Please use this identifier to cite or link to this item: https://doi.org/10.1111/petr.13105
Title: Prelisting predictions of early postoperative survival in infant heart transplantation using classification and regression tree analysis
Authors: Chen, Ching Kit 
Manlhiot, Cedric
Mital, Seema
Schwartz, Steven M
Van Arsdell, Glen S
Caldarone, Christopher
McCrindle, Brian W
Dipchand, Anne I
Keywords: Science & Technology
Life Sciences & Biomedicine
Pediatrics
Transplantation
data mining
infant heart transplant
mortality risk
predictive modeling
EXTRACORPOREAL MEMBRANE-OXYGENATION
CARDIAC TRANSPLANTATION
UNITED-STATES
RISK-FACTORS
CHILDREN
DISEASE
OUTCOMES
REGISTRY
DEATH
RECIPIENTS
Issue Date: 1-Mar-2018
Publisher: WILEY
Citation: Chen, Ching Kit, Manlhiot, Cedric, Mital, Seema, Schwartz, Steven M, Van Arsdell, Glen S, Caldarone, Christopher, McCrindle, Brian W, Dipchand, Anne I (2018-03-01). Prelisting predictions of early postoperative survival in infant heart transplantation using classification and regression tree analysis. PEDIATRIC TRANSPLANTATION 22 (2). ScholarBank@NUS Repository. https://doi.org/10.1111/petr.13105
Abstract: Infants listed for heart transplantation experience high waitlist and early post-transplant mortality, and thus, optimal allocation of scarce donor organs is required. Unfortunately, the creation and validation of multivariable regression models to identify risk factors and generate individual-level predictions are challenging. We sought to explore the use of data mining methods to generate a prediction model. CART analysis was used to create a model which, at the time of listing, would predict which infants listed for heart transplantation would survive at least 3 months post-transplantation. A total of 48 infants were included; 13 died while waiting, and six died within 3 months of heart transplant. CART analysis identified RRT, blood urea nitrogen, and hematocrit as terminal nodes with alanine transaminase as an intermediate node predicting death. No patients listed on RRT (n = 10) survived and only three of 12 (25%) patients listed on ECLS survived >3 months post-transplant. CART analysis overall accuracy was 83%, with sensitivity of 95% and specificity 76%. This study shows that CART analysis can be used to generate accurate prediction models in small patient populations. Model validation will be necessary before incorporation into decision-making algorithms used to determine transplant candidacy.
Source Title: PEDIATRIC TRANSPLANTATION
URI: https://scholarbank.nus.edu.sg/handle/10635/191503
ISSN: 13973142
13993046
DOI: 10.1111/petr.13105
Appears in Collections:Staff Publications
Elements

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
PedTx2018_Prelisting predictions of early postoperative survival in infant HTx using CART.pdfPublished version483.87 kBAdobe PDF

CLOSED

None

SCOPUSTM   
Citations

1
checked on May 21, 2022

WEB OF SCIENCETM
Citations

2
checked on Oct 8, 2021

Page view(s)

99
checked on May 12, 2022

Download(s)

1
checked on May 12, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.