Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Enhanced survival prediction using explainable artificial intelligence in heart transplantation

Lisboa, Paulo J.G. ; Jayabalan, Manoj ; Ortega-Martorell, Sandra ; Olier, Ivan ; Medved, Dennis LU orcid and Nilsson, Johan LU orcid (2022) In Scientific Reports 12(1).
Abstract

The most limiting factor in heart transplantation is the lack of donor organs. With enhanced prediction of outcome, it may be possible to increase the life-years from the organs that become available. Applications of machine learning to tabular data, typical of clinical decision support, pose the practical question of interpretation, which has technical and potential ethical implications. In particular, there is an issue of principle about the predictability of complex data and whether this is inherent in the data or strongly dependent on the choice of machine learning model, leading to the so-called accuracy-interpretability trade-off. We model 1-year mortality in heart transplantation data with a self-explaining neural network, which... (More)

The most limiting factor in heart transplantation is the lack of donor organs. With enhanced prediction of outcome, it may be possible to increase the life-years from the organs that become available. Applications of machine learning to tabular data, typical of clinical decision support, pose the practical question of interpretation, which has technical and potential ethical implications. In particular, there is an issue of principle about the predictability of complex data and whether this is inherent in the data or strongly dependent on the choice of machine learning model, leading to the so-called accuracy-interpretability trade-off. We model 1-year mortality in heart transplantation data with a self-explaining neural network, which is benchmarked against a deep learning model on the same development data, in an external validation study with two data sets: (1) UNOS transplants in 2017–2018 (n = 4750) for which the self-explaining and deep learning models are comparable in their AUROC 0.628 [0.602,0.654] cf. 0.635 [0.609,0.662] and (2) Scandinavian transplants during 1997–2018 (n = 2293), showing good calibration with AUROCs of 0.626 [0.588,0.665] and 0.634 [0.570, 0.698], respectively, with and without missing data (n = 982). This shows that for tabular data, predictive models can be transparent and capture important nonlinearities, retaining full predictive performance.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Scientific Reports
volume
12
issue
1
article number
19525
publisher
Nature Publishing Group
external identifiers
  • pmid:36376402
  • scopus:85141962945
ISSN
2045-2322
DOI
10.1038/s41598-022-23817-2
language
English
LU publication?
yes
id
c29a8edb-77f9-47f1-9b7a-3dbc9243562c
date added to LUP
2022-12-29 11:03:33
date last changed
2024-04-18 17:21:26
@article{c29a8edb-77f9-47f1-9b7a-3dbc9243562c,
  abstract     = {{<p>The most limiting factor in heart transplantation is the lack of donor organs. With enhanced prediction of outcome, it may be possible to increase the life-years from the organs that become available. Applications of machine learning to tabular data, typical of clinical decision support, pose the practical question of interpretation, which has technical and potential ethical implications. In particular, there is an issue of principle about the predictability of complex data and whether this is inherent in the data or strongly dependent on the choice of machine learning model, leading to the so-called accuracy-interpretability trade-off. We model 1-year mortality in heart transplantation data with a self-explaining neural network, which is benchmarked against a deep learning model on the same development data, in an external validation study with two data sets: (1) UNOS transplants in 2017–2018 (n = 4750) for which the self-explaining and deep learning models are comparable in their AUROC 0.628 [0.602,0.654] cf. 0.635 [0.609,0.662] and (2) Scandinavian transplants during 1997–2018 (n = 2293), showing good calibration with AUROCs of 0.626 [0.588,0.665] and 0.634 [0.570, 0.698], respectively, with and without missing data (n = 982). This shows that for tabular data, predictive models can be transparent and capture important nonlinearities, retaining full predictive performance.</p>}},
  author       = {{Lisboa, Paulo J.G. and Jayabalan, Manoj and Ortega-Martorell, Sandra and Olier, Ivan and Medved, Dennis and Nilsson, Johan}},
  issn         = {{2045-2322}},
  language     = {{eng}},
  number       = {{1}},
  publisher    = {{Nature Publishing Group}},
  series       = {{Scientific Reports}},
  title        = {{Enhanced survival prediction using explainable artificial intelligence in heart transplantation}},
  url          = {{http://dx.doi.org/10.1038/s41598-022-23817-2}},
  doi          = {{10.1038/s41598-022-23817-2}},
  volume       = {{12}},
  year         = {{2022}},
}