Clinical Validation of Machine Learning for Automatic Analysis of Multichannel Magnetocardiography

Abstract

Abstract. Magnetocardiographic (MCG) mapping measures magnetic fields generated by the electrophysiological activity of the heart. Quantitative analysis of MCG ventricular repolarization (VR) parameters may be useful to detect myocardial ischemia in patients with apparently normal ECG. However, manual calculation of MCG VR is time consuming and can be dependent on the examiner's experience. Alternatively, the use of machine learning (ML) has been proposed recently to automate the interpretation of MCG recordings and to minimize human interference with the analysis. The aim of this study was to validate the predictive value of ML techniques in comparison with interactive, computer-aided, MCG analysis.ML testing was done on a set of 140 randomly analysed MCG recordings from 74 subjects: 41 patients with ischemic heart disease (IHD) (group 1), 32 of them untreated (group 2), and 33 subjects without any evidence of cardiac disease (group 3). For each case at least 2 MCG datasets, recorded in different sessions, were analysed.Two ML techniques combined identified abnormal VR in 25 IHD patients (group 1) and excluded VR abnormalities in 28 controls (group 3) providing 75% sensitivity, 85% specificity, 83% positive predictive value, 78% negative predictive value, 80% predictive accuracy This result was for the most part in agreement, but statistically better than that obtained with interactive analysis.This study confirms that ML, applied on MCG recording at rest, has a predictive accuracy of 80% in detecting electrophysiological alterations associated with untreated IHD. Further work is needed to test the ML capability to differentiate VR alterations due to IHD from those due to non-ischemic cardiomyopathies.

Contactless magnetocardiographic mapping in anesthetized Wistar rats: evidence of age-related changes of cardiac electrical activity

“…T-wave extrema MF dynamics analysis was automatically calculated in any floating 30-ms time windows during JT peak (starting when MF strength was equal to one-third of that at Tpeak and continuing until Tpeak) as the following three parameters (15,31,54): 1) change in the angle between the positive pole and the negative pole, which, in humans, is abnormal if Ͼ45°; 2) distance between the positive pole and the negative pole, which, in humans, is abnormal if Ͼ20 mm; and 3) ratio of strength of the positive pole to strength of the negative pole, which, in humans, is abnormal if Ͼ0.3.…”

“…This suggests that such parameters, which have already proven sensitive for diagnosis of myocardial ischemia and other cardiomyopathies in humans, even in the absence of ECG alteration (31,36,37,54,64,71), could be useful to reveal VR abnormalities in animal models of cardiomyopathy, independently of sex and age.…”

Reproducibility of Quantitative Estimate of Magnetocardiographic Ventricular Depolarization and Repolarization Parameters in Healthy Subjects and Patients with Coronary Artery Disease

“…8,40,6 The signal to noise levels from the unshielded environment are mostly much lower than the signal to be measured, especially during S-T segment, 3 and even the signal to noise level of the shielding environment used in this study was not good enough for the S-T segment. To get the better reliability and the reproducibility and to increase its clinical value, the minimally shielded environment is highly recommended until revealing the firm clinical evidence of CAD using MCG system.…”

“…7,10,8,40 Clinically successful areas of MCG are the detection of myocardial ischemia and viability, arrhythmogenic risk assessment, source localization and imaging of arrhythmogenic mechanisms, multimodal electroanatomical integration, and fetal MCG. 7 In particular, the early detection of ischemic heart disease and myocardial viability are major foci for the MCG system as an innovative clinical tool.…”

Predictive value of rest magnetocardiography in patients with stable angina

“…A 36-channel DC-SQUID MCG system (CardioMag Imaging Inc) was used for MCG (intrinsic sensitivity: 20 fT/√Hz) [7]. One reference ECG lead (lead I) was simultaneously recorded with MCG signals.…”