Eighth Clinical and Translational Science Ontology Workshop: Difference between revisions

From NCOR Wiki
Jump to navigationJump to search
(63 intermediate revisions by 2 users not shown)
Line 1: Line 1:


== '''Announcement''' ==
== '''Background''' ==


'''The Clinical and Translational Science Ontology Group (CTSOG)''' invites you to join us March 16-18, 2022 in Orlando, Florida to discuss AI, Complex Systems in Biomedicine, and the role of ontology both in tempering the expectations of AI and advancing it to goals it can achieve.  For example, we hear things all the time like “Google’s deep-learning program for determining the 3D shapes of proteins stands to transform biology, say scientists.”  An optimism of this sort as to the potential of AI is shared by many working in the field of clinical and translational science. The purpose of this workshop is to explore the basis for this optimism, by looking at successes and failures of AI in different areas of biomedicine.
'''The Clinical and Translational Science Ontology Group (CTSOG)''' invites you to join us March 16-18, 2022 in Orlando, Florida to discuss AI, Complex Systems in Biomedicine, and the role of ontology both in tempering the expectations of AI and advancing it to goals it can achieve.  For example, we hear things all the time like “Google’s deep-learning program for determining the 3D shapes of proteins stands to transform biology, say scientists.”  An optimism of this sort as to the potential of AI is shared by many working in the field of clinical and translational science. The purpose of this workshop is to explore the basis for this optimism, by looking at successes and failures of AI in different areas of biomedicine. Details of prior workshops in this series are available [http://ncorwiki.buffalo.edu/index.php/Clinical_and_Translational_Science_Ontology_Group here].
 
Example topics include:
*Can NLP build useful medical ontologies?
*Machine learning and the role of ontology
*AI and team science
*AI and medical diagnosis and clinical decision support
*The limits of AI when applied to complex systems
*Complex systems and the replication crisis
*AI in therapeutic decision making
*AI in modelling cell biology
*AI in modelling systems biology
*AI-driven cell ontology
*The challenges of implementing AI in healthcare
 
'''Persons who are interested in participating can register [https://form.jotform.com/220035160081136 here]. If you have any questions, please contact William Hogan at hoganwr@ufl.edu.'''
 
----


== '''Organizers''' ==  
== '''Organizers''' ==  
Line 44: Line 27:


[https://embassysuites3.hilton.com/en/hotels/florida/embassy-suites-by-hilton-orlando-lake-buena-vista-south-MCOLKES/offers/index.htm Embassy Suites by Hilton Orlando Lake Buena Vista South], Kissimmee, FL (20 minutes from Orlando airport).  
[https://embassysuites3.hilton.com/en/hotels/florida/embassy-suites-by-hilton-orlando-lake-buena-vista-south-MCOLKES/offers/index.htm Embassy Suites by Hilton Orlando Lake Buena Vista South], Kissimmee, FL (20 minutes from Orlando airport).  
To reserve a room in our block, click [https://book.passkey.com/e/50259470 here].  The room rate is available 3 days pre and post meeting in case you'd like to stay in Florida and enjoy the warm weather a little longer.


=='''Registration'''==  
=='''Registration'''==  
Line 54: Line 35:
== '''Schedule'''==
== '''Schedule'''==


Outline of Agenda (starting and stopping times for official agenda each day in bold)
===Tuesday March 15th===
===Tuesday March 15th===


Line 63: Line 41:
===Wednesday March 16th===
===Wednesday March 16th===
   
   
9a-12p Working session on the ontology of social determinants of health
''Working session on the ontology of social determinants of health''
 
12p-1p Lunch (available to all, not just working session participants)
9:00 Clint Dowland, "Social Categories as Cognitively Represented Person Aggregates"
 
1p-1:15p Welcome and overview
10:45 Matt Diller, "[https://buffalo.box.com/v/Occuptions-Diller What We Mean When We Talk About Occupations]"
:We discuss two topics of ongoing work motivated by key SDoH use cases: (1) occupation and (2) social categories such as ethnic and gender categories
1:15p-3:15p '''AI and the Ontology of Complex Systems'''
*Opening Tutorial by Jobst Landgrebe, Cognotekt GmbH, co-sponsored by the [http://www.buffalo.edu/cas/philosophy/grad-study/ontology/wgaics.html Working Group on Artificial Intelligence and Complex Systems]


*Abstract: “Google’s deep-learning program for determining the 3D shapes of proteins stands to transform biology, say scientists.” An optimism of this sort as to the potential of AI is shared by many working in the field of clinical and translational science. The purpose of this tutorial is to explore the basis for this optimism, by looking at successes and failures of AI in different areas of biomedicine.
'''Tutorial'''


Potential topics to be explored are:
1:15-3:15 Jobst Landgrebe, '''AI and the Ontology of Complex Systems'''
:- Can NLP build useful medical ontologies?
:- Machine learning and the role of ontology
:- AI and team science
:- AI and medical diagnosis and clinical decision support
:- The limits of AI when applied to complex systems
:- Complex systems and the replication crisis
:- AI in therapeutic decision making
:- AI in modelling cell biology
:- AI in modelling systems biology
:- AI-driven cell ontology
:- The challenges of implementing AI in healthcare
The tutorial will focus on the question of what domains of medicine will benefit most from AI and how AI will impact the way we work in research and medical care.


Jobst Landgrebe is the founder and managing director of Cognotekt, an AI company based in Cologne, Germany, focusing on the creation of structured data from natural language text. Dr Landgrebe is an MD with a background in biomedical informatics. He is the co-author, with Barry Smith, of ''Why Machines Will Never Rule the World. Artificial Intelligence without Fear'', to be published by Routledge in summer 2022.
:Abstract: “Google’s deep-learning program for determining the 3D shapes of proteins stands to transform biology, say scientists.” An optimism of this sort as to the potential of AI is shared by many working in the field of clinical and translational science. The purpose of this tutorial is to explore the basis for this optimism, by looking at successes and failures of AI in different areas of biomedicine.
3:15-3:30 Break
3:30-5:00 Presentations


*Sivaram Arabandi, '''Clinical Decision Support, AI, and Ontology'''
[https://buffalo.box.com/v/Landgrebe-AI-in-Medicine Slides]


*Abstract: In an increasingly polychronic patient population, acute and/or new diseases (e.g. Covid) present a distressing reality of our limitations in providing high quality clinical care. A key challenge for Clinical Decision Support has been in building executable clinical guideline models that can interpret patient data and provide insights at the point of care. In this talk, the CPG-on-FHIR open standards based framework for creating shareable and reusable Clinical Practice Guidelines (CPG)  is described.
[https://buffalo.box.com/v/Landgrebe-Tutorial-CTS8 Video]
<small>
:'''1.''' Medicine: A Science of Complex Systems (0:00:00)
:::The Cartesian (Mechanistic) View of Medicine (0:02:23)
:::Cartesian Sciences Describe Simple (= Logic) Systems (0:05:15)
:::Phenomena Underlying Medicine are Complex System Processes (0:14:10)
:'''2.''' AI in Clinical Medicine: An Overview (0:28:59)
:::Limits of AI in Clinical Medicine (0:42:36)
:'''3.''' AI for Biomedical Research (1:00:37)
:::AlphaFold (1:01:30)
:'''4.''' Conclusion (1:26:15)
:::AI Will Bring Many Benefits to Medicine, But it Will Not Change its Nature as a Heuristic Science (1:26:15)
:::AlfaFold: One of the Greatest Achievements on the Part of Human Beings since Cologne Cathedral (1:32:2)
</small>
Jobst Landgrebe is the founder and managing director of Cognotekt, an AI company based in Cologne, Germany, focusing on the creation of structured data from natural language text. Dr Landgrebe is an MD with a background in biomedical informatics. He is the co-author, with Barry Smith, of ''Why Machines Will Never Rule the World. Artificial Intelligence without Fear'', to be published by Routledge in summer 2022. This tutorial is co-sponsored by the University at Buffalo [http://www.buffalo.edu/cas/philosophy/grad-study/ontology/wgaics.html Working Group on Artificial Intelligence and Complex Systems]
3:30-5:00 Sivaram Arabandi, '''Clinical Decision Support, AI, and Ontology''' [https://buffalo.box.com/v/Arabandi-CDS-CPG Slides] [https://buffalo.box.com/v/Arabandi-CPG Video]
:Abstract: In an increasingly polychronic patient population, acute and/or new diseases (e.g. Covid) present a distressing reality of our limitations in providing high quality clinical care. A key challenge for Clinical Decision Support has been in building executable clinical guideline models that can interpret patient data and provide insights at the point of care. In this talk, the CPG-on-FHIR open standards based framework for creating shareable and reusable Clinical Practice Guidelines (CPG)  is described.
   
   
5:30p Reception
5:30p Reception / Working Dinner


===Thursday March 17th===
===Thursday March 17th===


9a-'''5p''' Presentations with breaks and lunch provided
'''Presentations'''
 
Times TBD


*Bill Hogan, '''Ontology for Social Determinants of Health with a Focus on Education'''
*9:00 Bill Hogan, '''Ontology for Social Determinants of Health with a Focus on Education''' [https://buffalo.box.com/v/Hogan-Social-Health Slides]
:Educational attainment is a key social determinant of health.  I will report on classes developed in the Ontology of Medically Related Social Entities (OMRSE), where we defend a view that education imparts both knowledge (as an ICE) and the neurologically-based skills (some motor, some more intellectual) to apply it.
:Educational attainment is a key social determinant of health.  I will report on classes developed in the Ontology of Medically Related Social Entities (OMRSE), where we defend a view that education imparts both knowledge (as an ICE) and the neurologically-based skills (some motor, some more intellectual) to apply it.


*Jobst Landgrebe, '''The Replication Problem: Bad News for Medicine'''
*10:00 Jobst Landgrebe, '''The Replication Problem: Bad News for Medicine''' [https://buffalo.box.com/v/Landgrebe-Replication-Med Slides]  [https://buffalo.box.com/v/Landgrebe-Replication Video]
:The 'replication problem' is a phrase to describe the inability of scientific communities to independently confirm the results of scientific work. It has plagued medicine as a positive science since its beginnings (Virchov and Pasteur). But it has become worse over the last 30 years and has massive consequences for healthcare practice and policy. This talk explains the reasons for the replication problem in medicine and why it is here to stay.
:The 'replication problem' is a phrase to describe the inability of scientific communities to independently confirm the results of scientific work. It has plagued medicine as a positive science since its beginnings (Virchov and Pasteur). But it has become worse over the last 30 years and has massive consequences for healthcare practice and policy. This talk explains the reasons for the replication problem in medicine and why it is here to stay.


*Amelia Kahn, '''Definitions of Uncertainty'''
*11:00 Coffee
 
*11:15 Amelia Kahn, '''Definitions of Uncertainty''' [https://buffalo.box.com/v/Kahn-Uncertainty Slides]
:A preliminary survey of meanings assigned by government agencies to estimative words in the domain of probability and statistics.   
:A preliminary survey of meanings assigned by government agencies to estimative words in the domain of probability and statistics.   


*Barry Smith, '''Capabilities'''
*12:15 Lunch
:''Capability'' has been proposed as a universal intermediate between ''Function'' and ''Disposition'' in BFO. A capability is defined as a disposition in whose realisation some organism or group of organisms has an interest. We outline the implications of this definition for medicine.
 
*13:00 Barry Smith, '''Capabilities''' [https://buffalo.box.com/v/Capabilities-Language Slides] [https://www.youtube.com/watch?v=jH1sc7FTs3w Video]
:Part 1 provides a general theory of ''capability'' as a universal intermediate between ''function'' and ''disposition'' in BFO. A capability is defined as a disposition in whose realisation some organism or group of organisms has an interest.
:Part 2 develops an ontology of language according to which a language is a capability of a linguistic community. The theory is tested in application to dialects phenomena.


*Clint Dowland, '''Ontology of social categories'''
*14:00 Clint Dowland, '''Language Capabilities and Clinical Demographics''' [https://buffalo.box.com/v/Dowland-Language Slides]


*Matt Diller, '''The ontology of money with a view towards economic determinants of health'''
*15:00 Matt Diller, '''The Ontology of Money with a View towards Economic Determinants of Health''' [https://buffalo.box.com/v/Money-Diller Slides]
:Matters of money constitute an entire category of social determinants of health. To understand them, we first wish to define 'money'.
:Matters of money constitute an entire category of social determinants of health. To understand them, we first wish to define 'money'.
*16:00 Jihad Obeid, '''Phenotyping Using Deep Learning Text Classification: Can Ontologies Play a Role?''' [https://buffalo.box.com/v/Obeid-AI-Ontology Slides]
:The use of electronic health records (EHR) to identify specific clinical phenotypes has gained significant momentum over recent years. A variety of natural language processing pipelines leverage ontologies for of clinical text annotation and information extraction. With the advent of vast computational power, significant strides have been made in deep learning approaches. During this presentation, we will discuss various use cases of clinical text classifiers, using both traditional machine learning algorithms and deep learning. We will examine the performance and utility of these models for both phenotyping and predictive tasks in a variety of clinical scenarios as well as the impact of pre-trained simple language models. Future approaches using more advanced language models and ontologies will be considered.
6:30pm Working dinner


===Friday March 18th===
===Friday March 18th===
Line 131: Line 114:
*Discussion and next steps
*Discussion and next steps


=='''Rationale/Goals'''==
Presentations by Jobst Landgrebe on explainable AI and by Barry Smith on healthcare economics ontologies
 
 
 
== '''Travel Fund Application'''==
 


== '''Participants''' ==
== '''Participants''' ==


*Barry Smith, co-organizer, University at Buffalo
*Barry Smith, co-organizer, University at Buffalo
*Jobst Landgrebe, co-organizer and special guest
*Jobst Landgrebe, co-organizer, University at Buffalo
*William Hogan, co-organizer, University of Florida
*William Hogan, co-organizer, University of Florida


*Sivaram Arabandi, Ontopro
*Sivaram Arabandi, Ontopro
*Ravi Bajracharya, datum.md
*Jiang Bian, University of Florida
*Sarah Bost, University of Florida
*Sarah Bost, University of Florida
*Naomi Braun, University of Florida
*Naomi Braun, University of Florida
*Matt Diller, University of Florida
*Matt Diller, University of Florida
*Clint Dowland, University of Florida
*Clint Dowland, University of Florida
*Bill Duncan, University of Florida
*Yi Guo, University of Florida
*Hank Head, Optum Inc.
*Amelia Kahn, University at Buffalo
*Amelia Kahn, University at Buffalo
*Asiyah Lin, National Institutes of Health
*Alex Loiacono, University of Florida
*Alex Loiacono, University of Florida
*Jihad Obeid, Medical University of South Carolina
*Jihad Obeid, Medical University of South Carolina
*Samson Tu, Stanford University
*Donny Weinbrenner, University of Florida
*Donny Weinbrenner, University of Florida
*Pengfei Yin, University of Florida

Revision as of 00:45, 31 March 2022

Background

The Clinical and Translational Science Ontology Group (CTSOG) invites you to join us March 16-18, 2022 in Orlando, Florida to discuss AI, Complex Systems in Biomedicine, and the role of ontology both in tempering the expectations of AI and advancing it to goals it can achieve. For example, we hear things all the time like “Google’s deep-learning program for determining the 3D shapes of proteins stands to transform biology, say scientists.” An optimism of this sort as to the potential of AI is shared by many working in the field of clinical and translational science. The purpose of this workshop is to explore the basis for this optimism, by looking at successes and failures of AI in different areas of biomedicine. Details of prior workshops in this series are available here.

Organizers

Workshop Co-organizers:

Bill Hogan, Jobst Landgrebe, Barry Smith

CTSOG Co-chairs:

Bill Hogan (University of Florida College of Medicine, Gainesville, FL), hoganwr@ufl.edu

Barry Smith (University at Buffalo, Buffalo, NY), phismith@buffalo.edu

Past meetings of CTSOG

Sponsors

  • University of Florida Clinical and Translational Science Institute Biomedical Informatics Program

Date

March 16 (Wednesday) - 18 (Friday), 2022

Venue

Embassy Suites by Hilton Orlando Lake Buena Vista South, Kissimmee, FL (20 minutes from Orlando airport).

Registration

Registration is free, but we absolutely need you to register for planning purposes.

To register for the meeting, click here.

Schedule

Tuesday March 15th

Pre-Workshop Informal Meet & Greet: We will meet between 7pm and 10pm ...

Wednesday March 16th

Working session on the ontology of social determinants of health

9:00 Clint Dowland, "Social Categories as Cognitively Represented Person Aggregates"

10:45 Matt Diller, "What We Mean When We Talk About Occupations"

We discuss two topics of ongoing work motivated by key SDoH use cases: (1) occupation and (2) social categories such as ethnic and gender categories

Tutorial

1:15-3:15 Jobst Landgrebe, AI and the Ontology of Complex Systems

Abstract: “Google’s deep-learning program for determining the 3D shapes of proteins stands to transform biology, say scientists.” An optimism of this sort as to the potential of AI is shared by many working in the field of clinical and translational science. The purpose of this tutorial is to explore the basis for this optimism, by looking at successes and failures of AI in different areas of biomedicine.

Slides

Video

1. Medicine: A Science of Complex Systems (0:00:00)
The Cartesian (Mechanistic) View of Medicine (0:02:23)
Cartesian Sciences Describe Simple (= Logic) Systems (0:05:15)
Phenomena Underlying Medicine are Complex System Processes (0:14:10)
2. AI in Clinical Medicine: An Overview (0:28:59)
Limits of AI in Clinical Medicine (0:42:36)
3. AI for Biomedical Research (1:00:37)
AlphaFold (1:01:30)
4. Conclusion (1:26:15)
AI Will Bring Many Benefits to Medicine, But it Will Not Change its Nature as a Heuristic Science (1:26:15)
AlfaFold: One of the Greatest Achievements on the Part of Human Beings since Cologne Cathedral (1:32:2)

Jobst Landgrebe is the founder and managing director of Cognotekt, an AI company based in Cologne, Germany, focusing on the creation of structured data from natural language text. Dr Landgrebe is an MD with a background in biomedical informatics. He is the co-author, with Barry Smith, of Why Machines Will Never Rule the World. Artificial Intelligence without Fear, to be published by Routledge in summer 2022. This tutorial is co-sponsored by the University at Buffalo Working Group on Artificial Intelligence and Complex Systems

3:30-5:00 Sivaram Arabandi, Clinical Decision Support, AI, and Ontology Slides Video

Abstract: In an increasingly polychronic patient population, acute and/or new diseases (e.g. Covid) present a distressing reality of our limitations in providing high quality clinical care. A key challenge for Clinical Decision Support has been in building executable clinical guideline models that can interpret patient data and provide insights at the point of care. In this talk, the CPG-on-FHIR open standards based framework for creating shareable and reusable Clinical Practice Guidelines (CPG) is described.

5:30p Reception / Working Dinner

Thursday March 17th

Presentations

  • 9:00 Bill Hogan, Ontology for Social Determinants of Health with a Focus on Education Slides
Educational attainment is a key social determinant of health. I will report on classes developed in the Ontology of Medically Related Social Entities (OMRSE), where we defend a view that education imparts both knowledge (as an ICE) and the neurologically-based skills (some motor, some more intellectual) to apply it.
  • 10:00 Jobst Landgrebe, The Replication Problem: Bad News for Medicine Slides Video
The 'replication problem' is a phrase to describe the inability of scientific communities to independently confirm the results of scientific work. It has plagued medicine as a positive science since its beginnings (Virchov and Pasteur). But it has become worse over the last 30 years and has massive consequences for healthcare practice and policy. This talk explains the reasons for the replication problem in medicine and why it is here to stay.
  • 11:00 Coffee
  • 11:15 Amelia Kahn, Definitions of Uncertainty Slides
A preliminary survey of meanings assigned by government agencies to estimative words in the domain of probability and statistics.
  • 12:15 Lunch
Part 1 provides a general theory of capability as a universal intermediate between function and disposition in BFO. A capability is defined as a disposition in whose realisation some organism or group of organisms has an interest.
Part 2 develops an ontology of language according to which a language is a capability of a linguistic community. The theory is tested in application to dialects phenomena.
  • 14:00 Clint Dowland, Language Capabilities and Clinical Demographics Slides
  • 15:00 Matt Diller, The Ontology of Money with a View towards Economic Determinants of Health Slides
Matters of money constitute an entire category of social determinants of health. To understand them, we first wish to define 'money'.
  • 16:00 Jihad Obeid, Phenotyping Using Deep Learning Text Classification: Can Ontologies Play a Role? Slides
The use of electronic health records (EHR) to identify specific clinical phenotypes has gained significant momentum over recent years. A variety of natural language processing pipelines leverage ontologies for of clinical text annotation and information extraction. With the advent of vast computational power, significant strides have been made in deep learning approaches. During this presentation, we will discuss various use cases of clinical text classifiers, using both traditional machine learning algorithms and deep learning. We will examine the performance and utility of these models for both phenotyping and predictive tasks in a variety of clinical scenarios as well as the impact of pre-trained simple language models. Future approaches using more advanced language models and ontologies will be considered.

6:30pm Working dinner

Friday March 18th

9a-12p Working session and discussion of next steps, closing

  • Discussion and next steps

Presentations by Jobst Landgrebe on explainable AI and by Barry Smith on healthcare economics ontologies

Participants

  • Barry Smith, co-organizer, University at Buffalo
  • Jobst Landgrebe, co-organizer, University at Buffalo
  • William Hogan, co-organizer, University of Florida
  • Sivaram Arabandi, Ontopro
  • Ravi Bajracharya, datum.md
  • Jiang Bian, University of Florida
  • Sarah Bost, University of Florida
  • Naomi Braun, University of Florida
  • Matt Diller, University of Florida
  • Clint Dowland, University of Florida
  • Bill Duncan, University of Florida
  • Yi Guo, University of Florida
  • Hank Head, Optum Inc.
  • Amelia Kahn, University at Buffalo
  • Alex Loiacono, University of Florida
  • Jihad Obeid, Medical University of South Carolina
  • Samson Tu, Stanford University
  • Donny Weinbrenner, University of Florida
  • Pengfei Yin, University of Florida