The University of Michigan’s Department of Learning Health Sciences partners with the Institute for Healthcare Policy & Innovation and the Office of Research to convene the LHS Collaboratory: a hub for advancing interdisciplinary research and development of learning health systems at the University of Michigan.
Below are the archives of all the LHS Collaboratory's previous events ranging from 2016 to the current academic year.
2022 - 2023 Collaboratory Archive
Thursday, January 19, 2023
"A Conversation about Justice and Governance in Learning Health Systems: Legal and Ethical Issues"
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
Tuesday, November 8, 2022
Health Equity Reviews for AI in Health and Medicine
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.
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.
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.
This virtual workshop will review the concepts behind Learning Communities, which are foundational to Learning Health Systems. We will explore the phases of all learning communities, regardless of size or problem of interest: planning, initiating, implementing, and sustaining. Participants will engage in a collaborative activity to develop a learning community. Please join us either individually or as part of a team.
Tuesday, May 14, 2022
LHS Collaboratory Workshop: Learning Health Systems 101
This virtual workshop will review the basic concepts behind Learning Health Systems including the learning cycle, infrastructure, and learning communities. Participants will engage in a collaborative activity to design a learning cycle.
In this talk, Alan Karthikesalingam will discuss lessons learned in Google's experiences of taking medical AI systems from early research to clinical implementation.
Medical AI - Raising the Bar on Evidence Standards
In this talk, Xiao Liu will discuss existing and new clinical evidence standards as applied to medical AI systems. Her talk will focus on recently published standards to ensure transparency and reproducibility of clinical evidence underpinning medical AI systems, including reporting guidelines such as SPIRIT-AI and CONSORT-AI.
In this talk, Kathleen McTigue describes the vision of PCORNet, its organization, and its value to the field of clinical research. PCORNet is divided into regional subnetworks one of which is PaTH. The organization of PaTH along with its priories will be discussed.
The University of Michigan is an institutional member of PaTH/PCORNet.
In this talk, David Williams describes the organization and processes of the UM site within PCORNet/PaTH, studies in which UM participates, and resources for UM investigators interested in participating in PCORNet studies.
The session will describe the landscape history, current status, and future of federated health data networks that are used to support a Learning Health System. Dr. Brown will describe the creation, infrastructure, operation, and uses of several networks from the perspective of a network coordinating center. Dr. Harris will describe insights from participating in multiple networks as a network partner, including infrastructure, governance, and operational lessons learned.
This presentation will explore how Big Data Science and Informatics research can overcome deficiencies within the electronic health record and optimize real world data collection. We will discuss examples of how standardized nomenclature integrated into clinical workflow can enable statistical AI methods to advance clinical decision support and improve outcome models. Our successes in radiation oncology come from single multi-institutional, multi-national and multi-professional society collaboration.
Interoperability is considered a key capability of a high-performing healthcare system and has been a top policy priority for more than a decade. Implementing interoperability is, however, a complex undertaking – requiring stakeholder coordination that tackles incentives, governance, technology, standards, and more. In this talk, Dr. Adler-Milstein will describe current approaches to interoperability and where we stand with respect to current levels of national adoption. She will then discuss the implications for Learning Health System efforts at different levels of scale.
Special Fall Workshop: Operationalizing Learning Communities
This virtual workshop will review the concepts behind Learning Communities which are foundational to Learning Health Systems. We will explore the phases of all learning communities, regardless of size or problem of interest: planning, initiating, implementing, and sustaining. Participants will engage in a collaborative activity to develop a learning community. Please join us either individually or as part of a team.
Unlike structured data, unstructured data are often buried within free text clinical narratives that are difficult to analyze and interpret to derive useful insights. Free text cannot be easily categorized in the same way that a structured, numerical data point can, and unstructured data often have nuances that are not easily captured or represented in structured data.
This session will cover methods and techniques for interpreting and converting unstructured text into useful research data using two related, but distinct approaches: (1) Natural Language Processing (NLP), a specialized branch of AI focused on the interpretation and manipulation of human-generated spoken or written data; and (2) information retrieval, which often underlies many search engine technologies. This session will also highlight EMERSE, an open-source information retrieval tool that has been designed to help everyday users work with the free text documents (i.e., clinical notes) in medical records that is now being adopted by other academic medical centers.
Finally, attendees will hear directly from researchers about how they have used these methods and tools to enhance their research by accessing and harnessing the power of unstructured data.
Bringing data to the people: How a secure, self-service, free text search tool can empower clinical research teams and improve productivity
Janet and Bernard Becker Professor and founding Director of the Institute for Informatics (I2), Associate Dean for Health Information and Data Science, Chief Data Scientist, Washington University in St. Louis
The Learning Health (Record) System
Much has been written about the challenges associated with the use of current EHRs, however the promise of these technology platforms remans vast and mostly under-realized. This presentation will explore the ways in which Biomedical Data Science and Informatics research are helping to realize the potential of EHR technologies in the context of creating an LHS, from the optimization of workflow and human factors, to the generation of reproducible and systemic clinical phenotypes, to the delivery of emergent knowledge to both providers and patients via advanced clinical support systems.
Research Assistant Professor, Department of Biomedical Informatics, Scientific Director for PheWAS Core, Vanderbilt University
Techniques and Challenges for EHR Phenotyping
Electronic health records (EHR) contain a wealth of real world data that can be used for research purposes. However, extracting phenotype information from EHRs can be challenging. EHR phenotyping can be divided into two types: (1) Fast phenotyping which seeks to capture a broad swath of the medical phenome, and is often accomplished using coded EHR data (e.g. billing codes) and (2) slow phenotyping that seeks to achieve high precision and recall for a single phenotype, and often uses multiple EHR data types (e.g. medications, text, lab results). This talk will describe specific use-cases for both fast and slow phenotyping, and review challenges that are commonly encountered in creating research-grade EHR phenotypes.
LHS Collaboratory Summer Workshop: Learning Health Systems 101
This virtual workshop will review the basic concepts behind Learning Health Systems including the learning cycle, infrastructure, and learning communities. Participants will engage in a collaborative activity to design a learning cycle. Registration for this event is limited. Please consider registering early.
The Swiss Learning Health System (SLHS): A National Initiative to Support Evidence Uptake in Policy and Practice
Dr. Boes and Dr. Mantwill will provide an overview of the SLHS and its key features, as well as its capacity-building efforts to train young researchers in the field of learning health systems, and the development of a centralized metadata repository in support of creating a sufficient large evidence basis to support learning cycles in the Swiss health system. Further, they will discuss lessons learned from the past and the newest developments of the SLHS in light of a second funding phase supported by the Swiss government.
Promoting and supporting the uptake of evidence and evidence-informed decision-making in health-systems related policy and practice is a challenge. In Switzerland, the need to address this matter has been increasingly emphasized by different actors in the health system. In particular, the lack of comprehensive coordination efforts in the field of health services research, and subsequent knowledge translation activities, has been stressed.
In response, the Swiss Learning Health System (SLHS) was established as a nationwide project in 2017, currently involving ten academic partner institutions. One of the overarching objectives of the SLHS is to bridge research, policy, and practice by providing an infrastructure that supports learning cycles by: continuously identifying issues relevant to the Swiss health system, systemizing relevant evidence, presenting potential courses of action, and revising and reshaping responses.
Key features of learning cycles in the SLHS include the development of policy/evidence briefs that serve as a basis for stakeholder dialogues with actors from research, policy, and practice. Issues that are identified to be further pursued are monitored for potential implementation and eventually evaluated to inform new learning cycles and to support continuous learning within the system.
Professor
Computational Medicine and Bioinformatics, Medical School
Associate Director for Education and Training, Michigan Institute for Data Science (MIDAS)
Vice Chair
Department of Health Behavior and Biological Sciences
University of Michigan
Perspective: Data De‐Identification and Clinical Decision Support
Senior Director, Department of Evidence Synthesis and Translation Research
American Dental Association,
Science and Research Institute, LLC
Adjunct Assistant Professor
Department of Oral and Craniofacial Health Science, School of Dentistry,
University of North Carolina
at Chapel Hill
Perspective: LHS and Evidence-based Clinical Practice
Bert N. LaDu Professor of Anesthesiology
Senior Associate Chair, Research
Co-Director of the Michigan Opioid Prescribing Engagement Network (Michigan OPEN)
University of Michigan
Perspective: Precision Health in Opioid Management
Learning Health Systems thrive with use of real-world data from electronic health record (EHR) systems in both observational and interventional research to generate real-world evidence. Standardized EHR data can enable the aggregation of data and the generation of real-world evidence that will inform care delivery and improve patient outcomes. Data standards can also increase the speed in which promising evidence-based interventions are disseminated and adopted into new settings. However, despite their great potential, data standards have proven to be difficult and costly to implement, and nationally standardized EHR data continues to elude us.
Speaker: Rachel Richesson, PhD, MPH, MS, FACMI, Professor of Learning Health Sciences
Thursday, November 12, 2020
Reflections on Learning to Improve: Foundational Ideas, Observations from Practice, and Building a Field
Dr. Bryk’s talk describes a set of normative challenges that confront us, including ways to shift from pursuing the hot new idea as the silver bullet to continuously improving how core processes and systems in educational institutions work. It is a distinct form of inquiry that values basic research knowledge and rigorous evidence about new programs and interventions, but that also sees efforts aiming to solve problems of practice reliably and at scale as generating its own form of generalizable knowledge. It transforms the core improvement question from “What Works” into “What Works for Whom and under What Set of Context Conditions.”
Speaker:
Anthony S. Bryk, President of the Carnegie Foundation for the Advancement of Teaching
Moderator:
Donald J. Peurach, PhD, Professor, University of Michigan School of Education; Senior Fellow, Carnegie Foundation for the Advancement of Teaching
Discussants:
Elizabeth Birr Moje, PhD, Dean, George Herbert Mead Collegiate Professor of Education, and Arthur F. Thurnau Professor School of Education; Faculty Associate in the Institute for Social Research; Latino/a Studies; and the Joint Program in English & Education, University of Michigan
Caren M. Stalburg, MD, MA, Collaborative Lead for Education; Associate Professor of Learning Health Sciences
Tuesday, October 20, 2020
LHS as a Driver of Diversity, Equity, and Inclusion
The October 2020 LHS Collaboratory shared lessons from health advocates working on the frontlines to make healthcare and health more equitable. These thought leaders and do-ers illuminated the transformative power of LHSs - and the diverse and inclusive communities of interest that are collaborating to realize them.
Moderator:
Joshua C. Rubin, J.D., M.B.A., M.P.P., M.P.H., Program Officer, Learning Health System Initiatives
Panelists:
Luis Belén, Chief Executive Officer of the National Health IT Collaborative for the Underserved (NHIT Collaborative)
Danielle Brooks, J.D., Director of Health Equity, Amerihealth Caritas
Melissa S. Creary, Ph.D., M.P.H., Assistant Professor, Department of Health Management and Policy School of Public Health
Thursday, September 17, 2020: Seminar Series Fall Symposium Kick-Off - Academic Medical Centers as Learning Health Systems
The Collaboratory's fall symposium event showcased the LHS experiences of three research-intensive academic centers that have been promoting LHS methods. Distinguished senior colleagues from Duke, Vanderbilt, and Washington University, described and discussed their institutions' work in this area. They discussed strategies employed, investments made, challenges encountered, and successes achieved.
Carol R. Bradford, M.D., M.S., Leslie H. and Abigail S. Wexner Dean's Chair in Medicine, Ohio State University
Presenters:
Kevin B. Johnson, M.D., M.S., F.A.A.P., F.A.C.M.I., Cornelius Vanderbilt Professor & Chair, Department of Biomedical Informatics Professor; Department of Pediatrics Informatician-in-Chief, Vanderbilt University Medical Center
Christopher J. Lindsell, Ph.D., Professor of Biostatistics, Vanderbilt University; Co-director of the HEAlth Data Science, (HEADS) Center, Vanderbilt University
Philip R. O. Payne, Ph.D., F.A.C.M.I., F.A.M.I.A., Janet and Bernard Becker Professor and Director, Institute for Informatics (I2); Associate Dean for Health Information and Data Science, Chief Data Scientist, Washington University School of Medicine
Michael Pencina, Ph.D., Professor of Biostatistics and Bioinformatics, Duke University; Vice Dean for Data Science and Information Technology, Duke University
Eric G. Poon, M.D., M.P.H., Professor of Medicine, Chief Health Information Officer, Duke University
2019 - 2020 Collaboratory Archive
July 29, 2020: LHS/COVID-19 Webinar - International Collaboration to Realize a Global LHS for COVID-19: Lessons from Italy, Spain, and the United States
Charles P. Friedman, Chair, of the Department of Learning Health Sciences, Josiah Macy Jr. Professor of Medical Education at the University of Michigan Medical School, as well as Professor of Information and Public Health; Pablo Rivero, Senior Health and Public Sector Advisor for Everis / NTT Data, Member of the Digital Health Roster of Experts, World Health Organization
Presenters:
COVID-19 in Italian Nursing Homes: A Tragic Past and a Promising Future
Paolo Stocco, Executive Board Member, EuroHealthNet, a not-for- profit partnership of organizations, agencies and statutory bodies working on public health, disease prevention, promoting health, and reducing inequalities
A Globally Applicable Data-Driven Systems Approach to COVID-19
Francisco Ros, President, First-Tech Engineering, former Qualcomm Board Member, and former Secretary of State for Telecommunication and the Information Society in the government of Spain
Global Standards as an Essential Foundation for a Systems Approach
Rebecca Kush, Chief Scientific Officer for Elligo Health Research, President of Catalysis Research, Fellow for Japan’s TRI (Translational Research Center for Medical Innovation), Founder and President Emeritus of CDISC
Commentators:
The Comprehensive, Innovative Approach of Asturias, Spain
Borja Sanchez Garcia, Minister of Science, Innovation and University of the Asturias Principality government, Senior Researcher at the Dairy Research Institute, Scientific Founder of Microviable Therapeutics SL
Patient Perspectives and the Role of Telemedicine
Esther Gil Zorzo, President of Educatec Foundation, Diabetes Coordinator in HM Hospitals, Former President of the FEAED (National Federation for Diabetes Educators) and Member of the Executive Committee of the FEND (Federation European Nurses Diabetes)
Public Health Preparedness and Learning Health Systems
Joshua C. Rubin, Program Officer for Learning Health System Initiatives at the Department of Learning Health Sciences, University of Michigan Medical School
Prospects for the Future
Douglas Van Houweling, Professor Emeritus of Information, School of Information and Professor Emeritus in Service of Learning Health Sciences, University of Michigan Medical School
June 2, 2020: Learning Health Systems in the Time of COVID-19
Speakers: Charles P. Friedman, PhD, Karandeep Singh, MD, MMSc, Allen Flynn, PhD, PharmD, Anne Sales, PhD, RN, and Jody Platt, MPH, PhD
March 19, 2019: Peter Margolis, MD, PhD: Healthier Together: Collaborative networks of patients, clinicians and researchers working together to transform care
May 23, 2018: Managing Value in Health Care through Continuous Learning
Speakers: David F. Massaro, MD, MHCDS, MBA, FACHE, Deputy Chief Medical Officer, Veterans Health Administration, Department of Veterans Affairs
April 24, 2018: Marianne Udow-Phillips, MHSA, Executive Director, Center for Healthcare Research & Transformation (CHRT) and Rajiv Saran, MBBS, MD, MRCP, MS, Director of USRDS Coordinating Center
January 16, 2018: Computable Biomedical Knowledge for a Learning Health System,
Speakers: Harold P. Lehmann, MD, PhD, FACMI, Director of Research and Training, Division of Health Sciences Informatics, Johns Hopkins University School of Medicine and Stephen M. Downs, MD, MS, Director Children's Health Services Research, Indiana University
October 5, 2017: CancerLinQ: A learning health information network for quality
Speaker: Allen Lichter, MD, FASCO, former Chief Executive Officer of the American Society of Clinical Oncology and former Dean of the U-M Medical School
April 27, 2017: Seminar series presentation, Ethical, legal and social implications of learning health systems panel presentation with Andrew Shuman, MD, Kayte Spector-Bagdady, JD, MBioethics, and Nicholson Price, JD, PhD
