{"type":"ScholarlyArticle","title":"Forecasting Patient Outcomes in Kidney Exchange","authors":[{"name":"Naveen Durvasula","slug":"naveen-durvasula","given":"Naveen","family":"Durvasula","affiliation":"University of California , Berkeley"},{"name":"Aravind Srinivasan","slug":"aravind-srinivasan","given":"Aravind","family":"Srinivasan","affiliation":"University of Maryland , College Park"},{"name":"John Dickerson","slug":"john-dickerson","given":"John","family":"Dickerson","affiliation":"University of Maryland , College Park"}],"abstract":"Kidney exchanges allow patients with end-stage renal disease to find a lifesaving living donor by way of an organized market.  However, not all patients are equally easy to match, nor are all donor organs of equal quality---some patients are matched within weeks, while others may wait for years with no match offers at all. We propose the first decision-support tool for kidney exchange that takes as input the biological features of a patient-donor pair, and returns (i) the probability of being matched prior to expiry, and (conditioned on a match outcome), (ii) the waiting time for and (iii) the organ quality of the matched transplant.  This information may be used to inform medical and insurance decisions. We predict all quantities (i, ii, iii) exclusively from match records that are readily available in any kidney exchange using a quantile random forest approach. To evaluate our approach, we developed two state-of-the-art realistic simulators based on data from the United Network for Organ Sharing that sample from the training and test distribution for these learning tasks---in our application these distributions are distinct. We analyze distributional shift through a theoretical lens, and show that the two distributions converge as the kidney exchange nears steady-state. We then show that our approach produces clinically-promising estimates using simulated data. Finally, we show how our approach, in conjunction with tools from the model explainability literature, can be used to calibrate and detect bias in matching policies.","doi":"10.24963/ijcai.2022/701","url":"https://ijcai.org/proceedings/2022/701","pdf":"https://ijcai.org/proceedings/2022/0701.pdf","markdown":"https://ijcai.org/proceedings/2022/701.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/701","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Research Papers","track":"AI for Good","number":701,"pages":{"first":5052,"last":5058},"keywords":["Agent-based and Multi-agent Systems: Economic Paradigms, Auctions and Market-Based Systems","Multidisciplinary Topics and Applications: Health and Medicine","AI Ethics, Trust, Fairness: Explainability and Interpretability"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987144","length_sec":84,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985287","length_sec":718,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Agarwal et al., 2019] Nikhil Agarwal, Itai Ashlagi, Ed- uardo Azevedo, Clayton R Featherstone, and Ömer Karad- uman. Market failure in kidney exchange. American Eco- nomic Review, 109(11):4026-70, 2019.","title":"Market failure in kidney exchange","authors":"Nikhil Agarwal, Itai Ashlagi, Eduardo Azevedo, Clayton R Featherstone, Ömer Karaduman","year":"2019","venue":"American Economic Review","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Anderson et al., 2017] Ross Anderson, Itai Ashlagi, David Gamarnik, and Yash Kanoria. Efficient dynamic barter ex- change. Operations Research, 65(6):1446-1459, 2017.","title":"Efficient dynamic barter exchange","authors":"Ross Anderson, Itai Ashlagi, David Gamarnik, Yash Kanoria","year":"2017","venue":"Operations Research","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ashlagi and Roth, 2014] Itai Ashlagi and Alvin E Roth. Free riding and participation in large scale, multi-hospital kidney exchange. Theoretical Economics, 9(3):817-863, 2014.","title":"Free riding and participation in large scale, multi-hospital kidney exchange","authors":"Itai Ashlagi, Alvin E Roth","year":"2014","venue":"Theoretical Economics","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Ashlagi and Roth, 2021] Itai Ashlagi and Alvin Roth. Kid- ney exchange: an operations perspective. Management Science, 2021.","title":"Itai Ashlagi and Alvin Roth. Kidney exchange: an operations perspective","authors":"Roth Ashlagi","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Biró et al., 2019] Péter Biró, Bernadette Haase-Kromwijk, Tommy Andersson, Eyjólfur Ingi Ásgeirsson, Tatiana Bal- tesová, Ioannis Boletis, Catarina Bolotinha, Gregor Bond, Georg Böhmig, Lisa Burnapp, et al. Building kidney ex- change programmes in europe-an overview of exchange practice and activities. Transplantation, 103(7):1514, 2019.","title":"Building kidney exchange programmes in europe-an overview of exchange practice and activities","authors":"Péter Biró, Bernadette Haase-Kromwijk, Tommy Andersson, Eyjólfur Ingi Ásgeirsson, Tatiana Baltesová, Ioannis Boletis, Catarina Bolotinha, Gregor Bond, Georg Böhmig, Lisa Burnapp","year":"2019","venue":"Transplantation","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cox, 1992] David R Cox. Regression models and life- tables. In Breakthroughs in Statistics, pages 527-541. Springer, 1992.","title":"Regression models and lifetables","authors":"David R Cox","year":"1992","venue":"Breakthroughs in Statistics","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dickerson and Sandholm, 2015] John P. Dickerson and Tuomas Sandholm. FutureMatch: Combining human value judgments and machine learning to match in dy- namic environments. In AAAI Conference on Artificial In- telligence (AAAI), pages 622-628, 2015.","title":"FutureMatch: Combining human value judgments and machine learning to match in dynamic environments","authors":"John P Dickerson, Tuomas Sandholm","year":"2015","venue":"AAAI Conference on Artificial Intelligence (AAAI)","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dickerson et al., 2014] John P. Dickerson, Ariel D. Procac- cia, and Tuomas Sandholm. Price of fairness in kidney exchange. In International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), pages 1013- 1020, 2014.","title":"Price of fairness in kidney exchange","authors":"John P Dickerson, Ariel D Procaccia, Tuomas Sandholm","year":"2014","venue":"International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hinton and Roweis, 2002] Geoffrey Hinton and Sam T Roweis. Stochastic neighbor embedding. In Conference on Neural Information Processing Systems (NeurIPS), vol- ume 15, pages 833-840. Citeseer, 2002.","title":"Stochastic neighbor embedding","authors":"Roweis Hinton, Geoffrey Hinton, Sam T Roweis","year":"2002","venue":"Conference on Neural Information Processing Systems (NeurIPS)","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Levey et al., 1999] Andrew S Levey, Juan P Bosch, Ju- lia Breyer Lewis, Tom Greene, Nancy Rogers, and David Roth. A more accurate method to estimate glomerular fil- tration rate from serum creatinine: a new prediction equa- tion. Annals of internal medicine, 130(6):461-470, 1999.","title":"A more accurate method to estimate glomerular filtration rate from serum creatinine: a new prediction equation","authors":"Juan P Andrew S Levey, Julia Breyer Bosch, Tom Lewis, Nancy Greene, David Rogers, Roth","year":"1999","venue":"Annals of internal medicine","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lundberg and Lee, 2017] Scott Lundberg and Su-In Lee. A unified approach to interpreting model predictions. In Conference on Neural Information Processing Systems (NeurIPS), 2017.","title":"A unified approach to interpreting model predictions","authors":"Lee ; Lundberg, Scott Lundberg, Su-In Lee","year":"2017","venue":"Conference on Neural Information Processing Systems (NeurIPS)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Lundberg et al., 2018] Scott M Lundberg, Gabriel G Erion, and Su-In Lee. Consistent individualized feature attribu- tion for tree ensembles. arXiv preprint arXiv:1802.03888, 2018.","title":"Consistent individualized feature attribution for tree ensembles","authors":"Scott M Lundberg, Su-In Gabriel G Erion, Lee","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lundberg et al., 2020] Scott M Lundberg, Gabriel Erion, Hugh Chen, Alex DeGrave, Jordan M Prutkin, Bala Nair, Ronit Katz, Jonathan Himmelfarb, Nisha Bansal, and Su- In Lee. From local explanations to global understanding with explainable AI for trees. Nature machine intelligence, 2(1):56-67, 2020.","title":"From local explanations to global understanding with explainable AI for trees","authors":"Gabriel Scott M Lundberg, Hugh Erion, Alex Chen, Degrave, Bala Jordan M Prutkin, Ronit Nair, Jonathan Katz, Nisha Himmelfarb, Su-In Bansal, Lee","year":"2020","venue":"Nature machine intelligence","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Massart, 1990] Pascal Massart. The tight constant in the Dvoretzky-Kiefer-Wolfowitz inequality. The Annals of Probability, pages 1269-1283, 1990.","title":"The tight constant in the Dvoretzky-Kiefer-Wolfowitz inequality","authors":"Pascal Massart","year":"1990","venue":"The Annals of Probability","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Massie et al., 2016] Allan B Massie, Joseph Leanza, LM Fahmy, EKH Chow, Niraj M Desai, X Luo, EA King, MG Bowring, and DL Segev. A risk index for living donor kidney transplantation. American Journal of Transplantation, 16(7):2077-2084, 2016.","title":"A risk index for living donor kidney transplantation","authors":"Joseph Allan B Massie, L M Leanza, Fahmy, Chow, M Niraj, X Desai, Luo, King, Bowring, Segev","year":"2016","venue":"American Journal of Transplantation","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Meinshausen and Ridgeway, 2006] Nicolai Meinshausen and Greg Ridgeway. Quantile regression forests. Journal of Machine Learning Research, 7(6), 2006.","title":"Quantile regression forests","authors":"Nicolai Meinshausen, Greg Ridgeway","year":"2006","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Neuen et al., 2013] Brendon L Neuen, Georgina E Taylor, Alessandro R Demaio, and Vlado Perkovic. Global kidney disease. The Lancet, 382(9900):1243, 2013.","title":"Global kidney disease","authors":"Georgina E Brendon L Neuen, Alessandro R Taylor, Vlado Demaio, Perkovic","year":"2013","venue":"The Lancet","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[OPTN, 2021] OPTN. Organ Procurement and Transplan- tation Network (OPTN) policies, 2021. Policy 13: Kid- ney Paired Donation (KPD). Available online: https://optn. transplant.hrsa.gov/media/1200/optn policies.pdf.","title":"OPTN. Organ Procurement and Transplantation Network (OPTN) policies","authors":"Optn","year":"2021","venue":null,"doi":null,"url":"https://optn.transplant.hrsa.gov/media/1200/optnpolicies.pdf","internal_url":null},{"position":19,"raw":"[Rao et al., 2009] Panduranga S Rao, Douglas E Schaubel, Mary K Guidinger, Kenneth A Andreoni, Robert A Wolfe, Robert M Merion, Friedrich K Port, and Randall S Sung. A comprehensive risk quantification score for deceased donor kidneys: the kidney donor risk index. Transplan- tation, 88(2):231-236, 2009.","title":"A comprehensive risk quantification score for deceased donor kidneys: the kidney donor risk index","authors":"Douglas E Panduranga S Rao, Mary K Schaubel, Kenneth A Guidinger, Robert A Andreoni, Robert M Wolfe, Friedrich K Merion, Randall S Port, Sung","year":"2009","venue":"Transplantation","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Roth et al., 2004] Alvin Roth, Tayfun Sönmez, and Utku Ünver. Kidney exchange. Quarterly Journal of Eco- nomics, 119(2):457-488, 2004.","title":"Alvin Roth, Tayfun Sönmez, and Utku Ünver","authors":"Roth","year":"2004","venue":"Quarterly Journal of Economics","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Roth et al., 2005a] Alvin Roth, Tayfun Sönmez, and Utku Ünver. A kidney exchange clearinghouse in New England. American Economic Review, 95(2):376-380, 2005.","title":"A kidney exchange clearinghouse in New England","authors":"Roth","year":"2005","venue":"American Economic Review","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Roth et al., 2005b] Alvin Roth, Tayfun Sönmez, and Utku Ünver. Pairwise kidney exchange. Journal of Economic Theory, 125(2):151-188, 2005.","title":"Pairwise kidney exchange","authors":"Roth","year":"2005","venue":"Journal of Economic Theory","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Saidman et al., 2006] Susan L. Saidman, Alvin Roth, Tay- fun Sönmez, Utku Ünver, and Frank Delmonico. Increas- ing the opportunity of live kidney donation by match- ing for two and three way exchanges. Transplantation, 81(5):773-782, 2006.","title":"Increasing the opportunity of live kidney donation by matching for two and three way exchanges","authors":"Susan L Saidman, Alvin Roth, Tayfun Sönmez, Utku Ünver, Frank Delmonico","year":"2006","venue":"Transplantation","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Santos et al., 2015] Alfonso H Santos, Michael J Casey, Xuerong Wen, Ivan Zendejas, Shehzad Rehman, Karl L Womer, and Kenneth A Andreoni. Survival with dialy- sis versus kidney transplantation in adult hemolytic uremic syndrome patients: A fifteen-year study of the waiting list. Transplantation, 99(12):2608-2616, 2015.","title":"Survival with dialysis versus kidney transplantation in adult hemolytic uremic syndrome patients: A fifteen-year study of the waiting list","authors":"Michael J Alfonso H Santos, Xuerong Casey, Ivan Wen, Shehzad Zendejas, Karl L Rehman, Kenneth A Womer, Andreoni","year":"2015","venue":"Transplantation","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Sönmez et al., 2017] Tayfun Sönmez, Utku Unver, and M Bumin Yenmez. Incentivized kidney exchange, 2017. Tech. report, Boston College Dept. of Economics.","title":"Incentivized kidney exchange","authors":"Tayfun Sönmez, Utku Unver, M Bumin, Yenmez","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Toulis and Parkes, 2015] Panos Toulis and David C. Parkes. Design and analysis of multi-hospital kidney exchange mechanisms using random graphs. Games and Economic Behavior, 91(0):360-382, 2015.","title":"Design and analysis of multi-hospital kidney exchange mechanisms using random graphs","authors":"Panos Toulis, David C Parkes","year":"2015","venue":"Games and Economic Behavior","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[UNOS, 2015] UNOS. Revising kidney paired donation pi- lot program priority points, 2015. OPTN/UNOS Public Comment Proposal.","title":"UNOS. Revising kidney paired donation pilot program priority points","authors":"Unos","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Van der Maaten and Hinton, 2008] Laurens Van der Maaten and Geoffrey Hinton. Visualizing data using t-SNE. Jour- nal of Machine Learning Research, 9(11), 2008.","title":"Visualizing data using t-SNE","authors":"Van Der Maaten, Laurens Hinton, Geoffrey Van Der Maaten, Hinton","year":"2008","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}