Myria (and Scalable Graph Clustering with RelaxMap)
MMDS 2014: Myria (and Scalable Graph Clustering with RelaxMap)
 

Ähnlich wie Personalized health knowledge graph ckg workshop - iswc 2018 (2)

Delivering on the promise of data-driven healthcare: trade-offs, challenges, ...
Delivering on the promise of data-driven healthcare: trade-offs, challenges, ...Delivering on the promise of data-driven healthcare: trade-offs, challenges, ...
Delivering on the promise of data-driven healthcare: trade-offs, challenges, ...Paolo Missier
 
Aleksandar Zivaljevic - Annotation of clinical datasets using openEHR Archety...
Aleksandar Zivaljevic - Annotation of clinical datasets using openEHR Archety...Aleksandar Zivaljevic - Annotation of clinical datasets using openEHR Archety...
Aleksandar Zivaljevic - Annotation of clinical datasets using openEHR Archety...Health Informatics New Zealand
 
Role of AI in Transforming the Healthcare Industry
Role of AI in Transforming the Healthcare IndustryRole of AI in Transforming the Healthcare Industry
Role of AI in Transforming the Healthcare IndustryHammadAfzal23
 
Augmented Personalized Health: using AI techniques on semantically integrated...
Augmented Personalized Health: using AI techniques on semantically integrated...Augmented Personalized Health: using AI techniques on semantically integrated...
Augmented Personalized Health: using AI techniques on semantically integrated...Amit Sheth
 
The Future: Overcoming the Barriers to Using NHS Clinical Data For Research P...
The Future: Overcoming the Barriers to Using NHS Clinical Data For Research P...The Future: Overcoming the Barriers to Using NHS Clinical Data For Research P...
The Future: Overcoming the Barriers to Using NHS Clinical Data For Research P...Mark Hawker
 
Sun==big data analytics for health care
Sun==big data analytics for health careSun==big data analytics for health care
Sun==big data analytics for health careAravindharamanan S
 
TRANSFORMING BIG DATA INTO SMART DATA: Deriving Value via Harnessing Volume, ...
TRANSFORMING BIG DATA INTO SMART DATA: Deriving Value via Harnessing Volume, ...TRANSFORMING BIG DATA INTO SMART DATA: Deriving Value via Harnessing Volume, ...
TRANSFORMING BIG DATA INTO SMART DATA: Deriving Value via Harnessing Volume, ...Amit Sheth
 
Final APEC ERW 25 Aug 2022.pdf
Final APEC ERW 25 Aug 2022.pdfFinal APEC ERW 25 Aug 2022.pdf
Final APEC ERW 25 Aug 2022.pdfpantapong
 
Utility and Added Value of Classifications in Health Information Systems
Utility and Added Value of Classifications in Health Information SystemsUtility and Added Value of Classifications in Health Information Systems
Utility and Added Value of Classifications in Health Information SystemsBedirhan Ustun
 
NHS SE presentation
NHS SE presentationNHS SE presentation
NHS SE presentationJisc
 
The Learning Health System: Thinking and Acting Across Scales
The Learning Health System: Thinking and Acting Across ScalesThe Learning Health System: Thinking and Acting Across Scales
The Learning Health System: Thinking and Acting Across ScalesPhilip Payne
 
What's up at Kno.e.sis?
What's up at Kno.e.sis? What's up at Kno.e.sis?
What's up at Kno.e.sis? Amit Sheth
 
DCHI webinar on N3C January 2021
DCHI webinar on N3C January 2021DCHI webinar on N3C January 2021
DCHI webinar on N3C January 2021Warren Kibbe
 
Data_Science_Applications_&_Use_Cases.pdf
Data_Science_Applications_&_Use_Cases.pdfData_Science_Applications_&_Use_Cases.pdf
Data_Science_Applications_&_Use_Cases.pdfvishal choudhary
 
Standards in health informatics - Problem, clinical models and terminologies
Standards in health informatics - Problem, clinical models and terminologiesStandards in health informatics - Problem, clinical models and terminologies
Standards in health informatics - Problem, clinical models and terminologiesSilje Ljosland Bakke
 

Ähnlich wie Personalized health knowledge graph ckg workshop - iswc 2018 (2) (20)

Cri big data
Cri big dataCri big data
Cri big data
 
Delivering on the promise of data-driven healthcare: trade-offs, challenges, ...
Delivering on the promise of data-driven healthcare: trade-offs, challenges, ...Delivering on the promise of data-driven healthcare: trade-offs, challenges, ...
Delivering on the promise of data-driven healthcare: trade-offs, challenges, ...
 
Aleksandar Zivaljevic - Annotation of clinical datasets using openEHR Archety...
Aleksandar Zivaljevic - Annotation of clinical datasets using openEHR Archety...Aleksandar Zivaljevic - Annotation of clinical datasets using openEHR Archety...
Aleksandar Zivaljevic - Annotation of clinical datasets using openEHR Archety...
 
Role of AI in Transforming the Healthcare Industry
Role of AI in Transforming the Healthcare IndustryRole of AI in Transforming the Healthcare Industry
Role of AI in Transforming the Healthcare Industry
 
Augmented Personalized Health: using AI techniques on semantically integrated...
Augmented Personalized Health: using AI techniques on semantically integrated...Augmented Personalized Health: using AI techniques on semantically integrated...
Augmented Personalized Health: using AI techniques on semantically integrated...
 
The Future: Overcoming the Barriers to Using NHS Clinical Data For Research P...
The Future: Overcoming the Barriers to Using NHS Clinical Data For Research P...The Future: Overcoming the Barriers to Using NHS Clinical Data For Research P...
The Future: Overcoming the Barriers to Using NHS Clinical Data For Research P...
 
Sun==big data analytics for health care
Sun==big data analytics for health careSun==big data analytics for health care
Sun==big data analytics for health care
 
Hadoop Enabled Healthcare
Hadoop Enabled HealthcareHadoop Enabled Healthcare
Hadoop Enabled Healthcare
 
TRANSFORMING BIG DATA INTO SMART DATA: Deriving Value via Harnessing Volume, ...
TRANSFORMING BIG DATA INTO SMART DATA: Deriving Value via Harnessing Volume, ...TRANSFORMING BIG DATA INTO SMART DATA: Deriving Value via Harnessing Volume, ...
TRANSFORMING BIG DATA INTO SMART DATA: Deriving Value via Harnessing Volume, ...
 
AI & Healthcare @ AIISC: May 2021 Snapshot
AI & Healthcare @ AIISC: May 2021 SnapshotAI & Healthcare @ AIISC: May 2021 Snapshot
AI & Healthcare @ AIISC: May 2021 Snapshot
 
Final APEC ERW 25 Aug 2022.pdf
Final APEC ERW 25 Aug 2022.pdfFinal APEC ERW 25 Aug 2022.pdf
Final APEC ERW 25 Aug 2022.pdf
 
Utility and Added Value of Classifications in Health Information Systems
Utility and Added Value of Classifications in Health Information SystemsUtility and Added Value of Classifications in Health Information Systems
Utility and Added Value of Classifications in Health Information Systems
 
NHS SE presentation
NHS SE presentationNHS SE presentation
NHS SE presentation
 
The Learning Health System: Thinking and Acting Across Scales
The Learning Health System: Thinking and Acting Across ScalesThe Learning Health System: Thinking and Acting Across Scales
The Learning Health System: Thinking and Acting Across Scales
 
What's up at Kno.e.sis?
What's up at Kno.e.sis? What's up at Kno.e.sis?
What's up at Kno.e.sis?
 
DCHI webinar on N3C January 2021
DCHI webinar on N3C January 2021DCHI webinar on N3C January 2021
DCHI webinar on N3C January 2021
 
Data_Science_Applications_&_Use_Cases.pdf
Data_Science_Applications_&_Use_Cases.pdfData_Science_Applications_&_Use_Cases.pdf
Data_Science_Applications_&_Use_Cases.pdf
 
Innovative project1
Innovative project1Innovative project1
Innovative project1
 
Standards in health informatics - Problem, clinical models and terminologies
Standards in health informatics - Problem, clinical models and terminologiesStandards in health informatics - Problem, clinical models and terminologies
Standards in health informatics - Problem, clinical models and terminologies
 
NCATS CTSA N3C
NCATS CTSA N3C NCATS CTSA N3C
NCATS CTSA N3C
 

Mehr von Amélie Gyrard

Internet of Robotic Things Ontology catalog, knowledge extraction IEEE P1872....
Internet of Robotic Things Ontology catalog, knowledge extraction IEEE P1872....Internet of Robotic Things Ontology catalog, knowledge extraction IEEE P1872....
Internet of Robotic Things Ontology catalog, knowledge extraction IEEE P1872....Amélie Gyrard
 
Keynote WFIoT2019 - Data Graph, Knowledge Graphs Ontologies, Internet of Thin...
Keynote WFIoT2019 - Data Graph, Knowledge Graphs Ontologies, Internet of Thin...Keynote WFIoT2019 - Data Graph, Knowledge Graphs Ontologies, Internet of Thin...
Keynote WFIoT2019 - Data Graph, Knowledge Graphs Ontologies, Internet of Thin...Amélie Gyrard
 
Defining iot.schema.org: Using Knowledge Extraction from Existing IoT-based ...
Defining iot.schema.org: Using Knowledge Extraction from  Existing IoT-based ...Defining iot.schema.org: Using Knowledge Extraction from  Existing IoT-based ...
Defining iot.schema.org: Using Knowledge Extraction from Existing IoT-based ...Amélie Gyrard
 
Concept extraction from the web of things (3)
Concept extraction from the web of things (3)Concept extraction from the web of things (3)
Concept extraction from the web of things (3)Amélie Gyrard
 
Toward a Semantic Web of Vehicles
Toward a Semantic Web of VehiclesToward a Semantic Web of Vehicles
Toward a Semantic Web of VehiclesAmélie Gyrard
 
FiCloud2016 lov4iot extended
FiCloud2016 lov4iot extended FiCloud2016 lov4iot extended
FiCloud2016 lov4iot extended Amélie Gyrard
 
FiCloud2016 lov4iot second life ontology
FiCloud2016 lov4iot second life ontologyFiCloud2016 lov4iot second life ontology
FiCloud2016 lov4iot second life ontologyAmélie Gyrard
 
Presentation aina2016 seg3.0_methodology_v2
Presentation aina2016 seg3.0_methodology_v2Presentation aina2016 seg3.0_methodology_v2
Presentation aina2016 seg3.0_methodology_v2Amélie Gyrard
 
Assisting IoT Projects and Developers in Designing Interoperable Semantic Web...
Assisting IoT Projects and Developers in Designing Interoperable Semantic Web...Assisting IoT Projects and Developers in Designing Interoperable Semantic Web...
Assisting IoT Projects and Developers in Designing Interoperable Semantic Web...Amélie Gyrard
 
A Unified Semantic Engine for Internet of Things and Smart Cities: From Senso...
A Unified Semantic Engine for Internet of Things and Smart Cities: From Senso...A Unified Semantic Engine for Internet of Things and Smart Cities: From Senso...
A Unified Semantic Engine for Internet of Things and Smart Cities: From Senso...Amélie Gyrard
 
Fi cloudpresentationgyrardaugust2015 v2
Fi cloudpresentationgyrardaugust2015 v2Fi cloudpresentationgyrardaugust2015 v2
Fi cloudpresentationgyrardaugust2015 v2Amélie Gyrard
 
Designing Cross-Domain Semantic Web of Things Applications
Designing Cross-Domain Semantic Web of Things ApplicationsDesigning Cross-Domain Semantic Web of Things Applications
Designing Cross-Domain Semantic Web of Things ApplicationsAmélie Gyrard
 
Gyrard ssn2014 Helping IoT Application Developers with Sensor-based Linked Op...
Gyrard ssn2014 Helping IoT Application Developers with Sensor-based Linked Op...Gyrard ssn2014 Helping IoT Application Developers with Sensor-based Linked Op...
Gyrard ssn2014 Helping IoT Application Developers with Sensor-based Linked Op...Amélie Gyrard
 
An ontology-based approach for helping to secure the ETSI Machine-to-Machine ...
An ontology-based approach for helping to secure the ETSI Machine-to-Machine ...An ontology-based approach for helping to secure the ETSI Machine-to-Machine ...
An ontology-based approach for helping to secure the ETSI Machine-to-Machine ...Amélie Gyrard
 
Enrich Machine-to-Machine Data with Semantic Web Technologies for Cross-Domai...
Enrich Machine-to-Machine Data with Semantic Web Technologies for Cross-Domai...Enrich Machine-to-Machine Data with Semantic Web Technologies for Cross-Domai...
Enrich Machine-to-Machine Data with Semantic Web Technologies for Cross-Domai...Amélie Gyrard
 
An Ontology to Semantically Annotate the Machine-to-Machine (M2M) Device Meas...
An Ontology to Semantically Annotate the Machine-to-Machine (M2M) Device Meas...An Ontology to Semantically Annotate the Machine-to-Machine (M2M) Device Meas...
An Ontology to Semantically Annotate the Machine-to-Machine (M2M) Device Meas...Amélie Gyrard
 

Mehr von Amélie Gyrard (16)

Internet of Robotic Things Ontology catalog, knowledge extraction IEEE P1872....
Internet of Robotic Things Ontology catalog, knowledge extraction IEEE P1872....Internet of Robotic Things Ontology catalog, knowledge extraction IEEE P1872....
Internet of Robotic Things Ontology catalog, knowledge extraction IEEE P1872....
 
Keynote WFIoT2019 - Data Graph, Knowledge Graphs Ontologies, Internet of Thin...
Keynote WFIoT2019 - Data Graph, Knowledge Graphs Ontologies, Internet of Thin...Keynote WFIoT2019 - Data Graph, Knowledge Graphs Ontologies, Internet of Thin...
Keynote WFIoT2019 - Data Graph, Knowledge Graphs Ontologies, Internet of Thin...
 
Defining iot.schema.org: Using Knowledge Extraction from Existing IoT-based ...
Defining iot.schema.org: Using Knowledge Extraction from  Existing IoT-based ...Defining iot.schema.org: Using Knowledge Extraction from  Existing IoT-based ...
Defining iot.schema.org: Using Knowledge Extraction from Existing IoT-based ...
 
Concept extraction from the web of things (3)
Concept extraction from the web of things (3)Concept extraction from the web of things (3)
Concept extraction from the web of things (3)
 
Toward a Semantic Web of Vehicles
Toward a Semantic Web of VehiclesToward a Semantic Web of Vehicles
Toward a Semantic Web of Vehicles
 
FiCloud2016 lov4iot extended
FiCloud2016 lov4iot extended FiCloud2016 lov4iot extended
FiCloud2016 lov4iot extended
 
FiCloud2016 lov4iot second life ontology
FiCloud2016 lov4iot second life ontologyFiCloud2016 lov4iot second life ontology
FiCloud2016 lov4iot second life ontology
 
Presentation aina2016 seg3.0_methodology_v2
Presentation aina2016 seg3.0_methodology_v2Presentation aina2016 seg3.0_methodology_v2
Presentation aina2016 seg3.0_methodology_v2
 
Assisting IoT Projects and Developers in Designing Interoperable Semantic Web...
Assisting IoT Projects and Developers in Designing Interoperable Semantic Web...Assisting IoT Projects and Developers in Designing Interoperable Semantic Web...
Assisting IoT Projects and Developers in Designing Interoperable Semantic Web...
 
A Unified Semantic Engine for Internet of Things and Smart Cities: From Senso...
A Unified Semantic Engine for Internet of Things and Smart Cities: From Senso...A Unified Semantic Engine for Internet of Things and Smart Cities: From Senso...
A Unified Semantic Engine for Internet of Things and Smart Cities: From Senso...
 
Fi cloudpresentationgyrardaugust2015 v2
Fi cloudpresentationgyrardaugust2015 v2Fi cloudpresentationgyrardaugust2015 v2
Fi cloudpresentationgyrardaugust2015 v2
 
Designing Cross-Domain Semantic Web of Things Applications
Designing Cross-Domain Semantic Web of Things ApplicationsDesigning Cross-Domain Semantic Web of Things Applications
Designing Cross-Domain Semantic Web of Things Applications
 
Gyrard ssn2014 Helping IoT Application Developers with Sensor-based Linked Op...
Gyrard ssn2014 Helping IoT Application Developers with Sensor-based Linked Op...Gyrard ssn2014 Helping IoT Application Developers with Sensor-based Linked Op...
Gyrard ssn2014 Helping IoT Application Developers with Sensor-based Linked Op...
 
An ontology-based approach for helping to secure the ETSI Machine-to-Machine ...
An ontology-based approach for helping to secure the ETSI Machine-to-Machine ...An ontology-based approach for helping to secure the ETSI Machine-to-Machine ...
An ontology-based approach for helping to secure the ETSI Machine-to-Machine ...
 
Enrich Machine-to-Machine Data with Semantic Web Technologies for Cross-Domai...
Enrich Machine-to-Machine Data with Semantic Web Technologies for Cross-Domai...Enrich Machine-to-Machine Data with Semantic Web Technologies for Cross-Domai...
Enrich Machine-to-Machine Data with Semantic Web Technologies for Cross-Domai...
 
An Ontology to Semantically Annotate the Machine-to-Machine (M2M) Device Meas...
An Ontology to Semantically Annotate the Machine-to-Machine (M2M) Device Meas...An Ontology to Semantically Annotate the Machine-to-Machine (M2M) Device Meas...
An Ontology to Semantically Annotate the Machine-to-Machine (M2M) Device Meas...
 

Kürzlich hochgeladen

DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfJohn Sterrett
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Sapana Sha
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdfHuman37
 
Defining Constituents, Data Vizzes and Telling a Data Story
Defining Constituents, Data Vizzes and Telling a Data StoryDefining Constituents, Data Vizzes and Telling a Data Story
Defining Constituents, Data Vizzes and Telling a Data StoryJeremy Anderson
 
Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 2Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 217djon017
 
Predicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdfPredicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdfBoston Institute of Analytics
 
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一fhwihughh
 
RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.natarajan8993
 
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfKantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfSocial Samosa
 
How we prevented account sharing with MFA
How we prevented account sharing with MFAHow we prevented account sharing with MFA
How we prevented account sharing with MFAAndrei Kaleshka
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort servicejennyeacort
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsappssapnasaifi408
 
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degreeyuu sss
 
IMA MSN - Medical Students Network (2).pptx
IMA MSN - Medical Students Network (2).pptxIMA MSN - Medical Students Network (2).pptx
IMA MSN - Medical Students Network (2).pptxdolaknnilon
 
RadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfRadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfgstagge
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...Florian Roscheck
 
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)jennyeacort
 

Kürzlich hochgeladen (20)

DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdf
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf
 
Defining Constituents, Data Vizzes and Telling a Data Story
Defining Constituents, Data Vizzes and Telling a Data StoryDefining Constituents, Data Vizzes and Telling a Data Story
Defining Constituents, Data Vizzes and Telling a Data Story
 
Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 2Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 2
 
Predicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdfPredicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdf
 
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
 
RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.
 
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfKantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
 
How we prevented account sharing with MFA
How we prevented account sharing with MFAHow we prevented account sharing with MFA
How we prevented account sharing with MFA
 
Call Girls in Saket 99530🔝 56974 Escort Service
Call Girls in Saket 99530🔝 56974 Escort ServiceCall Girls in Saket 99530🔝 56974 Escort Service
Call Girls in Saket 99530🔝 56974 Escort Service
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
 
E-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptxE-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptx
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
 
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
 
IMA MSN - Medical Students Network (2).pptx
IMA MSN - Medical Students Network (2).pptxIMA MSN - Medical Students Network (2).pptx
IMA MSN - Medical Students Network (2).pptx
 
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
 
RadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfRadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdf
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
 
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
 

Personalized health knowledge graph ckg workshop - iswc 2018 (2)

  • 1. Personalized Health Knowledge Graph1 Ohio Center of Excellence in Knowledge-Enabled Computing Amelie Gyrard, Manas Gaur, Krishnaprasad Thirunarayan, Amit Sheth Kno.e.sis Research Center Department of Computer Science and Engineering, Wright State University, Dayton, Ohio (USA) Saeedeh Shekarpour University of Dayton, Ohio
  • 2. Problem • World Health Organization (WHO) estimates that the number of people suffering from asthma, obesity and Parkinson’s disease are respectively 235 million, 650 million, 4-6 million. => Need of “Personalized Preventive Coach Applications” to support physicians in understanding asthma symptoms 2
  • 3. Introduction DIKW pyramid: Data > Information > Knowledge > Wisdom/Actionable Insight 3Sheth, A., Anantharam, P., Henson, C.: Physical-cyber-social computing: An early 21st century approach. IEEE Intelligent Systems (2013), Slides: Semantic Web: introduction & overview [Sheth 2012]
  • 4. Agenda • The needs of Digital Health application ̶ Reasoner to derive meaningful information from health and IoT datasets ̶ Contextualization & Personalization • Limitations of the Related Work • Research Challenges • kHealth Project ̶ Use case for Asthma, Obesity and Parkinson diseases • Our solution: Personalized Healthcare Knowledge Graph ̶ Architecture ̶ Rule-based inference engine ̶ KAO ontology: Integration of knowledge from Ontology Catalogs • Conclusion and Future Work 4
  • 5. Definitions • Context-Awareness refers to the use of external data that can impact the user's situation. ̶ E.g., for Asthma: air pollution, pollen level • Personalization adjusts the treatment to each patient's condition. ̶ E.g., for Asthma patient: patient is allergic to a specific type of pollen 5
  • 6. Literature Survey: Limitations 6 Authors Publication date Topic KG ML Health KG Paulheim et al. 2016 Survey KG Yes No No Guha et al. Schema.org 2016 KG Yes No No Shi et al. 2017 Health KG Yes Yes Yes Yu et al. 2017 KG TCM Visualization Yes No Yes Ruan et al. 2017 KG TCM Yes No Yes Weng et al. 2017 KG TCM Yes No Yes Nickel al. 2016 KG + ML Yes Yes No Wilcke et al. 2017 KG + ML Yes Yes No Rotmensch et al. 2017 Health KG + EMR Yes Yes Yes Dong et al. 2014 Knowledge Vault - Google KG Yes No No No personalization No IoT datasets exploited to understand the surrounding environment of the patient
  • 7. KHealth Asthma: kit + cloud-based analysis + visual analytics dashboard 7Source: Augmented Personalized Health - URL (slide 21) Data Sources Heterogeneous data and collection method Smart Data Actionable meaningful information from the data collected Active and passive sensing
  • 8. KHealth Dataset • 8Source: Augmented Personalized Health - 23 parameters - URL (slide 25)
  • 9. Research Challenges (RC) • (RC1) How to model a knowledge graph for healthcare and chronic disease management? • (RC2) How to model personalization and context-awareness to represent patient's symptoms and derive actionable insights? • (RC3) How to analyze datasets generated by IoT devices to deduce information that is actionable? • (RC4) How to promote reproduceable experiments from previous projects (e.g., datasets, data models, and reasoning mechanisms)? • (RC5) How to customize and instantiate relevant knowledge from existing publicly available health knowledge bases to obtain insights from health-related social media text? 9 RC RC 1 RC 2 RC 3 RC 4 RC 5
  • 10. Our Solution: Personalized Healthcare Knowledge Graph Personalized Healthcare Knowledge Graph (PHKG) is a solution which explicitly describes and integrates both medical knowledge and personal health data, and can serve as a foundation for (deductive and abductive) reasoning. 10
  • 12. Reusing domain knowledge from Ontology Catalogs • BioPortal for biomedical ontologies [1] • Linked Open Vocabularies (LOV) [2] • Linked Open Vocabularies for Internet of Things (LOV4IoT) [3] [1] https://bioportal.bioontology.org/, [2] https://lov.linkeddata.es/dataset/lov/, [3] http://lov4iot.appspot.com/ RC 1, 2, 4
  • 14. SNOMED-CT • Knowledge is already encoded! • Example: Cough and Pollen concepts have rich taxonomies Pollen: http://purl.bioontology.org/ontology/SNOMEDCT/256259004 Cough: http://purl.bioontology.org/ontology/SNOMEDCT/49727002
  • 15. Kno.e.sis Alchemy API • 15 RC 2, 5 http://wiki.knoesis.org/index.php/Knoesis_Alchemy_of_Healthcare
  • 16. KAO Ontology • KAO: KHealth Asthma Ontology [1] • Integration of several ontologies relevant to interpret kHealth datasets ̶ W3C SOSA/SSN ̶ Asthma from BioPortal ̶ Weather and smart home ontologies [Staroch 2013] [Kofler et al. 2011] • More and more ontologies to integrate: ̶ SNOMED-CT from BioPortal (e.g., Cough, Pollen concepts) ̶ Symptoms Ontology ̶ Etc. [1] http://wiki.knoesis.org/index.php/KHealthAsthmaOntology
  • 17. KAO Ontology Evaluation • How to evaluate an ontology? ̶ So many tools to evaluate ontologies ̶ PerfectO [1] a platform to assist ontology developers in evaluating and improving ontologies • Set of ontology best practices executed with kao [2] [1] http://perfectsemanticweb.appspot.com/?p=ontologyValidation [2] http://wiki.knoesis.org/index.php/KHealthAsthmaOntology
  • 18. KAO Ontology Quality with PerfectO • http://perfectsemanticweb.appspot.com/documentation/SemanticWebBestPracticesForDummies.pdf http://wiki.knoesis.org/index.php/KHealthAsthmaOntology
  • 19. KAO Ontology Quality with PerfectO • http://perfectsemanticweb.appspot.com/documentation/SemanticWebBestPracticesForDummies.pdf http://wiki.knoesis.org/index.php/KHealthAsthmaOntology
  • 20. KAO Ontology Quality with PerfectO • http://perfectsemanticweb.appspot.com/documentation/SemanticWebBestPracticesForDummies.pdf http://wiki.knoesis.org/index.php/KHealthAsthmaOntology
  • 21. KAO Ontology Quality with PerfectO • http://perfectsemanticweb.appspot.com/documentation/SemanticWebBestPracticesForDummies.pdf http://wiki.knoesis.org/index.php/KHealthAsthmaOntology
  • 22. KAO Ontology Quality with PerfectO • http://perfectsemanticweb.appspot.com/documentation/SemanticWebBestPracticesForDummies.pdf http://wiki.knoesis.org/index.php/KHealthAsthmaOntology
  • 23. KHealth Reasoner 23 Raw kHealth Dataset kHealth Reasoner kHealth ontologies Semantic Dataset (RDF Triple Store) Example: pollen=11 rdf:type AO:Pollen rdf:type kao:HighPollenLevel 3) Update the triple store with more contextually relevant triples 2) Executing the reasoner1) Semantic Annotation Example: Asthma dataset pollen=11 Example: knoesis Asthma Ontology (kAO) Example: rdf:type kao:HighPollenLevel RC 2, 3
  • 25. Rule Example for Air Quality 25 • Rule implementation compliant with: ̶ Jena inference engine ̶ Ontologies: kao, W3C SOSA/SSN, etc • Code example: <= Usage of W3C SOSA/SSN ontology <= Usage of kao ontology
  • 26. Rule Example for Pollen Level 26 =>Change the thresholds with other parameters to achieve the personalization
  • 27. Rule Example for Heart Beat 27 =>?measurement = heart beat patient data Personalization
  • 28. Demo: Health Reasoner 28 => 6 scenarios supported by the health reasoner (pollen data, air quality, outside humidity, heart beat, room temperature and peak expiratory flow). http://linkedopenreasoning.appspot.com/
  • 29. Demo: Health Reasoner 29 => Enriched information => Automatic Semantic Annotation http://linkedopenreasoning.appspot.com/
  • 30. Completeness and Correctness of the KG 30 http://sensormeasurement.appspot.com/documentation/NomenclatureSensorData.pdf ● Correctness means that are no incompatibility with other rules ● Completeness means that all sensor values are covered by an high level information
  • 31. Overall Challenge Research Impact 31 Knowledge Extraction Internet of Things Natural Language Processing Web of Things Medical Text Analysis Semantic Web Knowledge Graphs
  • 32. Conclusion & Future Work ● Context-specific and personalized knowledge ● Reasoning mechanisms to deduce high-level abstractions from data and replace domain experts ● Challenge of integrating heterogeneous data from: ○ Healthcare, IoT data, Web of Data • Future work: ̶ More disease use cases (e.g., asthma, obesity, Parkinson) ̶ Dynamic PKG (continuous evolution based on incoming streams of observations) 32
  • 33. Acknowledgments ● This work is partially funded by: ○ Hazards SEES NSF Award EAR 1520870 ○ KHealth NIH 1 R01 HD087132-01. ● Thanks to the kHealth team for fruitful discussions and feedback. ● The opinions expressed are those of the authors and do not reflect those of the sponsors. 33
  • 35. Personalized Health Knowledge Graph Ohio Center of Excellence in Knowledge-Enabled Computing Amelie Gyrard, Manas Gaur, Krishnaprasad Thirunarayan, Amit Sheth Kno.e.sis Research Center Department of Computer Science and Engineering, Wright State University, Dayton, Ohio (USA) Saeedeh Shekarpour University of Dayton, Ohio
  • 36. Annexe: Modeling the Patient 36 ● Modeling the Person/Patient ● Body Mass Index Scenario: weight, height, age ● Challenges: ○ Property vs. class ○ Incomplete information
  • 37. Annexe: Modeling the Weight - BioPortal 37 • Results from BioPortal when looking for weight property
  • 38. Annexe: Modeling the Weight - LOV 38 • Query the LOV ontology catalog to find a weight property to describe the patient, sometimes concepts and not properties, decide among 148 results
  • 39. Annexe: Modeling the Weight - Schema.org 39 • Schema.org provides the Person concept, and its properties such as height, weight, but not the property age that would we need for computer BMI and since we do not have the birthdate for privacy reasons. • https://schema.org/weight
  • 40. Annexe: Modeling the Weight - DBpedia 40 • Weight description from DBpedia, notice that range must be in kilogram • http://dbpedia.org/ontology/Person/weight