ECG Signal Analysis for Troponin Level Assessment and Coronary Artery Disease Detection: The NEEDED Study 2014

Physical exercise is widely recognized as beneficial to the cardiovascular system. However, intense exercise may also carry fatal risk. Investigation of this phenomenon is one of the primary purposes of the North Sea Race Endurance Exercise Study (NEEDED). This paper describes analysis of electrocardiograms (ECG) and heart rate signals collected from amateur athletes, participants of the race, to facilitate noninvasive estimation of the level of cardiac troponin I (cardiovas-cular risk biomarker) and detection of coronary artery disease (CAD). It was demonstrated that the combination of ECG and heart rate parameters can predict CAD with high specificity (up to 98 %) and relatively good sensitivity. Moreover, while troponin level assessment is unlikely to be reliably performed using regression techniques, it might be possible using a new, probabilistic classification-based model. Further evaluation of the latter requires the use of additional data, which is one of possible directions for the future work.

[1]  Rik Willems,et al.  Which QT Correction Formulae to Use for QT Monitoring? , 2016, Journal of the American Heart Association.

[2]  K. Dickstein,et al.  Highly increased Troponin I levels following high-intensity endurance cycling may detect subclinical coronary artery disease in presumably healthy leisure sport cyclists: The North Sea Race Endurance Exercise Study (NEEDED) 2013 , 2017, European journal of preventive cardiology.

[3]  K. Oskal Myocardial damage during mountain bike race - an analysis of data from Nordsjørittet 2014 (NEEDED study) , 2016 .

[4]  J. Sarko,et al.  Cardiac troponins. , 2002, The Journal of emergency medicine.

[5]  K. George,et al.  The impact of exercise intensity on the release of cardiac biomarkers in marathon runners , 2011, European Journal of Applied Physiology.

[6]  S. Solomon,et al.  Prognostic value of cardiac troponin I measured with a highly sensitive assay in patients with stable coronary artery disease. , 2013, Journal of the American College of Cardiology.

[7]  Tomasz Wiktorski,et al.  The North Sea Bicycle Race ECG project: Time-domain analysis , 2017, Conference on Computer Science and Information Systems.

[8]  A. Sahlén,et al.  Heart rate and its variability in response to running-associations with troponin. , 2014, Medicine and science in sports and exercise.

[9]  K. George,et al.  Exercise-induced cardiac troponin elevation: evidence, mechanisms, and implications. , 2010, Journal of the American College of Cardiology.

[10]  Abdelfatah Charef,et al.  PVC discrimination using the QRS power spectrum and self-organizing maps , 2009, Comput. Methods Programs Biomed..

[11]  E. Pietka,et al.  Information Technologies in Biomedicine , 2008 .

[12]  Randal S. Olson,et al.  Automating Biomedical Data Science Through Tree-Based Pipeline Optimization , 2016, EvoApplications.

[13]  K. George,et al.  Predictors of cardiac troponin release after a marathon. , 2015, Journal of science and medicine in sport.

[14]  T. Villines,et al.  Marathon running as a cause of troponin elevation: a systematic review and meta-analysis. , 2010, Journal of interventional cardiology.

[15]  A. Jaffe,et al.  Troponin: the biomarker of choice for the detection of cardiac injury , 2005, Canadian Medical Association Journal.

[16]  Hirofumi Tanaka,et al.  Age-predicted maximal heart rate revisited. , 2001, Journal of the American College of Cardiology.

[17]  A. Legaz-Arrese,et al.  Cardiac Biomarkers and Exercise Duration and Intensity During a Cycle-Touring Event , 2009, Clinical journal of sport medicine : official journal of the Canadian Academy of Sport Medicine.