Learning Social Fairness Preferences from Non-Expert Stakeholder Opinions in Kidney Placement

Mukund Telukunta, Sukruth Rao, Gabriella Stickney, Venkata Sriram Siddhardh Nadendla, Casey Canfield
Proceedings of the fifth Conference on Health, Inference, and Learning, PMLR 248:683-695, 2024.

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 algorithmic fairness 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. A novel social fairness preference learning algorithm is proposed based on minimizing social feedback regret computed using a novel logit-based fairness feedback model. The proposed model and learning algorithm are both validated using simulation experiments as well as Prolific data. Public preferences towards group fairness notions in the context of kidney placement have been estimated and discussed in detail. The specific ARP tested in the Prolific survey has been deemed fair by the participants.

Cite this Paper

BibTeX
@InProceedings{pmlr-v248-telukunta24a, title = {Learning Social Fairness Preferences from Non-Expert Stakeholder Opinions in Kidney Placement}, author = {Telukunta, Mukund and Rao, Sukruth and Stickney, Gabriella and Nadendla, Venkata Sriram Siddhardh and Canfield, Casey}, booktitle = {Proceedings of the fifth Conference on Health, Inference, and Learning}, pages = {683--695}, year = {2024}, editor = {Pollard, Tom and Choi, Edward and Singhal, Pankhuri and Hughes, Michael and Sizikova, Elena and Mortazavi, Bobak and Chen, Irene and Wang, Fei and Sarker, Tasmie and McDermott, Matthew and Ghassemi, Marzyeh}, volume = {248}, series = {Proceedings of Machine Learning Research}, month = {27--28 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v248/main/assets/telukunta24a/telukunta24a.pdf}, url = {https://proceedings.mlr.press/v248/telukunta24a.html}, 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 algorithmic fairness 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. A novel social fairness preference learning algorithm is proposed based on minimizing social feedback regret computed using a novel logit-based fairness feedback model. The proposed model and learning algorithm are both validated using simulation experiments as well as Prolific data. Public preferences towards group fairness notions in the context of kidney placement have been estimated and discussed in detail. The specific ARP tested in the Prolific survey has been deemed fair by the participants.} }
Endnote
%0 Conference Paper %T Learning Social Fairness Preferences from Non-Expert Stakeholder Opinions in Kidney Placement %A Mukund Telukunta %A Sukruth Rao %A Gabriella Stickney %A Venkata Sriram Siddhardh Nadendla %A Casey Canfield %B Proceedings of the fifth Conference on Health, Inference, and Learning %C Proceedings of Machine Learning Research %D 2024 %E Tom Pollard %E Edward Choi %E Pankhuri Singhal %E Michael Hughes %E Elena Sizikova %E Bobak Mortazavi %E Irene Chen %E Fei Wang %E Tasmie Sarker %E Matthew McDermott %E Marzyeh Ghassemi %F pmlr-v248-telukunta24a %I PMLR %P 683--695 %U https://proceedings.mlr.press/v248/telukunta24a.html %V 248 %X 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 algorithmic fairness 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. A novel social fairness preference learning algorithm is proposed based on minimizing social feedback regret computed using a novel logit-based fairness feedback model. The proposed model and learning algorithm are both validated using simulation experiments as well as Prolific data. Public preferences towards group fairness notions in the context of kidney placement have been estimated and discussed in detail. The specific ARP tested in the Prolific survey has been deemed fair by the participants.
APA
Telukunta, M., Rao, S., Stickney, G., Nadendla, V.S.S. & Canfield, C.. (2024). Learning Social Fairness Preferences from Non-Expert Stakeholder Opinions in Kidney Placement. Proceedings of the fifth Conference on Health, Inference, and Learning, in Proceedings of Machine Learning Research 248:683-695 Available from https://proceedings.mlr.press/v248/telukunta24a.html.

Related Material