Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Machine learning compared with rule-in/rule-out algorithms and logistic regression to predict acute myocardial infarction based on troponin T concentrations

Björkelund, Anders LU ; Ohlsson, Mattias LU orcid ; Lundager Forberg, Jakob LU ; Mokhtari, Arash LU ; Olsson de Capretz, Pontus LU ; Ekelund, Ulf LU orcid and Björk, Jonas LU (2021) In Journal of the American college of emergency physicians open 2(2).
Abstract

Objective
Computerized decision‐support tools may improve diagnosis of acute myocardial infarction (AMI) among patients presenting with chest pain at the emergency department (ED). The primary aim was to assess the predictive accuracy of machine learning algorithms based on paired high‐sensitivity cardiac troponin T (hs‐cTnT) concentrations with varying sampling times, age, and sex in order to rule in or out AMI.
Methods
In this register‐based, cross‐sectional diagnostic study conducted retrospectively based on 5695 chest pain patients at 2 hospitals in Sweden 2013–2014 we used 5‐fold cross‐validation 200 times in order to compare the performance of an artificial neural network (ANN) with European guideline‐recommended... (More)

Objective
Computerized decision‐support tools may improve diagnosis of acute myocardial infarction (AMI) among patients presenting with chest pain at the emergency department (ED). The primary aim was to assess the predictive accuracy of machine learning algorithms based on paired high‐sensitivity cardiac troponin T (hs‐cTnT) concentrations with varying sampling times, age, and sex in order to rule in or out AMI.
Methods
In this register‐based, cross‐sectional diagnostic study conducted retrospectively based on 5695 chest pain patients at 2 hospitals in Sweden 2013–2014 we used 5‐fold cross‐validation 200 times in order to compare the performance of an artificial neural network (ANN) with European guideline‐recommended 0/1‐ and 0/3‐hour algorithms for hs‐cTnT and with logistic regression without interaction terms. Primary outcome was the size of the intermediate risk group where AMI could not be ruled in or out, while holding the sensitivity (rule‐out) and specificity (rule‐in) constant across models.
Results
ANN and logistic regression had similar (95%) areas under the receiver operating characteristics curve. In patients (n = 4171) where the timing requirements (0/1 or 0/3 hour) for the sampling were met, using ANN led to a relative decrease of 9.2% (95% confidence interval 4.4% to 13.8%; from 24.5% to 22.2% of all tested patients) in the size of the intermediate group compared to the recommended algorithms. By contrast, using logistic regression did not substantially decrease the size of the intermediate group.
Conclusion
Machine learning algorithms allow for flexibility in sampling and have the potential to improve risk assessment among chest pain patients at the ED.
(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
Journal of the American college of emergency physicians open
volume
2
issue
2
article number
e12363
publisher
John Wiley & Sons Inc.
external identifiers
  • pmid:33778804
  • pmid:33778804
  • scopus:85128553978
ISSN
2688-1152
DOI
10.1002/emp2.12363
project
AIR Lund - Artificially Intelligent use of Registers
language
English
LU publication?
yes
id
ecc7003f-2316-4e2c-8c35-1ab26a2f6b5d
date added to LUP
2021-03-29 15:29:57
date last changed
2024-04-19 20:09:53
@article{ecc7003f-2316-4e2c-8c35-1ab26a2f6b5d,
  abstract     = {{<br/>Objective<br/>Computerized decision‐support tools may improve diagnosis of acute myocardial infarction (AMI) among patients presenting with chest pain at the emergency department (ED). The primary aim was to assess the predictive accuracy of machine learning algorithms based on paired high‐sensitivity cardiac troponin T (hs‐cTnT) concentrations with varying sampling times, age, and sex in order to rule in or out AMI.<br/>Methods<br/>In this register‐based, cross‐sectional diagnostic study conducted retrospectively based on 5695 chest pain patients at 2 hospitals in Sweden 2013–2014 we used 5‐fold cross‐validation 200 times in order to compare the performance of an artificial neural network (ANN) with European guideline‐recommended 0/1‐ and 0/3‐hour algorithms for hs‐cTnT and with logistic regression without interaction terms. Primary outcome was the size of the intermediate risk group where AMI could not be ruled in or out, while holding the sensitivity (rule‐out) and specificity (rule‐in) constant across models.<br/>Results<br/>ANN and logistic regression had similar (95%) areas under the receiver operating characteristics curve. In patients (n = 4171) where the timing requirements (0/1 or 0/3 hour) for the sampling were met, using ANN led to a relative decrease of 9.2% (95% confidence interval 4.4% to 13.8%; from 24.5% to 22.2% of all tested patients) in the size of the intermediate group compared to the recommended algorithms. By contrast, using logistic regression did not substantially decrease the size of the intermediate group.<br/>Conclusion<br/>Machine learning algorithms allow for flexibility in sampling and have the potential to improve risk assessment among chest pain patients at the ED.<br/>}},
  author       = {{Björkelund, Anders and Ohlsson, Mattias and Lundager Forberg, Jakob and Mokhtari, Arash and Olsson de Capretz, Pontus and Ekelund, Ulf and Björk, Jonas}},
  issn         = {{2688-1152}},
  language     = {{eng}},
  number       = {{2}},
  publisher    = {{John Wiley & Sons Inc.}},
  series       = {{Journal of the American college of emergency physicians open}},
  title        = {{Machine learning compared with rule-in/rule-out algorithms and logistic regression to predict acute myocardial infarction based on troponin T concentrations}},
  url          = {{http://dx.doi.org/10.1002/emp2.12363}},
  doi          = {{10.1002/emp2.12363}},
  volume       = {{2}},
  year         = {{2021}},
}