2022 - 2023 LHS Collaboratory Archive

Dipak Kalra, PhD, FRCGP, FACMI, FBCS

View Dr. Kalra's slides here.

"Implementing AI in Health"

Lisa Lehmann, PhD, MD, "A Roadmap for Implementing Trustworthy AI in Healthcare"

View Lisa Lehmann's presentation slides here.

Michael Pencina, PhD, "Evaluation and Governance of AI-based Clinical Decision Support Tools in Health Systems"

Recording- AM Session 

Recording- PM Session 

Barbara Barry, PhD, "Implementing AI in Health Care with a Human-in-the-Loop"

View Barbara Barry's presentation slides here.

Michael Kim, MD, "Translating Trustworthy AI Frameworks into Practice at the US Department of Veterans Affairs"

View Michael Kim's presentation slides here.

Keynote Speaker:  

Thomas Campion, Jr., PhD, FACMI, FAMIA

Clinical and translational investigators need patient data, especially from electronic health record (EHR) systems, to conduct research, but optimal approaches are unknown.  This talk explores an approach for supporting different types of investigators and study designs by matching investigators with informatics tools and services.

View the recording here.

"Interoperability of Electronic Medical and Dental Records: A Learning Health System (LHS) Approach to Sharing Data, Generating Knowledge, Changing Practice and Improving Patient Outcomes”

Keynote Speaker:  

Lawrence A. Tabak, DDS, PhD, Performing the Duties of the NIH Director

"The Future is Data Analytics: Many Challenges, Many Opportunities”

View the recording here.

Breakout room #1: Data Integration and Sharing: Opportunities in Entrepreneurship and Research

Wenyuan Shi, PhD, Chief Executive Officer, Forsyth Institute

Presentation: Building the Eco-system to Support Disruptive Technologies in Dentistry

Christopher Balaban, DMD, MSC, FACD, Vice President of Clinical Affairs, Overjet

Presentation: Entrepreneurship and AI/LHS in Dentistry

View the recording here.

Breakout room # 2:  Data Integration and Sharing in/out of the Clinic: New Medical and Dental Technologies and LHS Methods to Optimize Care

Alexandre F. M. DaSilva, DDS, DMedSc, Tenured Professor, Director of Learning Health Systems, University of Michigan School of Dentistry

Presentation: Integrating and Sharing Dental and Medical Data in a Diverse Ecosystem – The Learning Health Systems Perspective

Muhammad F. Walji, PhD, Associate Dean, Technology Services & Informatics, Professor, School of Dentistry, UT Health Science Center at Houston

Presentation: BigMouth: Lessons Learned from a Decade of Sharing EHR Data in Dentistry

View the recording here.

Breakout room #3: Data Integration and Sharing in Imaging and Pharmacogenetics

Lucia Cevidanes, DDS, MS, PhD, Thomas and Doris Graber Endowed Professor of Dentistry, Predoctoral Orthodontics Director, University of Michigan School of Dentistry

Presentation: Innovations in Multimodal Imaging Data Integration and Sharing

Amy Pasternak, PharmD, Clinical Assistant Professor of Pharmacy and Clinical Pharmacist, Michigan Medicine

Presentation: Integrating Pharmacogenomics into Daily Practice

View the recording here.

Osagie K. Obasogie, JD, PhD, Haas Distinguished Chair, Professor of Law and Bioethics, University of California, Berkeley

An interview and discussion with Professor Osagie K. Obasogie, JD, PhD.  Facilitators Jodyn E. Platt, MPH, PhD, Azia Harris-Martin, and Salomé Viljoen.

Kayte Spector-Bagdady, JD, Bioethics, Interim Co-Director, Center for Bioethics & Social Sciences in Medicine Assistant Professor, Obstetrics & Gynecology
University of Michigan Medical School

In contrast to the laborious and expensive process of generating genetic datasets de novo, academic genetic researchers are increasingly using large and inexpensive “secondary” research datasets held by government, consortia, and industry for their work. Choosing between different kinds of data providers is about more than just convenience, however, it can also have important implications for the kind of science advanced and to which communities it will generalize. This talk will explore the factors driving researchers to select certain datasets for their work as well as their experiences sharing to, as well as using, shared data resources. As researchers wait for the new National Institutes of Health’s “Policy for Data Management and Sharing” to go into effect in January 2023, this talk will explore who ultimately carries the burden of increasing data sharing requirements

Kadija Ferryman, PhD, Assistant Professor, Johns Hopkins Bloomberg School of Public Health

In this talk, Professor Ferryman will discuss the merits and challenges of conducting health equity reviews of artificial intelligence (AI) tools used in health and medicine. The talk will examine how interdisciplinary approaches from the social sciences, bioethics and humanities, and computational fields can be involved in the development of concepts, methods, frameworks, and guidelines for understanding and governing digital health tools.

Dr. Kadija Ferryman's presentation slides.

Alex John London, PhD, Clara L. West Professor of Ethics and Philosophy, Director of the Center for Ethics and Policy at Carnegie Mellon University

Explainability Is Not the Solution to Structural Challenges to AI in Medicine

Explainability is often treated as a necessary condition for ethical applications of artificial intelligence (AI) in Medicine. In this brief talk I survey some of the structural challenges facing the development and deployment of effective AI systems in health care to illustrate some of the limitations to explainability in addressing these challenges. This talk builds on prior work (London 2019, 2022) to illustrate how ambitions for AI in health care likely require significant changes to key aspects of health systems.

Melissa McCradden, PhD, MHSc

John and Melinda Thompson Director of AI in Medicine (Integration lead), Bioethicist, The Hospital for Sick Children

On the Inextricability of Explainability from Ethics: Explainable AI does not Ethical AI Make

Explainability is embedded into a plethora of legal, professional, and regulatory guidelines as it is often presumed that an ethical use of AI will require explainable algorithms. There is considerable controversy, however, as to whether post hoc explanations are computationally reliable, their value for decision-making, and the relational implications of their use in shared decision-making. This talk will explore the literature across these domains and argue that while post hoc explainability may be a reasonable technical goal, it should not be offered status as a moral standard by which AI use is judged to be ‘ethical.’

The session is moderated by Karandeep Singh, MD, MMSc, Assistant Professor of Learning Health Sciences, Assistant Professor of Internal Medicine, University of Michigan.

Dr. Melissa McCradden's presentation slides

"A Celebration of Learning Health Systems at the University of Michigan"

Complete list of poster titles, authors, and affiliations  

1. LHS Collaboratory:  Working Together to Implement Learning Health Systems at the University of Michigan
2. The Learning Health Systems Collaboratory:  Emphasis on the Ethical, Legal, and Social Implications of Learning Health Systems (ELSI-LHS)
3. A Panorama of LHS efforts @ UofM Health & Beyond (IHPI students)
4. UM OVPR BOLD Challenge: 3D Mobile Technology to increase diversity, inclusion, and accuracy in pain management of complex patients -  School of Dentistry
5. Building the Field of Improvement Research in Education: The UM School of Education as Catalyst and Hub
6. Concussion Learning Health System (C-LHS): Lessons Learned and a Path Forward  
7. Single and Multi-Institutional Experience in Radiation Oncology Constructing a Learning Health System (LHS) from Real World Data
8. Applying the LHS Framework in Real Life: Building a Learning Health System for Medical Rehabilitation
9. HeartSafe Home: Learning Community Initiative to Reduce Out-of-Hospital Cardiac Arrest Mortality
10. The Heinz C. Prechter Bipolar Research Program: A Snapshot of Longitudinal Data
11. Precision Health at the University of Michigan
12. Leveraging Library Expertise to Make Computable Biomedical Knowledge FAIR
13. Precision Feedback: A Scalable Service to Improve the Quality of Anesthesia Care
14. Enhancing Researcher Value: Connecting MICHR’s Network-Based Research Unit (NBRU)
15. Behind the Scenes at the NBRU: An Inside Look at the Informatics and IT Enabling MICHR’s Network-Based Research Unit
16. Clinical Intelligence Committee at Michigan Medicine-Governing Machine Learning to Support Michigan Medicine Priorities
17. MSQC Leads Hospitals to Save $3 Million in Colectomy Post-Discharge Spending
18. The Michigan Cardiac Rehabilitation Network (MiCRN): A Statewide Collaboration to Improve Cardiac Rehabilitation Participation  (MCV CQI)
19. An Overview of the Michigan Urological Surgery Improvement Collaborative (MUSIC)
20. Using Registry Data to Drive Quality Improvement: The BMC2 Experience
21. MOQC Michigan Oncology Quality Consortium
22. MCT2D  “The Michigan Collaborative for Type 2 Diabetes”
23. Leveraging Cross-Sector Partnerships to Address Social Determinants of Health
24. e-HAIL: Making the University of Michigan a Premier Hub for e-Health and AI
25. Michigan Radiation Oncology Quality Consortium (MROQC)
26. Mobilizing Computable Biomedical Knowledge: A Growing Community to Transform Health
27. Journal of Learning Health Systems: A Novel Journal for a Transdisciplinary Science