Category: Conferences

We had a great time at the Symposium on Bridging Disparities in Health Care Using Artificial Intelligence​ at the end of 2024. The conference consisted of 60 Presenters/Attendees representing both academia (computer science, bioethics, philosophy, psychology, medicine, theology) and industry (health care, supply chain, OPOs, UNOS)​. In particular, we were intrigued by the discussion on how to go from principles around AI ethics (e.g., privacy, non-discrimination, autonomy) to practice. This requires systems for ongoing monitoring and evaluation.

We had participants from SLU, Missouri S&T, UNOS, Washington U., NYU, Vanderbilt, Yale, Johns Hopkins, Duquesne, U. of Rochester, U. of Texas, U. of North Carolina-Charlotte, U. of Missouri-Kansas City, and Kansas City University of Medicine and Biosciences. ​

The day consisted of 3 plenary lectures, 2 in-depth panels, and 11 paper presentations​. It was a great day of networking and education for those in attendance. Thank you to all of those who attended and supported our work. We can’t wait for a great new year!

We had a great time at the the Conference on Health, Inference, and Learning (CHIL) this year. CHIL aims to include clinicians and researchers from both industry and academia who specialize in machine learning, health policy, causality, fairness, and other related fields. The conference aims to foster insightful discussions on innovative and emerging ideas, fostering collaboration and dialogue. Different presentations on fairness in regards to algorithms were found to be very helpful toward our project.

Dr. Nadendla (Associate Professor) and Mukund Telukunta (PhD Student) presented “Learning Social Fairness Preferences from Non-Expert Stakeholder Opinions in Kidney Placement”.

Abstract: Modern kidney placement incorporates several intelligent recommendation systems which exhibit social discrimination due to biases inherited from training data. Although initial attempts were made in the literature to study biases in kidney placement, these methods replace true outcomes with surgeons’ decisions due to the long delays involved in recording such outcomes reliably. However, the replacement of true outcomes with surgeons’ decisions disregards expert stakeholders’ biases as well as social opinions of other stakeholders who do not possess medical expertise. This paper alleviates the latter concern and designs a novel fairness feedback survey to evaluate an acceptance rate predictor (ARP) that predicts a kidney’s acceptance rate in a given kidney-match pair. The survey is launched on Prolific, a crowdsourcing platform, and public opinions are collected from 85 anonymous crowd participants. Our results show that the public participants deem “accuracy equality” as the preferred notion of fairness across all sensitive features. Moreover, the specific ARP tested in the Prolific survey has been deemed fair by the participants.

Our first time attending the Association of Organ Procurement Organizations (AOPO) annual meeting in San Antonio, TX was a success. Casey Canfield presented a poster on “Increasing Kidney Utilization Using Artificial Intelligence Decision Support” and talked with many OPOs about our proposal for integrating AI into their workflow. We look forward to continuing to work with the OPO community!

The Association of Organ Procurement Organizations 41st annual meeting will be held in San Antonio, Texas from June 24th – 26th. The AOPO Annual Meeting brings organ and tissue procurement professionals together to share ideas, create connections, and educate the donation and transplant community.

Casey Canfield will have a poster titled “Increasing Kidney Utilization Using Artificial Intelligence Decision Support for Accelerated Placement” on display in the foyer outside the Ballroom. She will be presenting it on Wednesday (6/26) from 10:30-11am. Be sure to stop by to ask her any questions and see how you can get involved!

We learned a lot in Philadelphia at ATC. The team presented 3 posters, which included work funded by the National Science Foundation and Mid-America Transplant. Rachel Dzieran’s poster on “Fuzzy Associative Memory and Deep Learning Network Model Interface with Transplant Surgeon in Assessing Hard-to-Place Kidneys for Use in Digital Twin Model” was awarded a Best of Show ribbon!

We also got to network with our colleagues in St. Louis at Saint Louis University and Mid-America Transplant as well as make new connections.

We will be presenting about this research at the American Transplant Congress (ATC) in Philadelphia, PA from June 1-5. ATC brings together the transplant industry to share the latest science, clinical care, ethics, and more. 

Saturday, June 1, 5:30-7pm at the Poster Hall, Exhibit Hall A on the second level:

• Richard Threlkeld will be presenting “Investigation of Racial and Ethnic Bias in Kidney Non-Utilization Decisions Using the Deceased Donor Organ Allocation Model”
• Rachel Dzieran will be presenting “Fuzzy Associative Memory and Deep Learning Network Model Interface with Transplant Surgeon in Assessing Hard-to-Place Kidneys for Use in Digital Twin Model”.

Tuesday, June 4, 9:15-10am at the Poster Hall, Exhibit Hall A on the second level:

• Cihan Dagli will be presenting “AI-Model Interpretation for Deceased Donor Kidney Acceptance Practices”

The 21st Annual Conference on Systems Engineering Research (CSER 2024) pushed the boundaries of systems engineering, from the digital engineering transformation to the seamless integration of artificial intelligence within systems. Kummer Innovation and Entrepreneurship Doctoral Fellow Rachel Dzieran attended CSER in Tucson AZ on March 25-27.

She presented the paper, “System-of-Systems Approach for Improving Quality of Kidney Transplant Decision-Making Support for Transplant Surgeons”, authored by Rachel Dzieran, Dr. Lirim Ashiku, Dr. Richard Threlkeld, Dr. Cihan Dagli, and Dr. Robert Marley. The paper is about the creation of a meta-architecture for software that could be developed in the future for dissemination of this research once it is fully completed. The objective is to build a Transplant Surgeon specific model for decision-making at the transplant center.