A Machine Learning Algorithm for Risk Prediction of Acute Coronary Syndrome

Luis Polero, Cristian M. Garmendia, Raúl E. Echegoyen, Alberto Alves de Lima, Felipe Bertón, Florencia Lambardi, Paula Ariznavarreta, Roberto Campos, Juan Pablo Costabel

Abstract


Background: Chest pain represents one of the most common reasons for consultation in emergency medical services (EMS). A diagnostic strategy using objective and subjective information about the characteristics of chest pain has not been identified yet. Objective: The aim of this study was to evaluate the performance of a machine learning classifier to predict the risk for non-ST segmentelevation acute coronary syndrome (ACS) in patients consulting an EMS due to chest pain. Methods: A total of 161 patients consulting the EMS due to chest pain were analyzed. Both objective and subjective variables aboutthe characteristics of chest pain were recorded using a machine learning classifier. Results: Mean age was 57.43±12 years, 75% were men and 16% had history of cardiovascular disease. Acute coronary syndrome was present in 57.8% of cases with an incidence of acute myocardial infarction of 29.8%. Among the latter 35% required percutaneous coronary intervention and 9.9% myocardial revascularization surgery during the 30-day follow-up. A Random Forest Classifier was used as model of classification, with an area under the ROC curve of 0.8991, sensitivity of 0.8552, specificity of 0.8588 and accuracy of 0.8441. The most significant predictors in the model were weight (p = 0.002), age (p = 5.011e-07), pain intensity (p = 3.0679e-05),systolic blood pressure (p = 0.6068) and the subjective characteristics of pain (p = 1.590 e-04).Conclusions: Machine learning classifiers are a useful and effective tool to predict an acute coronary syndrome at 30-day follow-up.

References


Cortés M, Lambardi F, Ariznavarreta P, Resi S, Arbucci R, Borda M, et al. Utilidad del score HEART con troponina T de alta sensibilidad para la evaluación de pacientes con dolor torácico. Rev Argent Cardiol 2018;86:333-7. https://doi.org/10.7775/rac.v86.i5.13326

Costabel J, Cortés M, Lambardi F, Ariznavarreta P, Resi S, Campos R, et al. Usefulness of the HEART score without troponin value to stratify patients with suspected non-ST elevation acute coronary syndrome. J Am Coll Cardiol 2019;73: Supplement 1. https://doi. org/10.1016/S0735-1097(19)30879-4

Panju, AA, Hemmelgarn BR, Guyatt GH, Simel DL. Is This Patient Having a Myocardial Infarction? JAMA 1998;280:1256. https://doi.org/10.1001/jama.280.14.1256

Chun AA, McGee S.R Bedside diagnosis of coronary artery disease:A systematic review. Am J Med 2004;117:334-43. https://doi.org/10.1016/j.amjmed.2004.03.021

Dezman ZD, Mattu A, Body R. Utility of the History and Physical Examination in the Detection of Acute Coronary Syndromes in Emergency Department Patients. West J Emerg Med. 2017;18:752-60

Goodacre S, Locker T, Morris F, Campbell S. How useful are clinical features in the diagnosis of acute, undifferentiated chest pain? Acad Emerg Med 2002;9:203-8. https://doi.org/10.1197/aemj.9.3.203

Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: Machine Learning in Python. Journ of Mach Lear Res 2011;12:2825-30

Goodfellow Y, Bengio Y, Courville A. Deep Learning. Cambridge, MA MIT Press; 2017.

VanHouten JP, Starmer JM, Lorenzi NM, Maron DJ, Lasko TA. Machine learning for risk prediction of acute coronary syndrome. AMIA Annu Symp Proc 2014:1940-9. eCollection 2014.

Antman EM, Cohen M, Bernink PJ, McCabe CH, Horacek T, Papuchis G, et al. The TIMI risk score for unstable angina/non-ST elevation MI: A method for prognostication and therapeutic decision making. JAMA 2000;284:835-42. https://doi.org/10.1001/jama.284.7.835

Elbarouni B, Goodman SG, Yan RT, Welsh RC, Kornder JM, Deyoung JP, et al; Canadian Global Registry of Acute Coronary Events (GRACE/GRACE(2)) Investigators. Validation of the Global Registry of Acute Coronary Event (GRACE) risk score for in-hospital mortality in patients with acute coronary syndrome in Canada. Am Heart J 2009;158:392-9. https://doi.org/10.1016/j.ahj.2009.06.010

Weng SF, Reps J, Kai J, Garibaldi JM, Qureshi N. Can machine learning improve cardiovascular risk prediction using routine clinicaldata? PLoS One. 2017;12:e0174944

https://doi.org/10.1371/journal.pone.0174944

Zhao Q, Zhang L. ECG feature extraction and classification using wave let trans-form and support vector machines. Int Conf Neural Net Brain 2005;2:1089-92.

Afsar FA, Arif M, Yang J. Detection of ST segment deviation episodes in ECG using KLT with an ensemble neural classifier. PhysiolMeas 2008;29:747-60. https://doi.org/10.1088/0967-3334/29/7/004

van Rosendael AR, Maliakal G, Kolli KK, Beecy A, Al’Aref SJ, Dwivedi A, et al. Maximization of the usage of coronary CTA derived plaque information using a machine learning based algorithm to improve risk stratification; insights from the CONFIRM registry. J Cardiovasc Comput Tomogr 2018;12:204-9. https://doi.org/10.1016/j.jcct.2018.04.011

Arsanjani R, Xu Y, Dey D, Vahistha V, Shalev A, Nakanishi R,et al. Improved accuracy of myocardial perfusion SPECT for

detection of coronary artery disease by machine learning in a large population. J Nucl Cardiol 2013;20:553-62. https://doi.org/10.1007/s12350-013-9706-2

Scavuzzo JM, Trucco F, Espinosa M, Tauro CB, Abril M, Scavuzzo CM, Frery AC. Modeling Dengue vector population using remotelysensed data and machine learning. Acta Trop 2018;185:167-75.https://doi.org/10.1016/j.actatropica.2018.05.003


Full Text

Refbacks

  • There are currently no refbacks.


Licencia Creative Commons
The documents published in this journal are under the licencia Creative Commons Atribución-NoComercial-Compartir-Igual 2.5 Argentina.

Revista argentina de cardiología. ISSN en línea 1850-3748. Argentine journal of cardiology (English ed. Online ISSN 2314-2286) Sociedad Argentina de Cardiología. Azcuénaga 980 (C1115AAD),Ciudad Autónoma de Buenos Aires, República Argentina. Tel. (54 11) 4961-6027/8/9 Fax: 4961-6020 www.sac.org.ar revista@sac.org.ar