ATC Abstracts

American Transplant Congress abstracts

  • Home
  • Meetings Archive
    • 2022 American Transplant Congress
    • 2021 American Transplant Congress
    • 2020 American Transplant Congress
    • 2019 American Transplant Congress
    • 2018 American Transplant Congress
    • 2017 American Transplant Congress
    • 2016 American Transplant Congress
    • 2015 American Transplant Congress
    • 2013 American Transplant Congress
  • Keyword Index
  • Resources
    • 2021 Resources
    • 2016 Resources
      • 2016 Welcome Letter
      • ATC 2016 Program Planning Committees
      • ASTS Council 2015-2016
      • AST Board of Directors 2015-2016
    • 2015 Resources
      • 2015 Welcome Letter
      • ATC 2015 Program Planning Committees
      • ASTS Council 2014-2015
      • AST Board of Directors 2014-2015
      • 2015 Conference Schedule
  • Search

Donor Disposition AI Model to Predict Transplant for Recovered Deceased Donor Kidneys

L. Ashiku1, R. Threlkeld1, C. Dagli1, M. Schnitzler2, C. Canfield1, K. Lentine2, H. Randall2

1MST, Rolla, MO, 2SLU, Saint Louis, MO

Meeting: 2022 American Transplant Congress

Abstract number: 711

Keywords: Donors, marginal, Kidney transplantation, Organ Selection/Allocation

Topic: Clinical Science » Kidney » 31 - Kidney Deceased Donor Allocation

Session Information

Session Name: Kidney Deceased Donor Allocation

Session Type: Poster Abstract

Date: Saturday, June 4, 2022

Session Time: 5:30pm-7:00pm

 Presentation Time: 5:30pm-7:00pm

Location: Hynes Halls C & D

*Purpose: Current practice for accelerated kidney placements rely heavily on the Kidney Donor Profile Index (KDPI) to determine if recovered deceased-donor (DD) kidneys are hard-to-place. A neural network model using DD disposition is trained to predict Not Transplanted (perfect correlation with discard) or Transplanted based on features beyond those used to calculate KDPI. These models may aid Organ Procurement Organizations (OPOs) in quickly identifying hard-to-place kidneys for early accelerated placement.

*Methods: The data used to train and test the neural network was obtained from the Unified Network of Organ System (UNOS). Missing values limited the study to the most recent four years of DD data. We deployed feature elimination techniques and advanced 35 DD features to use for the models. A 4-layer convolutional neural network is developed to train the models while saving 15% of the data for testing. Missing values on dual kidney label led to treating each kidney separately, creating two copies of the data and isolating features that belonged to one kidney when analyzing the other. Model development is performed in Python using TensorFlow on Google Colab.

*Results: Fig. 1 shows the current discard rate, historical disposition data of both kidneys, and two models’ prediction of disposition on both kidneys. The models were trained and tested using principal DD features, such as kidney scarring, hypertension duration, glomeruli count, KDPI, etc. Both models trained on the principal features yielded 85% accuracy and greater opportunity space to aptly identify hard-to-place kidneys instead of KDPI alone at 83% accuracy. The disposition prediction models are moderately sensitive to high KDPI but not for lower value KDPI, and many DD features influence disposition models that may otherwise be discounted. Expanded criteria donors may cause the peak at 95 KDPI relationship, whereas decline may be due to early accelerated placement not ascertained in the data.

*Conclusions: Current practice of quickly identifying hard-to-place kidneys solely on KDPI may overlook crucial DD features. This study aims to use an impartial approach for quickly identifying hard-to-place kidneys using broader DD features. Both models show significant improvements to KDPI and could serve as tools in identifying when to engage in accelerated placement. Limitations include dual kidney model label, and lack of info on accelerated placement for out-of-sequence placements. Future work will consist of feature selections using refined deep learning algorithms to increase prediction performance for high KDPI kidneys.

  • Tweet
  • Email
  • Print

To cite this abstract in AMA style:

Ashiku L, Threlkeld R, Dagli C, Schnitzler M, Canfield C, Lentine K, Randall H. Donor Disposition AI Model to Predict Transplant for Recovered Deceased Donor Kidneys [abstract]. Am J Transplant. 2022; 22 (suppl 3). https://atcmeetingabstracts.com/abstract/donor-disposition-ai-model-to-predict-transplant-for-recovered-deceased-donor-kidneys/. Accessed May 9, 2025.

« Back to 2022 American Transplant Congress

Visit Our Partner Sites

American Transplant Congress (ATC)

Visit the official site for the American Transplant Congress »

American Journal of Transplantation

The official publication for the American Society of Transplantation (AST) and the American Society of Transplant Surgeons (ASTS) »

American Society of Transplantation (AST)

An organization of more than 3000 professionals dedicated to advancing the field of transplantation. »

American Society of Transplant Surgeons (ASTS)

The society represents approximately 1,800 professionals dedicated to excellence in transplantation surgery. »

Copyright © 2013-2025 by American Society of Transplantation and the American Society of Transplant Surgeons. All rights reserved.

Privacy Policy | Terms of Use | Cookie Preferences