An artificial intelligence approach to early predict non-ST-elevation myocardial infarction patients with chest pain

Chieh Chen Wu, Wen Ding Hsu, Md Mohaimenul Islam, Tahmina Nasrin Poly, Hsuan Chia Yang, Phung Anh  (Alex) Nguyen, Yao Chin Wang, Yu Chuan  (Jack) Li

研究成果: 雜誌貢獻文章

摘要

Background and Aims: Hospital admission rate for the patients with chest pain has already been increased worldwide but no existing risk score has been designed to stratify non-ST-elevation myocardial infarction (NSTEMI) from non-cardiogenic chest pain. Clinical diagnosis of chest pain in the emergency department is always highly subjective and variable. We, therefore, aimed to develop an artificial intelligence approach to predict stable NSTEMI that would give valuable insight to reduce misdiagnosis in the real clinical setting. Methods: A standard protocol was developed to collect data from chest pain patients who had visited the emergency department between December 2016 and February 2017. All the chest pain patients with aged <20 years were primarily included in this study. However, STEMI, previous history of ACS, and out-of-hospital cardiac arrest were excluded from our study. An artificial neural network (ANN) model was then developed to predict NSTEMI patients. The accuracy, sensitivity, specificity, and receiver operating characteristic curve was used to measure the performance of this model. Results: A total of 268 chest pain patients were included in this study; of those, 47 (17.5%) was stable NSTEMI, and 221 (82.5%) was unstable angina patients. Serval risk factors such as cardiac risk factor, systolic blood pressure, hemoglobin, corrected QT interval (QTc), PR interval, glutamic-oxaloacetic transaminase, glutamic pyruvic transaminase and troponin were independently associated with stable NSTEMI. The area under the receiver operating characteristic (AUROC) and accuracy of ANN were 98.4, and 92.86. Additionally, the sensitivity, specificity, positive predictive value, and negative predictive value of the ANN model was 90.91, 93.33, 76.92, and 97.67 respectively. Conclusion: Our prediction model showed a higher accuracy to predict NSTEMI patients. This model has a potential application in disease detection, monitoring, and prognosis of chest pain at risk of AMI.
原文英語
頁(從 - 到)109-117
頁數9
期刊Computer Methods and Programs in Biomedicine
173
DOIs
出版狀態已發佈 - 五月 1 2019

指紋

Artificial Intelligence
Chest Pain
Artificial intelligence
Neural networks
Neural Networks (Computer)
ROC Curve
Hospital Emergency Service
Hemoglobin
Blood pressure
Blood Pressure
Out-of-Hospital Cardiac Arrest
Sensitivity and Specificity
Troponin
Patient Admission
Unstable Angina
Aspartate Aminotransferases
Non-ST Elevated Myocardial Infarction
Diagnostic Errors
Alanine Transaminase
Hemoglobins

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Health Informatics

引用此文

An artificial intelligence approach to early predict non-ST-elevation myocardial infarction patients with chest pain. / Wu, Chieh Chen; Hsu, Wen Ding; Islam, Md Mohaimenul; Poly, Tahmina Nasrin; Yang, Hsuan Chia; Nguyen, Phung Anh  (Alex); Wang, Yao Chin; Li, Yu Chuan  (Jack).

於: Computer Methods and Programs in Biomedicine, 卷 173, 01.05.2019, p. 109-117.

研究成果: 雜誌貢獻文章

Wu, Chieh Chen ; Hsu, Wen Ding ; Islam, Md Mohaimenul ; Poly, Tahmina Nasrin ; Yang, Hsuan Chia ; Nguyen, Phung Anh  (Alex) ; Wang, Yao Chin ; Li, Yu Chuan  (Jack). / An artificial intelligence approach to early predict non-ST-elevation myocardial infarction patients with chest pain. 於: Computer Methods and Programs in Biomedicine. 2019 ; 卷 173. 頁 109-117.
@article{1c9fe98620e9403788cfbce771c30065,
title = "An artificial intelligence approach to early predict non-ST-elevation myocardial infarction patients with chest pain",
abstract = "Background and Aims: Hospital admission rate for the patients with chest pain has already been increased worldwide but no existing risk score has been designed to stratify non-ST-elevation myocardial infarction (NSTEMI) from non-cardiogenic chest pain. Clinical diagnosis of chest pain in the emergency department is always highly subjective and variable. We, therefore, aimed to develop an artificial intelligence approach to predict stable NSTEMI that would give valuable insight to reduce misdiagnosis in the real clinical setting. Methods: A standard protocol was developed to collect data from chest pain patients who had visited the emergency department between December 2016 and February 2017. All the chest pain patients with aged <20 years were primarily included in this study. However, STEMI, previous history of ACS, and out-of-hospital cardiac arrest were excluded from our study. An artificial neural network (ANN) model was then developed to predict NSTEMI patients. The accuracy, sensitivity, specificity, and receiver operating characteristic curve was used to measure the performance of this model. Results: A total of 268 chest pain patients were included in this study; of those, 47 (17.5{\%}) was stable NSTEMI, and 221 (82.5{\%}) was unstable angina patients. Serval risk factors such as cardiac risk factor, systolic blood pressure, hemoglobin, corrected QT interval (QTc), PR interval, glutamic-oxaloacetic transaminase, glutamic pyruvic transaminase and troponin were independently associated with stable NSTEMI. The area under the receiver operating characteristic (AUROC) and accuracy of ANN were 98.4, and 92.86. Additionally, the sensitivity, specificity, positive predictive value, and negative predictive value of the ANN model was 90.91, 93.33, 76.92, and 97.67 respectively. Conclusion: Our prediction model showed a higher accuracy to predict NSTEMI patients. This model has a potential application in disease detection, monitoring, and prognosis of chest pain at risk of AMI.",
keywords = "Acute coronary syndrome, Artificial neural network, Chest pain, Non-ST elevated MI",
author = "Wu, {Chieh Chen} and Hsu, {Wen Ding} and Islam, {Md Mohaimenul} and Poly, {Tahmina Nasrin} and Yang, {Hsuan Chia} and Nguyen, {Phung Anh  (Alex)} and Wang, {Yao Chin} and Li, {Yu Chuan  (Jack)}",
year = "2019",
month = "5",
day = "1",
doi = "10.1016/j.cmpb.2019.01.013",
language = "English",
volume = "173",
pages = "109--117",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - An artificial intelligence approach to early predict non-ST-elevation myocardial infarction patients with chest pain

AU - Wu, Chieh Chen

AU - Hsu, Wen Ding

AU - Islam, Md Mohaimenul

AU - Poly, Tahmina Nasrin

AU - Yang, Hsuan Chia

AU - Nguyen, Phung Anh  (Alex)

AU - Wang, Yao Chin

AU - Li, Yu Chuan  (Jack)

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Background and Aims: Hospital admission rate for the patients with chest pain has already been increased worldwide but no existing risk score has been designed to stratify non-ST-elevation myocardial infarction (NSTEMI) from non-cardiogenic chest pain. Clinical diagnosis of chest pain in the emergency department is always highly subjective and variable. We, therefore, aimed to develop an artificial intelligence approach to predict stable NSTEMI that would give valuable insight to reduce misdiagnosis in the real clinical setting. Methods: A standard protocol was developed to collect data from chest pain patients who had visited the emergency department between December 2016 and February 2017. All the chest pain patients with aged <20 years were primarily included in this study. However, STEMI, previous history of ACS, and out-of-hospital cardiac arrest were excluded from our study. An artificial neural network (ANN) model was then developed to predict NSTEMI patients. The accuracy, sensitivity, specificity, and receiver operating characteristic curve was used to measure the performance of this model. Results: A total of 268 chest pain patients were included in this study; of those, 47 (17.5%) was stable NSTEMI, and 221 (82.5%) was unstable angina patients. Serval risk factors such as cardiac risk factor, systolic blood pressure, hemoglobin, corrected QT interval (QTc), PR interval, glutamic-oxaloacetic transaminase, glutamic pyruvic transaminase and troponin were independently associated with stable NSTEMI. The area under the receiver operating characteristic (AUROC) and accuracy of ANN were 98.4, and 92.86. Additionally, the sensitivity, specificity, positive predictive value, and negative predictive value of the ANN model was 90.91, 93.33, 76.92, and 97.67 respectively. Conclusion: Our prediction model showed a higher accuracy to predict NSTEMI patients. This model has a potential application in disease detection, monitoring, and prognosis of chest pain at risk of AMI.

AB - Background and Aims: Hospital admission rate for the patients with chest pain has already been increased worldwide but no existing risk score has been designed to stratify non-ST-elevation myocardial infarction (NSTEMI) from non-cardiogenic chest pain. Clinical diagnosis of chest pain in the emergency department is always highly subjective and variable. We, therefore, aimed to develop an artificial intelligence approach to predict stable NSTEMI that would give valuable insight to reduce misdiagnosis in the real clinical setting. Methods: A standard protocol was developed to collect data from chest pain patients who had visited the emergency department between December 2016 and February 2017. All the chest pain patients with aged <20 years were primarily included in this study. However, STEMI, previous history of ACS, and out-of-hospital cardiac arrest were excluded from our study. An artificial neural network (ANN) model was then developed to predict NSTEMI patients. The accuracy, sensitivity, specificity, and receiver operating characteristic curve was used to measure the performance of this model. Results: A total of 268 chest pain patients were included in this study; of those, 47 (17.5%) was stable NSTEMI, and 221 (82.5%) was unstable angina patients. Serval risk factors such as cardiac risk factor, systolic blood pressure, hemoglobin, corrected QT interval (QTc), PR interval, glutamic-oxaloacetic transaminase, glutamic pyruvic transaminase and troponin were independently associated with stable NSTEMI. The area under the receiver operating characteristic (AUROC) and accuracy of ANN were 98.4, and 92.86. Additionally, the sensitivity, specificity, positive predictive value, and negative predictive value of the ANN model was 90.91, 93.33, 76.92, and 97.67 respectively. Conclusion: Our prediction model showed a higher accuracy to predict NSTEMI patients. This model has a potential application in disease detection, monitoring, and prognosis of chest pain at risk of AMI.

KW - Acute coronary syndrome

KW - Artificial neural network

KW - Chest pain

KW - Non-ST elevated MI

UR - http://www.scopus.com/inward/record.url?scp=85063111784&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063111784&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2019.01.013

DO - 10.1016/j.cmpb.2019.01.013

M3 - Article

VL - 173

SP - 109

EP - 117

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

SN - 0169-2607

ER -