Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Improving Machine Learning 30-Day Mortality Prediction by Discounting Surprising Deaths

Heyman, Ellen Tolestam LU orcid ; Ashfaq, Awais ; Khoshnood, Ardavan LU orcid ; Ohlsson, Mattias LU orcid ; Ekelund, Ulf LU orcid ; Holmqvist, Lina Dahlén and Lingman, Markus (2021) In Journal of Emergency Medicine 61(6). p.763-773
Abstract

BACKGROUND: Machine learning (ML) is an emerging tool for predicting need of end-of-life discussion and palliative care, by using mortality as a proxy. But deaths, unforeseen by emergency physicians at time of the emergency department (ED) visit, might have a weaker association with the ED visit.

OBJECTIVES: To develop an ML algorithm that predicts unsurprising deaths within 30 days after ED discharge.

METHODS: In this retrospective registry study, we included all ED attendances within the Swedish region of Halland in 2015 and 2016. All registered deaths within 30 days after ED discharge were classified as either "surprising" or "unsurprising" by an adjudicating committee with three senior specialists in emergency medicine.... (More)

BACKGROUND: Machine learning (ML) is an emerging tool for predicting need of end-of-life discussion and palliative care, by using mortality as a proxy. But deaths, unforeseen by emergency physicians at time of the emergency department (ED) visit, might have a weaker association with the ED visit.

OBJECTIVES: To develop an ML algorithm that predicts unsurprising deaths within 30 days after ED discharge.

METHODS: In this retrospective registry study, we included all ED attendances within the Swedish region of Halland in 2015 and 2016. All registered deaths within 30 days after ED discharge were classified as either "surprising" or "unsurprising" by an adjudicating committee with three senior specialists in emergency medicine. ML algorithms were developed for the death subclasses by using Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM).

RESULTS: Of all 30-day deaths (n = 148), 76% (n = 113) were not surprising to the adjudicating committee. The most common diseases were advanced stage cancer, multidisease/frailty, and dementia. By using LR, RF, and SVM, mean area under the receiver operating characteristic curve (ROC-AUC) of unsurprising deaths in the test set were 0.950 (SD 0.008), 0.944 (SD 0.007), and 0.949 (SD 0.007), respectively. For all mortality, the ROC-AUCs for LR, RF, and SVM were 0.924 (SD 0.012), 0.922 (SD 0.009), and 0.931 (SD 0.008). The difference in prediction performance between all and unsurprising death was statistically significant (P < .001) for all three models.

CONCLUSION: In patients discharged to home from the ED, three-quarters of all 30-day deaths did not surprise an adjudicating committee with emergency medicine specialists. When only unsurprising deaths were included, ML mortality prediction improved significantly.

(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
keywords
machine learning, artificial intelligence, emergency department, emergency medicine, end-of-life, palliative care, Maskininlärning, artificial intelligence, akutsjukvård, palliativ vård, livets slutskede
in
Journal of Emergency Medicine
volume
61
issue
6
pages
763 - 773
publisher
Elsevier
external identifiers
  • pmid:34716042
  • scopus:85118363200
ISSN
0736-4679
DOI
10.1016/j.jemermed.2021.09.004
project
AIR Lund - Artificially Intelligent use of Registers
Resource Management in the Emergency Department by using Machine Learning
language
English
LU publication?
yes
additional info
Copyright © 2021 The Author(s). Published by Elsevier Inc. All rights reserved.
id
fb2b9343-b12a-4e64-a8ff-3e22856cc612
date added to LUP
2021-11-09 00:25:28
date last changed
2025-04-04 15:15:21
@article{fb2b9343-b12a-4e64-a8ff-3e22856cc612,
  abstract     = {{<p>BACKGROUND: Machine learning (ML) is an emerging tool for predicting need of end-of-life discussion and palliative care, by using mortality as a proxy. But deaths, unforeseen by emergency physicians at time of the emergency department (ED) visit, might have a weaker association with the ED visit.</p><p>OBJECTIVES: To develop an ML algorithm that predicts unsurprising deaths within 30 days after ED discharge.</p><p>METHODS: In this retrospective registry study, we included all ED attendances within the Swedish region of Halland in 2015 and 2016. All registered deaths within 30 days after ED discharge were classified as either "surprising" or "unsurprising" by an adjudicating committee with three senior specialists in emergency medicine. ML algorithms were developed for the death subclasses by using Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM).</p><p>RESULTS: Of all 30-day deaths (n = 148), 76% (n = 113) were not surprising to the adjudicating committee. The most common diseases were advanced stage cancer, multidisease/frailty, and dementia. By using LR, RF, and SVM, mean area under the receiver operating characteristic curve (ROC-AUC) of unsurprising deaths in the test set were 0.950 (SD 0.008), 0.944 (SD 0.007), and 0.949 (SD 0.007), respectively. For all mortality, the ROC-AUCs for LR, RF, and SVM were 0.924 (SD 0.012), 0.922 (SD 0.009), and 0.931 (SD 0.008). The difference in prediction performance between all and unsurprising death was statistically significant (P &lt; .001) for all three models.</p><p>CONCLUSION: In patients discharged to home from the ED, three-quarters of all 30-day deaths did not surprise an adjudicating committee with emergency medicine specialists. When only unsurprising deaths were included, ML mortality prediction improved significantly.</p>}},
  author       = {{Heyman, Ellen Tolestam and Ashfaq, Awais and Khoshnood, Ardavan and Ohlsson, Mattias and Ekelund, Ulf and Holmqvist, Lina Dahlén and Lingman, Markus}},
  issn         = {{0736-4679}},
  keywords     = {{machine learning; artificial intelligence; emergency department; emergency medicine; end-of-life; palliative care; Maskininlärning; artificial intelligence; akutsjukvård; palliativ vård; livets slutskede}},
  language     = {{eng}},
  number       = {{6}},
  pages        = {{763--773}},
  publisher    = {{Elsevier}},
  series       = {{Journal of Emergency Medicine}},
  title        = {{Improving Machine Learning 30-Day Mortality Prediction by Discounting Surprising Deaths}},
  url          = {{http://dx.doi.org/10.1016/j.jemermed.2021.09.004}},
  doi          = {{10.1016/j.jemermed.2021.09.004}},
  volume       = {{61}},
  year         = {{2021}},
}