A neural network-based approach for predicting organ donation potential

Benjamin R. Schleich, Sarah S. Lam, Sang Won Yoon, Waheed Tajik, Michael Goldstein, Helen Irving

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This research proposes a potential organ donor prediction model using an artificial neural network-based approach to forecast the amount of daily incoming organ referrals and their medical suitability. The daily amount of incoming organ referrals and their medical suitability indicate organ donation potential. Predicting organ donation potential is vital for organ procurement organizations (OPOs) to improve staffing and scheduling practices. As a result, the objective of this study is to develop an accurate organ donation potential prediction model that can help the OPOs in achieving their mission to save lives. Several supervised artificial neural networks were designed, tested and compared with each other to identify best prediction accuracy. The experimental results and analyses indicate that the prediction accuracy for organ donation potential depends not only on the network type, but also on the architecture selection and the choice of inputs and time frame. The constructed neural network model shows good organ potential prediction accuracy with a R-squared value of 0.73. Hence, implementing such a model can support organ procurement organizations in their mission to save lives.

Original languageEnglish (US)
Title of host publicationIIE Annual Conference and Expo 2013
PublisherInstitute of Industrial Engineers
Pages1532-1541
Number of pages10
StatePublished - 2013
Externally publishedYes
EventIIE Annual Conference and Expo 2013 - San Juan, Puerto Rico
Duration: May 18 2013May 22 2013

Other

OtherIIE Annual Conference and Expo 2013
CountryPuerto Rico
CitySan Juan
Period5/18/135/22/13

Fingerprint

Neural networks
Scheduling

Keywords

  • Artificial neural networks
  • Organ donation
  • Organ referral prediction
  • Time series forecasting

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Cite this

Schleich, B. R., Lam, S. S., Yoon, S. W., Tajik, W., Goldstein, M., & Irving, H. (2013). A neural network-based approach for predicting organ donation potential. In IIE Annual Conference and Expo 2013 (pp. 1532-1541). Institute of Industrial Engineers.

A neural network-based approach for predicting organ donation potential. / Schleich, Benjamin R.; Lam, Sarah S.; Yoon, Sang Won; Tajik, Waheed; Goldstein, Michael; Irving, Helen.

IIE Annual Conference and Expo 2013. Institute of Industrial Engineers, 2013. p. 1532-1541.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Schleich, BR, Lam, SS, Yoon, SW, Tajik, W, Goldstein, M & Irving, H 2013, A neural network-based approach for predicting organ donation potential. in IIE Annual Conference and Expo 2013. Institute of Industrial Engineers, pp. 1532-1541, IIE Annual Conference and Expo 2013, San Juan, Puerto Rico, 5/18/13.
Schleich BR, Lam SS, Yoon SW, Tajik W, Goldstein M, Irving H. A neural network-based approach for predicting organ donation potential. In IIE Annual Conference and Expo 2013. Institute of Industrial Engineers. 2013. p. 1532-1541
Schleich, Benjamin R. ; Lam, Sarah S. ; Yoon, Sang Won ; Tajik, Waheed ; Goldstein, Michael ; Irving, Helen. / A neural network-based approach for predicting organ donation potential. IIE Annual Conference and Expo 2013. Institute of Industrial Engineers, 2013. pp. 1532-1541
@inproceedings{dd3dfc16ca664e0a8e97ff6ea1e3eabe,
title = "A neural network-based approach for predicting organ donation potential",
abstract = "This research proposes a potential organ donor prediction model using an artificial neural network-based approach to forecast the amount of daily incoming organ referrals and their medical suitability. The daily amount of incoming organ referrals and their medical suitability indicate organ donation potential. Predicting organ donation potential is vital for organ procurement organizations (OPOs) to improve staffing and scheduling practices. As a result, the objective of this study is to develop an accurate organ donation potential prediction model that can help the OPOs in achieving their mission to save lives. Several supervised artificial neural networks were designed, tested and compared with each other to identify best prediction accuracy. The experimental results and analyses indicate that the prediction accuracy for organ donation potential depends not only on the network type, but also on the architecture selection and the choice of inputs and time frame. The constructed neural network model shows good organ potential prediction accuracy with a R-squared value of 0.73. Hence, implementing such a model can support organ procurement organizations in their mission to save lives.",
keywords = "Artificial neural networks, Organ donation, Organ referral prediction, Time series forecasting",
author = "Schleich, {Benjamin R.} and Lam, {Sarah S.} and Yoon, {Sang Won} and Waheed Tajik and Michael Goldstein and Helen Irving",
year = "2013",
language = "English (US)",
pages = "1532--1541",
booktitle = "IIE Annual Conference and Expo 2013",
publisher = "Institute of Industrial Engineers",

}

TY - GEN

T1 - A neural network-based approach for predicting organ donation potential

AU - Schleich, Benjamin R.

AU - Lam, Sarah S.

AU - Yoon, Sang Won

AU - Tajik, Waheed

AU - Goldstein, Michael

AU - Irving, Helen

PY - 2013

Y1 - 2013

N2 - This research proposes a potential organ donor prediction model using an artificial neural network-based approach to forecast the amount of daily incoming organ referrals and their medical suitability. The daily amount of incoming organ referrals and their medical suitability indicate organ donation potential. Predicting organ donation potential is vital for organ procurement organizations (OPOs) to improve staffing and scheduling practices. As a result, the objective of this study is to develop an accurate organ donation potential prediction model that can help the OPOs in achieving their mission to save lives. Several supervised artificial neural networks were designed, tested and compared with each other to identify best prediction accuracy. The experimental results and analyses indicate that the prediction accuracy for organ donation potential depends not only on the network type, but also on the architecture selection and the choice of inputs and time frame. The constructed neural network model shows good organ potential prediction accuracy with a R-squared value of 0.73. Hence, implementing such a model can support organ procurement organizations in their mission to save lives.

AB - This research proposes a potential organ donor prediction model using an artificial neural network-based approach to forecast the amount of daily incoming organ referrals and their medical suitability. The daily amount of incoming organ referrals and their medical suitability indicate organ donation potential. Predicting organ donation potential is vital for organ procurement organizations (OPOs) to improve staffing and scheduling practices. As a result, the objective of this study is to develop an accurate organ donation potential prediction model that can help the OPOs in achieving their mission to save lives. Several supervised artificial neural networks were designed, tested and compared with each other to identify best prediction accuracy. The experimental results and analyses indicate that the prediction accuracy for organ donation potential depends not only on the network type, but also on the architecture selection and the choice of inputs and time frame. The constructed neural network model shows good organ potential prediction accuracy with a R-squared value of 0.73. Hence, implementing such a model can support organ procurement organizations in their mission to save lives.

KW - Artificial neural networks

KW - Organ donation

KW - Organ referral prediction

KW - Time series forecasting

UR - http://www.scopus.com/inward/record.url?scp=84900340315&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900340315&partnerID=8YFLogxK

M3 - Conference contribution

SP - 1532

EP - 1541

BT - IIE Annual Conference and Expo 2013

PB - Institute of Industrial Engineers

ER -