TY - GEN
T1 - Improving the Detection of Acute Coronary Syndrome Using Machine Learning of Blood Biomarkers
AU - Rjoob, Khaled
AU - McGilligan, V. E.
AU - Bond, RR
AU - Watterson, Steven
AU - El Chemaly, Melody
AU - Mc Allister, Roisin
AU - De Melo Malaquias, Tiago
AU - Leslie, Stephen James
AU - Knoery, Charles
AU - Iftikhar, Aleeha
AU - McShane, Anne
AU - Bjourson, AJ
AU - Peace, Aaron
PY - 2021/2/10
Y1 - 2021/2/10
N2 - Background: Acute coronary syndrome (ACS) is one of the main causes of death worldwide. The 12-lead electrocardiogram (ECG) is used to help diagnose ACS, along with clinical risk factors (smoking, diabetes mellitus, hypertension, hscTn and positive family history of ACS. These methods however are associated with many limitations resulting in variable sensitivity/specificity. The aim of this study was to use a machine learning approach to develop an optimum panel of blood protein biomarkers capable of independently diagnosing ACS. Methods: A hybrid feature selection and ML prediction algorithms including two classifiers: 1) decision tree (DT) and 2) logistic regression were applied to protein biomarkers (327 proteins) collected from patients with ACS n=91 or non-ACS n=97. Results: Using this approach, 20 proteins out of 327 proteins were able to accurately distinguish between ACS and non-ACS (logistic regression ROC-AUC=0.8 and accuracy=82.5% and DT ROC-AUC=0.6 and accuracy=64.9%. Conclusion: Logistic regression obtained a higher performance compared to DT and showed promising results uncovering a panel of 20 protein biomarkers which included those associated with progressive atherosclerotic plaques, myocardial injury and inflammation. This approach was able to accurately discriminate between patients with ACS and non-ACS.
AB - Background: Acute coronary syndrome (ACS) is one of the main causes of death worldwide. The 12-lead electrocardiogram (ECG) is used to help diagnose ACS, along with clinical risk factors (smoking, diabetes mellitus, hypertension, hscTn and positive family history of ACS. These methods however are associated with many limitations resulting in variable sensitivity/specificity. The aim of this study was to use a machine learning approach to develop an optimum panel of blood protein biomarkers capable of independently diagnosing ACS. Methods: A hybrid feature selection and ML prediction algorithms including two classifiers: 1) decision tree (DT) and 2) logistic regression were applied to protein biomarkers (327 proteins) collected from patients with ACS n=91 or non-ACS n=97. Results: Using this approach, 20 proteins out of 327 proteins were able to accurately distinguish between ACS and non-ACS (logistic regression ROC-AUC=0.8 and accuracy=82.5% and DT ROC-AUC=0.6 and accuracy=64.9%. Conclusion: Logistic regression obtained a higher performance compared to DT and showed promising results uncovering a panel of 20 protein biomarkers which included those associated with progressive atherosclerotic plaques, myocardial injury and inflammation. This approach was able to accurately discriminate between patients with ACS and non-ACS.
KW - Acute Coronary Syndrome
KW - Machine Learning
KW - Biomarker discovery
UR - https://ieeexplore.ieee.org/document/9344422
UR - http://www.scopus.com/inward/record.url?scp=85100924895&partnerID=8YFLogxK
U2 - 10.22489/CinC.2020.337
DO - 10.22489/CinC.2020.337
M3 - Conference contribution
SN - 978-1-7281-1105-6
T3 - Computing in Cardiology
BT - 2020 Computing in Cardiology, CinC 2020
CY - Rimini, Italy
T2 - Computing in Cardiology 2020
Y2 - 13 September 2020 through 16 September 2020
ER -