Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Machine learning for early prediction of acute myocardial infarction or death in acute chest pain patients using electrocardiogram and blood tests at presentation

de Capretz, Pontus Olsson LU ; Björkelund, Anders LU ; Björk, Jonas LU ; Ohlsson, Mattias LU orcid ; Mokhtari, Arash LU ; Nyström, Axel LU and Ekelund, Ulf LU orcid (2023) In BMC Medical Informatics and Decision Making 23(1).
Abstract

Aims: In the present study, we aimed to evaluate the performance of machine learning (ML) models for identification of acute myocardial infarction (AMI) or death within 30 days among emergency department (ED) chest pain patients. Methods and results: Using data from 9519 consecutive ED chest pain patients, we created ML models based on logistic regression or artificial neural networks. Model inputs included sex, age, ECG and the first blood tests at patient presentation: High sensitivity TnT (hs-cTnT), glucose, creatinine, and hemoglobin. For a safe rule-out, the models were adapted to achieve a sensitivity > 99% and a negative predictive value (NPV) > 99.5% for 30-day AMI/death. For rule-in, we set the models to achieve a... (More)

Aims: In the present study, we aimed to evaluate the performance of machine learning (ML) models for identification of acute myocardial infarction (AMI) or death within 30 days among emergency department (ED) chest pain patients. Methods and results: Using data from 9519 consecutive ED chest pain patients, we created ML models based on logistic regression or artificial neural networks. Model inputs included sex, age, ECG and the first blood tests at patient presentation: High sensitivity TnT (hs-cTnT), glucose, creatinine, and hemoglobin. For a safe rule-out, the models were adapted to achieve a sensitivity > 99% and a negative predictive value (NPV) > 99.5% for 30-day AMI/death. For rule-in, we set the models to achieve a specificity > 90% and a positive predictive value (PPV) of > 70%. The models were also compared with the 0 h arm of the European Society of Cardiology algorithm (ESC 0 h); An initial hs-cTnT < 5 ng/L for rule-out and ≥ 52 ng/L for rule-in. A convolutional neural network was the best model and identified 55% of the patients for rule-out and 5.3% for rule-in, while maintaining the required sensitivity, specificity, NPV and PPV levels. ESC 0 h failed to reach these performance levels. Discussion: An ML model based on age, sex, ECG and blood tests at ED arrival can identify six out of ten chest pain patients for safe early rule-out or rule-in with no need for serial blood tests. Future studies should attempt to improve these ML models further, e.g. by including additional input data.

(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
Acute myocardial infarction, Chest pain, Deep learning, Emergency department, High-sensitivity troponin, Machine learning
in
BMC Medical Informatics and Decision Making
volume
23
issue
1
article number
25
publisher
BioMed Central (BMC)
external identifiers
  • scopus:85147318502
  • pmid:36732708
ISSN
1472-6947
DOI
10.1186/s12911-023-02119-1
project
AIR Lund - Artificially Intelligent use of Registers
language
English
LU publication?
yes
id
ed5bee3a-1094-4b93-a02d-ef6fce22c41f
date added to LUP
2023-03-10 11:00:19
date last changed
2024-06-27 21:38:08
@article{ed5bee3a-1094-4b93-a02d-ef6fce22c41f,
  abstract     = {{<p>Aims: In the present study, we aimed to evaluate the performance of machine learning (ML) models for identification of acute myocardial infarction (AMI) or death within 30 days among emergency department (ED) chest pain patients. Methods and results: Using data from 9519 consecutive ED chest pain patients, we created ML models based on logistic regression or artificial neural networks. Model inputs included sex, age, ECG and the first blood tests at patient presentation: High sensitivity TnT (hs-cTnT), glucose, creatinine, and hemoglobin. For a safe rule-out, the models were adapted to achieve a sensitivity &gt; 99% and a negative predictive value (NPV) &gt; 99.5% for 30-day AMI/death. For rule-in, we set the models to achieve a specificity &gt; 90% and a positive predictive value (PPV) of &gt; 70%. The models were also compared with the 0 h arm of the European Society of Cardiology algorithm (ESC 0 h); An initial hs-cTnT &lt; 5 ng/L for rule-out and ≥ 52 ng/L for rule-in. A convolutional neural network was the best model and identified 55% of the patients for rule-out and 5.3% for rule-in, while maintaining the required sensitivity, specificity, NPV and PPV levels. ESC 0 h failed to reach these performance levels. Discussion: An ML model based on age, sex, ECG and blood tests at ED arrival can identify six out of ten chest pain patients for safe early rule-out or rule-in with no need for serial blood tests. Future studies should attempt to improve these ML models further, e.g. by including additional input data.</p>}},
  author       = {{de Capretz, Pontus Olsson and Björkelund, Anders and Björk, Jonas and Ohlsson, Mattias and Mokhtari, Arash and Nyström, Axel and Ekelund, Ulf}},
  issn         = {{1472-6947}},
  keywords     = {{Acute myocardial infarction; Chest pain; Deep learning; Emergency department; High-sensitivity troponin; Machine learning}},
  language     = {{eng}},
  number       = {{1}},
  publisher    = {{BioMed Central (BMC)}},
  series       = {{BMC Medical Informatics and Decision Making}},
  title        = {{Machine learning for early prediction of acute myocardial infarction or death in acute chest pain patients using electrocardiogram and blood tests at presentation}},
  url          = {{http://dx.doi.org/10.1186/s12911-023-02119-1}},
  doi          = {{10.1186/s12911-023-02119-1}},
  volume       = {{23}},
  year         = {{2023}},
}