Duncan C McElfresh. I use methods from computer science and operations research for resource allocation and decision making, and I also work on processes for governing and monitoring these systems in applied settings.

Currently I am a Postdoctoral Fellow at the Veterans Health Administration (at Ci2i) and Stanford's Department of Health Policy, and I am a part-time machine learning researcher at Abacus.ai. I hold a PhD in Applied Mathematics (AMSC) from the University of Maryland, College Park.

photo of Duncan

Research

I apply Resource Allocation and market design methods to real settings, including Kidney Exchange and Blood Donation. This work combines theory (such as matching and complexity analysis), empirical methods (such as data-driven simulations), and real-world experiments. To ensure that these systems align with stakeholder interests, I also study AI and Human Decision Making. My academic advisor is John P Dickerson.

Resource Allocation

I apply resource allocation and market design methods to real settings, including Kidney Exchange and Blood Donation.

Kidney Exchange

kidney exchange

Patients with kidney failure have only two options: a lifetime on dialysis, or kidney transplantation. Dialysis is far more expensive and burdensome than transplantation, however donor kidneys are scarce — on average, 20 people die each day in the US while waiting for a transplant. Furthermore, many patients in need of a kidney have willing living donors, but cannot undergo transplantation due to medical incompatibilities.

To address this supply-demand mismatch, kidney exchange allows patients with willing living donors to swap their donors in order to find a compatible (or better) patient-donor match. Formulated as an optimization problem, kidney exchange is NP-hard and APX-hard, though modern exchanges are solvable in a reasonable amount of time.

Robustness to Uncertainty
There are many sources of uncertainty in real kidney exchanges—due to medical, moral, and policy factors. These sources of uncertainty are difficult to characterize, and can severely impact the outcome of an exchange. We investigate techniques from robust optimization to address this problem.

Publications:
  • Duncan C McElfresh, John P Dickerson, Ke Ren, and Hoda Bidkhori. "Distributionally Robust Cycle and Chain Packing With Application To Organ Exchange." 2021 Winter Simulation Conference (WSC).
  • Duncan C McElfresh, Michael Curry, Sarah E Booker, Morgan Stuart, Darren Stewart, Ruthanne Leishman, Tuomas Sandholm, and John P Dickerson. "Who can be matched via kidney exchange?" [abstract]. Am J Transplant. 2021; 21 (suppl 3). Abstract presented as a poster at the 2021 American Tranpsplant Congress (ATC).
  • Duncan C McElfresh, Michael Curry, Sarah E Booker, Morgan Stuart, Darren Stewart, Ruthanne Leishman, Tuomas Sandholm, and John P Dickerson. "Improving Policy-constrained Kidney Exchange Via Pre-screening." Am J Transplant. 2021; 21 (suppl 3). Abstract presented as a talk at the 2021 American Tranpsplant Congress (ATC).
  • McElfresh, Duncan C, Michael Curry, Tuomas Sandholm, and John P Dickerson, "Improving Policy-Constrained Kidney Exchange via Pre-Screening.” Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems (NeurIPS), 2020.
  • Bidkhori, Hoda, John P Dickerson, Ke Ren, and Duncan C McElfresh. “Kidney exchange with Inhomogeneous Edge Existence Uncertainty.” Conference on Uncertainty in Artificial Intelligence (UAI). 2020.
  • McElfresh, Duncan C, Hoda Bidkhori, and John P Dickerson, "Scalable Robust Kidney Exchange.” Conference on Artificial Intelligence (AAAI), 2019.
Fairness in Kidney Exchange

How can we prioritize marginalized patients, without severely impacting the overall exchange? We study several different methods for enforcing this notion of fairness, and demonstrate their effects on data collected from real exchanges.

Publications:
  • McElfresh, Duncan C, and John P Dickerson, "Balancing lexicographic fairness and a utilitarian objective with application to kidney exchange." Conference on Artificial Intelligence (AAAI), 2018.
Ethics and Kidney Exchange

Designing a kidney exchange program requires input from medical professionals, policymakers, computer scientists, and ethicists. A "good" program should be both technically- and morally-sound — however technical experts (e.g., computer scientists) and stakeholders (e.g., medical professionals) often work independently. We propose a formal division of labor between technical experts and stakeholders, and outline a framework through which these experts can collaborate. Through this framework we analyze existing kidney exchange programs and survey the technical literature on kidney exchange algorithms. We identify areas for future collaboration between technical experts and stakeholders.

Relevant work:
  • Presentation: McElfresh, Duncan C, Patricia Mayer, Gabriel Schnickel, and John P Dickerson. "Ok Google: Who Gets the Kidney?": Artificial Intelligence and Transplant Algorithms. Panel presentation and discussion at the annual meeting of the American Society of Bioethics and Humanities (ASBH), Anaheim, CA. (slides)
Immunosuppression

Recent advances in immunosuppression treatments allow some patients to receive a kidney transplant from donors who are otherwise medically incompatible. We develop a theoretical model for this setting, and provide an optimization framework for a wide variety of objectives (e.g., prioritizing certain types of patients or transplants). Simulations indicate that even a small number of immunosuppressants (10 or 20) can double the number of transplants facilitated by real-sized exchanges with hundreds of patients.

Publications:
  • Haris Aziz, Ágnes Cseh, John P Dickerson, and Duncan C McElfresh. “Optimal Kidney Exchange with Immunosuppressants.” Conference on Artificial Intelligence (AAAI). 2021.

Blood Donation

blood matching

Blood is a scarce resource that can save the lives of those in need, and managing the blood supply chain has been a topic of research for decades. We consider an aspect of the blood supply chain that is seldom addressed by the literature: coordinating a network of donors to meet demand from a network of recipients.

In a collaboration with Facebook, we deployed the first large-scale algorithmic system for matching blood donors with recipients. We focused on the Facebook Blood Donation Tool, a platform that connects prospective blood donors with nearby recipients. There are many objectives in this setting, including: increasing the number of blood donations, treating recipients fairly, and respecting user preferences. To formalize these goals we developed an online matching framework, and matching policies for automatic donor notification. Both simulations and a fielded experiment demonstrate that our methods increase expected donation rates by 5% which—when generalized to the entire Blood Donation Tool—corresponds to an increase in tens of thousands of donations every few months.

Relevant work:
  • McElfresh, Duncan C, Christian Kroer, Sergey Pupyrev, Eric Sodomka, Karthik Abinav Sankararaman, Zack Chauvin, Neil Dexter, John P Dickerson. “Matching Algorithms for Blood Donation” Under review at PNAS. An earlier version appeared at The 21st ACM Conference on Economics and Computation (EC), 2020.
  • Poster and Presentation: McElfresh, Duncan C, Christian Kroer, Sergey Pupyrev, Eric Sodomka, John P Dickerson. “Matching Algorithms for Blood Donation.” Workshop on Mechanism Design for Social Good MD4SG, 2019.

AI and Human Decision Making

AI is increasingly used to influence, or make, important decisions in a wide range of domains, including medicine, education, criminal justice, and financial services. Indeed, two key examples are kidney exchange and blood donation. I study the interaction between stakeholders and algorithmic decision tools, with an eye toward developing responsible decision support tools.

Perceptions of algorithmic "fairness"

kidney exchange

AI and ML researchers have proposed several mathematical definitions of fairness, however it is not clear if stakeholders understand or agree with these notions. We develop and validate a comprehension score to measure peoples’ understanding of mathematical fairness. Using a hypothetical decision scenario related to hiring, we translate several mathematical fairness definitions into “rules” that a hiring manager must follow. Using our comprehension score, we find that most people do not understand these rules, and those who do often disagree with them. This raises questions about the usefulness of algorithmic fairness: can an AI system be truly “fair” if its stakeholders do not understand its behavior?

  • Saha, Debjani, Candice Schumann, Duncan C McElfresh, John P Dickerson, Michelle L Mazurek and Michael Carl Tschantz. “Measuring Non-Expert Comprehension of Machine Learning Fairness Metrics.” Proceedings of the Thirty-seventh International Conference on Machine Learning (ICML). 2020.
  • Saha, Debjani, Candice Schumann, Duncan C McElfresh, John P Dickerson, Michelle L Mazurek and Michael Carl Tschantz. “Human Comprehension of Fairness in Machine Learning." AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES), 2020.

Understanding Indecision

kidney exchange

Many modern AI methods, are guided by models of stake- holder preferences, which are often learned through observed decisions (such as product purchases) or through hypothetical decisions (e.g., surveys). There are many cases where stakeholders may be unwilling to express a preference: for example, if more information is needed to arrive at a decision, or of all available options are bad; in these cases we say they are indecisive. Drawing from moral philosophy and psychology, we develop a class of indecision models, which can be fit to observed data; in two survey studies we that indecision is common, and several causes of indecision are plausible. This raises many questions for the use of AI in decision making: from a theoretical perspective, how should we aggregate indecisive voters if indecision has multiple meanings? From an empirical perspective, how can we identify an indecisive agent, and what characteristics of a decision scenario lead to indecision?

  • McElfresh, Duncan C, Lok Chan, Kenzie Doyle, Walter Sinnott-Armstrong, Vincent Conitzer, Jana Schaich Borg,John P Dickerson. “Indecision Modeling.” Conference on Artificial Intelligence (AAAI). 2021. (poster)

AI-Influenced Decision Making

Using a survey study we simulate the effect of an AI tool on decision making: we suggest random predictions of participant preferences, and we attribute this prediction to an "AI system," or a human "expert." We find that participants follow these prediction—even though they are random— both when the predictions are attributed to “AI”, and to "experts" (compared with a control group that receives no prediction). This has serious implications for AI in decision making: if random decision support can influence a stakeholder’s behavior, it is easy to imagine that adversarial AI systems can easily manipulate a stakeholder’s decisions. Furthermore, if AI tools are both trained on and influence stakeholders’ behavior, it is difficult to define what a "correct" decision is.

  • Chan, Lok, Kenzie Doyle, Duncan C McElfresh, Vincent Conitzer, John P Dickerson, Jana Schaich Borg and Walter Sinnott-Armstrong. “Artificial Artificial Intelligence: Measuring Influence of AI "Assessments" on Moral Decision-Making.” AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES), 2020.

Publications

"Top Tier" Conference Publications.

𝔸 = alphabetical author ordering.

    2021

  • McElfresh, Duncan C, Lok Chan, Kenzie Doyle, Walter Sinnott-Armstrong, Vincent Conitzer, Jana Schaich Borg,John P Dickerson. “Indecision Modeling.” Conference on Artificial Intelligence (AAAI). 2021. (poster)
  • (𝔸) Haris Aziz, Ágnes Cseh, John P Dickerson, and Duncan C McElfresh. “Optimal Kidney Exchange with Immunosuppressants.” Conference on Artificial Intelligence (AAAI). 2021.
  • 2020

  • McElfresh, Duncan C, Michael Curry, Tuomas Sandholm, and John P Dickerson, "Improving Policy-Constrained Kidney Exchange via Pre-Screening.” Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems (NeurIPS), 2020.
  • Saha, Debjani, Candice Schumann, Duncan C McElfresh, John P Dickerson, Michelle L Mazurek and Michael Carl Tschantz. “Measuring Non-Expert Comprehension of Machine Learning Fairness Metrics.” Proceedings of the Thirty-seventh International Conference on Machine Learning (ICML). 2020.
  • McElfresh, Duncan C, Christian Kroer, Sergey Pupyrev, Eric Sodomka, Karthik Abinav Sankararaman, Zack Chauvin, Neil Dexter, John P Dickerson. “Matching Algorithms for Blood Donation” Under review at PNAS. An earlier version appeared at The 21st ACM Conference on Economics and Computation (EC), 2020.
  • (𝔸) Bidkhori, Hoda, John P Dickerson, Ke Ren, and Duncan C McElfresh. “Kidney exchange with Inhomogeneous Edge Existence Uncertainty.” Conference on Uncertainty in Artificial Intelligence (UAI). 2020.
  • Chan, Lok, Kenzie Doyle, Duncan C McElfresh, Vincent Conitzer, John P Dickerson, Jana Schaich Borg and Walter Sinnott-Armstrong. “Artificial Artificial Intelligence: Measuring Influence of AI "Assessments" on Moral Decision-Making.” AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES), 2020.
  • Saha, Debjani, Candice Schumann, Duncan C McElfresh, John P Dickerson, Michelle L Mazurek and Michael Carl Tschantz. “Human Comprehension of Fairness in Machine Learning." AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES), 2020.
  • 2019

  • McElfresh, Duncan C, Hoda Bidkhori, and John P Dickerson, "Scalable Robust Kidney Exchange.” Conference on Artificial Intelligence (AAAI), 2019.
  • 2018

  • McElfresh, Duncan C, and John P Dickerson, "Balancing lexicographic fairness and a utilitarian objective with application to kidney exchange." Conference on Artificial Intelligence (AAAI), 2018.
  • 2012

  • Bach, Jörg-Hendrik, Arne-Freerk Meyer, Duncan McElfresh, Jörn Anemüller, "Automatic classification of audio data using nonlinear neural response models." IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012.
Other Publications
  • Duncan C McElfresh, Katherine Bracamontes, Patricia Mayer. "Universal Ethics Evaluation of ICU Patients: A Model." Journal of Hospital Ethics (JoHE). Vol. 8 Num. 3, 2022.
  • D.C. McElfresh, K. Bracamontes, P. Mayer, “Universal Ethics Evaluation of ICU Patients: A Model.” Journal of Hospital Ethics (JoHE). Vol. 8 Num. 3, 2022
  • Duncan C McElfresh, John P Dickerson, Ke Ren, and Hoda Bidkhori. "Distributionally Robust Cycle and Chain Packing With Application To Organ Exchange." 2021 Winter Simulation Conference (WSC), 2021.
  • Duncan C McElfresh, Michael Curry, Sarah E Booker, Morgan Stuart, Darren Stewart, Ruthanne Leishman, Tuomas Sandholm, and John P Dickerson. "Who can be matched via kidney exchange?" [abstract]. Am J Transplant. 2021; 21 (suppl 3). Abstract presented as a poster at the 2021 American Tranpsplant Congress (ATC).
  • Duncan C McElfresh, Michael Curry, Sarah E Booker, Morgan Stuart, Darren Stewart, Ruthanne Leishman, Tuomas Sandholm, and John P Dickerson. "Improving Policy-constrained Kidney Exchange Via Pre-screening." Am J Transplant. 2021; 21 (suppl 3). Abstract presented as a talk at the 2021 American Tranpsplant Congress (ATC).
  • Nanda, Vedant, Duncan C McElfresh, and John P Dickerson. "Learning to Explain Machine Learning." Workshop on Operationalizing Human-centered Perspectives in Explainable AI (at CHI’21).
  • McElfresh, Duncan C, Samuel Dooley, Charles Cui, Kendra Griesman, Weiqin Wang, Tyler Will, Neil Sehgal and John Dickerson. “Can an Algorithm be My Healthcare Proxy?” 2020 International Workshop on Health Intelligence (at AAAI'20). (Workshop Paper.)
  • McElfresh, Duncan C, Christian Kroer, Sergey Pupyrev, Eric Sodomka, John P Dickerson. “Matching Algorithms for Blood Donation.” Workshop on Mechanism Design for Social Good MD4SG'19. (Poster and Presentation.)
  • McElfresh, Duncan C. “A Framework for Technically- and Morally-Sound AI.” AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES). 2019 (Student program and poster.)
  • McElfresh, Duncan C, "Triplet exciton transport in the benzophenone-fluorene-naphthalene molecule." Master's Thesis, Colorado School of Mines, 2013.

Service

Peer Review
  • Journal Reviewer: EJOR, JAIR, TEAC
  • Senior Program Committee: AAMAS ('22)
  • Program Committee: NeurIPS (‘20, ‘21, ‘22), AAAI (‘20, ‘21, ‘23), EAAMO (‘21, ‘22)
  • Poster Session Co-Organizer: Workshop on Mechanism Design for Social Good (MD4SG'20) (‘20)
  • Proposal Reviewer: ACM/EC Global Challenges in Economics and Computation (GCEC) (‘20)
IBM Watson AI XPrize (link):
  • Red Judge. Helped teams prepare for the semifinal review of the IBM Watson AI XPrize competition. (2018-2019)
  • Independent Observer. Attended site visits to validate claims made by semifinalist teams. (2019-2020)
Organization and Mentorship
  • Mentor, Statistics for Social Good, Stanford University (link). (2022-)
  • Working Group Co-organizer, Mechanism Design for Social Good (MD4SG) Working Group on Algorithms, Law, and Policy. (2020-2021)
  • Working Group Co-organizer, Mechanism Design for Social Good (MD4SG) Working Group on Bias, Discrimination, and Fairness. (2019-2020)
  • Student Representative. AMSC Student Council. (2018-2019)
  • Site Coordinator & Mentor. Site Coordinator, Girls Excelling in Math and Science (GEMS) of Prince George’s County, MD. (link) (2017-2018)