Learning Matching Representations for Individualized Organ Transplantation Allocation

Organ transplantation is often the last resort for treating end-stage illness, but the probability of a successful transplantation depends greatly on compatibility between donors and recipients. 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 organ matching using observational data for organ allocations and transplant outcomes. This problem departs from the standard supervised learning setup in that it involves matching the two feature spaces (i.e., donors and recipients), and requires estimating transplant outcomes under counterfactual matches not observed in the data. To address these problems, 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 outcomes for a given donor-recipient feature instance. Experiments on semi-synthetic and real-world datasets show that our model outperforms state-of-art allocation methods and policies executed by human experts. Proceedings of the 24 International Conference on Artificial Intelligence and Statistics (AISTATS) 2021, San Diego, California, USA. PMLR: Volume 130. Copyright 2021 by the author(s). Observational training data for Organ allocation Matching decisions for new patients Good generalization performance Poor generalization performance Figure 1: Donor-recipient matching for organ transplantation. We show an exemplary training data set with two types of donors and recipients (red and blue in either case). In current practice, blue recipients are consistently allocated red organs, and vice versa; hence we only observe blue-red and red-blue matches in training data. Using a supervised learning model f to predict transplant outcomes for alternative allocations would provide accurate predictions for blue-red/red-blue matches but would generalize poorly to blue-blue/red-red matches, making it challenging to learn new allocation rules from the training data.

[1]  D. Goldfarb Donor kidney exchanges. , 2005, The Journal of urology.

[2]  Robert A Montgomery,et al.  Kidney paired donation: fundamentals, limitations, and expansions. , 2011, American journal of kidney diseases : the official journal of the National Kidney Foundation.

[3]  Uri Shalit,et al.  Learning Representations for Counterfactual Inference , 2016, ICML.

[4]  F. Delmonico,et al.  A Report of the Vancouver Forum on the Care of the Live Organ Donor: Lung, Liver, Pancreas, and Intestine Data and Medical Guidelines , 2006, Transplantation.

[5]  Stefan Wager,et al.  Estimation and Inference of Heterogeneous Treatment Effects using Random Forests , 2015, Journal of the American Statistical Association.

[6]  Mattias Ohlsson,et al.  The International Heart Transplant Survival Algorithm (IHTSA): A New Model to Improve Organ Sharing and Survival , 2015, PloS one.

[7]  Arthur E. Hoerl,et al.  Ridge Regression: Biased Estimation for Nonorthogonal Problems , 2000, Technometrics.

[8]  Karl Pearson F.R.S. LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[9]  Max Welling,et al.  Causal Effect Inference with Deep Latent-Variable Models , 2017, NIPS 2017.

[10]  Uri Shalit,et al.  Estimating individual treatment effect: generalization bounds and algorithms , 2016, ICML.

[11]  M. L. de la Mata,et al.  Donor-recipient matching: myths and realities. , 2013, Journal of hepatology.

[12]  Mattias Ohlsson,et al.  Improving prediction of heart transplantation outcome using deep learning techniques , 2018, Scientific Reports.

[13]  Mihaela van der Schaar,et al.  GANITE: Estimation of Individualized Treatment Effects using Generative Adversarial Nets , 2018, ICLR.

[14]  Ali Farhadi,et al.  Unsupervised Deep Embedding for Clustering Analysis , 2015, ICML.

[15]  Mihaela van der Schaar,et al.  Personalized Donor-Recipient Matching for Organ Transplantation , 2016, AAAI.

[16]  Han Zhao,et al.  On Learning Invariant Representations for Domain Adaptation , 2019, ICML.

[17]  A. Müller Integral Probability Metrics and Their Generating Classes of Functions , 1997, Advances in Applied Probability.

[18]  Mihaela van der Schaar,et al.  Deep Counterfactual Networks with Propensity-Dropout , 2017, ArXiv.

[19]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[20]  G. Tutz,et al.  An introduction to recursive partitioning: rationale, application, and characteristics of classification and regression trees, bagging, and random forests. , 2009, Psychological methods.

[21]  Megan Sykes,et al.  Organ transplantation—how much of the promise has been realized? , 2005, Nature Medicine.

[22]  Bertram L Kasiske,et al.  New national allocation policy for deceased donor kidneys in the United States and possible effect on patient outcomes. , 2014, Journal of the American Society of Nephrology : JASN.

[23]  Aidong Zhang,et al.  Representation Learning for Treatment Effect Estimation from Observational Data , 2018, NeurIPS.

[24]  R. Rubin Infection in the Organ Transplant Recipient , 1994 .

[25]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[26]  Mihaela van der Schaar,et al.  Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes , 2017, NIPS.

[27]  Mihaela van der Schaar,et al.  Limits of Estimating Heterogeneous Treatment Effects: Guidelines for Practical Algorithm Design , 2018, ICML.

[28]  Yao Zhang,et al.  Learning Overlapping Representations for the Estimation of Individualized Treatment Effects , 2020, AISTATS.

[29]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[30]  R. Freeman,et al.  Ethical issues in organ transplantation. , 2012, Progress in cardiovascular diseases.