Learning Matching Representations for Individualized Organ Transplantation Allocation

Can Xu, Ahmed Alaa, Ioana Bica, Brent Ershoff, Maxime Cannesson, Mihaela van der Schaar
Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR 130:2134-2142, 2021.

Abstract

Organ transplantation can improve life expectancy for recipients, but the probability of a successful transplant depends on the compatibility between donor and recipient features. Current medical practice relies on coarse rules for donor-recipient matching, but is short of domain knowledge regarding the complex factors underlying organ compatibility. In this paper, we formulate the problem of learning data-driven rules for donor-recipient matching using observational data for organ allocations and transplant outcomes. This problem departs from the standard supervised learning setup in that it involves matching two feature spaces (for donors and recipients), and requires estimating transplant outcomes under counterfactual matches not observed in the data. To address this problem, we propose a model based on representation learning to predict donor-recipient compatibility—our model learns representations that cluster donor features, and applies donor-invariant transformations to recipient features to predict transplant outcomes under a given donor-recipient feature instance. Experiments on several semi-synthetic and real-world datasets show that our model outperforms state-of-art allocation models and real-world policies executed by human experts.

Cite this Paper

BibTeX
@InProceedings{pmlr-v130-xu21e, title = { Learning Matching Representations for Individualized Organ Transplantation Allocation }, author = {Xu, Can and Alaa, Ahmed and Bica, Ioana and Ershoff, Brent and Cannesson, Maxime and van der Schaar, Mihaela}, booktitle = {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics}, pages = {2134--2142}, year = {2021}, editor = {Banerjee, Arindam and Fukumizu, Kenji}, volume = {130}, series = {Proceedings of Machine Learning Research}, month = {13--15 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v130/xu21e/xu21e.pdf}, url = {https://proceedings.mlr.press/v130/xu21e.html}, abstract = { Organ transplantation can improve life expectancy for recipients, but the probability of a successful transplant depends on the compatibility between donor and recipient features. Current medical practice relies on coarse rules for donor-recipient matching, but is short of domain knowledge regarding the complex factors underlying organ compatibility. In this paper, we formulate the problem of learning data-driven rules for donor-recipient matching using observational data for organ allocations and transplant outcomes. This problem departs from the standard supervised learning setup in that it involves matching two feature spaces (for donors and recipients), and requires estimating transplant outcomes under counterfactual matches not observed in the data. To address this problem, we propose a model based on representation learning to predict donor-recipient compatibility—our model learns representations that cluster donor features, and applies donor-invariant transformations to recipient features to predict transplant outcomes under a given donor-recipient feature instance. Experiments on several semi-synthetic and real-world datasets show that our model outperforms state-of-art allocation models and real-world policies executed by human experts. } }
Endnote
%0 Conference Paper %T Learning Matching Representations for Individualized Organ Transplantation Allocation %A Can Xu %A Ahmed Alaa %A Ioana Bica %A Brent Ershoff %A Maxime Cannesson %A Mihaela van der Schaar %B Proceedings of The 24th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2021 %E Arindam Banerjee %E Kenji Fukumizu %F pmlr-v130-xu21e %I PMLR %P 2134--2142 %U https://proceedings.mlr.press/v130/xu21e.html %V 130 %X Organ transplantation can improve life expectancy for recipients, but the probability of a successful transplant depends on the compatibility between donor and recipient features. Current medical practice relies on coarse rules for donor-recipient matching, but is short of domain knowledge regarding the complex factors underlying organ compatibility. In this paper, we formulate the problem of learning data-driven rules for donor-recipient matching using observational data for organ allocations and transplant outcomes. This problem departs from the standard supervised learning setup in that it involves matching two feature spaces (for donors and recipients), and requires estimating transplant outcomes under counterfactual matches not observed in the data. To address this problem, we propose a model based on representation learning to predict donor-recipient compatibility—our model learns representations that cluster donor features, and applies donor-invariant transformations to recipient features to predict transplant outcomes under a given donor-recipient feature instance. Experiments on several semi-synthetic and real-world datasets show that our model outperforms state-of-art allocation models and real-world policies executed by human experts.
APA
Xu, C., Alaa, A., Bica, I., Ershoff, B., Cannesson, M. & van der Schaar, M.. (2021). Learning Matching Representations for Individualized Organ Transplantation Allocation . Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 130:2134-2142 Available from https://proceedings.mlr.press/v130/xu21e.html.

Related Material