Accept or Decline? An Analytics-Based Decision Tool for Kidney Offer Evaluation

Dimitris Bertsimas, Jerry Kung, Nikolaos Trichakis, David Wojciechowski, Parsia A. Vagefi

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Background When a deceased-donor kidney is offered to a waitlisted candidate, the decision to accept or decline the organ relies primarily upon a practitioner's experience and intuition. Such decisions must achieve a delicate balance between estimating the immediate benefit of transplantation and the potential for future higher-quality offers. However, the current experience-based paradigm lacks scientific rigor and is subject to the inaccuracies that plague anecdotal decision-making. Methods A data-driven analytics-based model was developed to predict whether a patient will receive an offer for a deceased-donor kidney at Kidney Donor Profile Index thresholds of 0.2, 0.4, and 0.6, and at timeframes of 3, 6, and 12 months. The model accounted for Organ Procurement Organization, blood group, wait time, DR antigens, and prior offer history to provide accurate and personalized predictions. Performance was evaluated on data sets spanning various lengths of time to understand the adaptability of the method. Results Using United Network for Organ Sharing match-run data from March 2007 to June 2013, out-of-sample area under the receiver operating characteristic curve was approximately 0.87 for all Kidney Donor Profile Index thresholds and timeframes considered for the 10 most populous Organ Procurement Organizations. As more data becomes available, area under the receiver operating characteristic curve values increase and subsequently level off. Conclusions The development of a data-driven analytics-based model may assist transplant practitioners and candidates during the complex decision of whether to accept or forgo a current kidney offer in anticipation of a future high-quality offer. The latter holds promise to facilitate timely transplantation and optimize the efficiency of allocation.

Original languageEnglish (US)
Pages (from-to)2898-2904
Number of pages7
JournalTransplantation
Volume101
Issue number12
DOIs
StatePublished - Dec 1 2017
Externally publishedYes

Fingerprint

Kidney
Tissue Donors
Tissue and Organ Procurement
ROC Curve
Transplantation
Intuition
Plague
Blood Group Antigens
Decision Making
History
Transplants
Antigens

ASJC Scopus subject areas

  • Transplantation

Cite this

Accept or Decline? An Analytics-Based Decision Tool for Kidney Offer Evaluation. / Bertsimas, Dimitris; Kung, Jerry; Trichakis, Nikolaos; Wojciechowski, David; Vagefi, Parsia A.

In: Transplantation, Vol. 101, No. 12, 01.12.2017, p. 2898-2904.

Research output: Contribution to journalArticle

Bertsimas, Dimitris ; Kung, Jerry ; Trichakis, Nikolaos ; Wojciechowski, David ; Vagefi, Parsia A. / Accept or Decline? An Analytics-Based Decision Tool for Kidney Offer Evaluation. In: Transplantation. 2017 ; Vol. 101, No. 12. pp. 2898-2904.
@article{5845b36905694eae848de20f8ef9b374,
title = "Accept or Decline? An Analytics-Based Decision Tool for Kidney Offer Evaluation",
abstract = "Background When a deceased-donor kidney is offered to a waitlisted candidate, the decision to accept or decline the organ relies primarily upon a practitioner's experience and intuition. Such decisions must achieve a delicate balance between estimating the immediate benefit of transplantation and the potential for future higher-quality offers. However, the current experience-based paradigm lacks scientific rigor and is subject to the inaccuracies that plague anecdotal decision-making. Methods A data-driven analytics-based model was developed to predict whether a patient will receive an offer for a deceased-donor kidney at Kidney Donor Profile Index thresholds of 0.2, 0.4, and 0.6, and at timeframes of 3, 6, and 12 months. The model accounted for Organ Procurement Organization, blood group, wait time, DR antigens, and prior offer history to provide accurate and personalized predictions. Performance was evaluated on data sets spanning various lengths of time to understand the adaptability of the method. Results Using United Network for Organ Sharing match-run data from March 2007 to June 2013, out-of-sample area under the receiver operating characteristic curve was approximately 0.87 for all Kidney Donor Profile Index thresholds and timeframes considered for the 10 most populous Organ Procurement Organizations. As more data becomes available, area under the receiver operating characteristic curve values increase and subsequently level off. Conclusions The development of a data-driven analytics-based model may assist transplant practitioners and candidates during the complex decision of whether to accept or forgo a current kidney offer in anticipation of a future high-quality offer. The latter holds promise to facilitate timely transplantation and optimize the efficiency of allocation.",
author = "Dimitris Bertsimas and Jerry Kung and Nikolaos Trichakis and David Wojciechowski and Vagefi, {Parsia A.}",
year = "2017",
month = "12",
day = "1",
doi = "10.1097/TP.0000000000001824",
language = "English (US)",
volume = "101",
pages = "2898--2904",
journal = "Transplantation",
issn = "0041-1337",
publisher = "Lippincott Williams and Wilkins",
number = "12",

}

TY - JOUR

T1 - Accept or Decline? An Analytics-Based Decision Tool for Kidney Offer Evaluation

AU - Bertsimas, Dimitris

AU - Kung, Jerry

AU - Trichakis, Nikolaos

AU - Wojciechowski, David

AU - Vagefi, Parsia A.

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Background When a deceased-donor kidney is offered to a waitlisted candidate, the decision to accept or decline the organ relies primarily upon a practitioner's experience and intuition. Such decisions must achieve a delicate balance between estimating the immediate benefit of transplantation and the potential for future higher-quality offers. However, the current experience-based paradigm lacks scientific rigor and is subject to the inaccuracies that plague anecdotal decision-making. Methods A data-driven analytics-based model was developed to predict whether a patient will receive an offer for a deceased-donor kidney at Kidney Donor Profile Index thresholds of 0.2, 0.4, and 0.6, and at timeframes of 3, 6, and 12 months. The model accounted for Organ Procurement Organization, blood group, wait time, DR antigens, and prior offer history to provide accurate and personalized predictions. Performance was evaluated on data sets spanning various lengths of time to understand the adaptability of the method. Results Using United Network for Organ Sharing match-run data from March 2007 to June 2013, out-of-sample area under the receiver operating characteristic curve was approximately 0.87 for all Kidney Donor Profile Index thresholds and timeframes considered for the 10 most populous Organ Procurement Organizations. As more data becomes available, area under the receiver operating characteristic curve values increase and subsequently level off. Conclusions The development of a data-driven analytics-based model may assist transplant practitioners and candidates during the complex decision of whether to accept or forgo a current kidney offer in anticipation of a future high-quality offer. The latter holds promise to facilitate timely transplantation and optimize the efficiency of allocation.

AB - Background When a deceased-donor kidney is offered to a waitlisted candidate, the decision to accept or decline the organ relies primarily upon a practitioner's experience and intuition. Such decisions must achieve a delicate balance between estimating the immediate benefit of transplantation and the potential for future higher-quality offers. However, the current experience-based paradigm lacks scientific rigor and is subject to the inaccuracies that plague anecdotal decision-making. Methods A data-driven analytics-based model was developed to predict whether a patient will receive an offer for a deceased-donor kidney at Kidney Donor Profile Index thresholds of 0.2, 0.4, and 0.6, and at timeframes of 3, 6, and 12 months. The model accounted for Organ Procurement Organization, blood group, wait time, DR antigens, and prior offer history to provide accurate and personalized predictions. Performance was evaluated on data sets spanning various lengths of time to understand the adaptability of the method. Results Using United Network for Organ Sharing match-run data from March 2007 to June 2013, out-of-sample area under the receiver operating characteristic curve was approximately 0.87 for all Kidney Donor Profile Index thresholds and timeframes considered for the 10 most populous Organ Procurement Organizations. As more data becomes available, area under the receiver operating characteristic curve values increase and subsequently level off. Conclusions The development of a data-driven analytics-based model may assist transplant practitioners and candidates during the complex decision of whether to accept or forgo a current kidney offer in anticipation of a future high-quality offer. The latter holds promise to facilitate timely transplantation and optimize the efficiency of allocation.

UR - http://www.scopus.com/inward/record.url?scp=85037039490&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85037039490&partnerID=8YFLogxK

U2 - 10.1097/TP.0000000000001824

DO - 10.1097/TP.0000000000001824

M3 - Article

C2 - 28514250

AN - SCOPUS:85037039490

VL - 101

SP - 2898

EP - 2904

JO - Transplantation

JF - Transplantation

SN - 0041-1337

IS - 12

ER -