Diagnostic Value of Magnetocardiography to Detect Abnormal Myocardial Perfusion: A Pilot Study

Huan Zhang; Zhao Ma; Hongzhi Mi; Jian Jiao; Wei Dong; Shuwen Yang; Linqi Liu; Shu Zhou; Lanxin Feng; Xin Zhao; Xueyao Yang; Chenchen Tu; Xiantao Song; Hongjia Zhang

doi:10.31083/j.rcm2510379

Diagnostic Value of Magnetocardiography to Detect Abnormal Myocardial Perfusion: A Pilot Study

Rev Cardiovasc Med. 2024 Oct 23;25(10):379. doi: 10.31083/j.rcm2510379. eCollection 2024 Oct.

Authors

Huan Zhang¹, Zhao Ma¹, Hongzhi Mi², Jian Jiao², Wei Dong², Shuwen Yang¹, Linqi Liu¹, Shu Zhou¹, Lanxin Feng¹, Xin Zhao¹, Xueyao Yang¹, Chenchen Tu¹, Xiantao Song¹, Hongjia Zhang³

Affiliations

¹ Department of Cardiology, Beijing Anzhen Hospital, Capital Medical University, 100029 Beijing, China.
² Department of Nuclear Medicine, Beijing Anzhen Hospital, Capital Medical University, 100029 Beijing, China.
³ Department of Cardiac Surgery, Beijing Anzhen Hospital, Capital Medical University, 100029 Beijing, China.

Abstract

Background: Magnetocardiography (MCG) is a novel non-invasive technique that detects subtle magnetic fields generated by cardiomyocyte electrical activity, offering sensitive detection of myocardial ischemia. This study aimed to assess the ability of MCG to predict impaired myocardial perfusion using single-photon emission computed tomography (SPECT).

Methods: A total of 112 patients with chest pain underwent SPECT and MCG scans, from which 65 MCG output parameters were analyzed. Using least absolute shrinkage and selection operator (LASSO) regression to screen for significant MCG variables, three machine learning models were established to detect impaired myocardial perfusion: random forest (RF), decision tree (DT), and support vector machine (SVM). The diagnostic performance was evaluated based on the sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristic curve (AUC).

Results: Five variables, the ratio of magnetic field amplitude at R-peak and positive T-peak (RoART+), R and T-peak magnetic field angle (RTA), maximum magnetic field angle (MAmax), maximum change in current angle (CCAmax), and change positive pole point area between the T-wave beginning and peak (CPPPATbp), were selected from 65 automatic output parameters. RTA emerged as the most critical variable in the RF, DT, and SVM models. All three models exhibited excellent diagnostic performance, with AUCs of 0.796, 0.780, and 0.804, respectively. While all models showed high sensitivity (RF = 0.870, DT = 0.826, SVM = 0.913), their specificity was comparatively lower (RF = 0.500, DT = 0.300, SVM = 0.100).

Conclusions: Machine learning models utilizing five key MCG variables successfully predicted impaired myocardial perfusion, as confirmed by SPECT. These findings underscore the potential of MCG as a promising future screening tool for detecting impaired myocardial perfusion.

Clinical trial registration: ChiCTR2200066942, https://www.chictr.org.cn/showproj.html?proj=187904.

Keywords: chronic coronary syndromes; machine learning algorithm; magnetocardiography; myocardial perfusion imaging.

Grants and funding

This study was supported by Beijing Hospitals Authority ‘sailing' Program (grant number YGLX202323), Beijing Nova Program (grant number 20220484222), Coordinated innovation of scientific and technological in Beijing-Tianjin-Hebei Region (grant number Z231100003923008), Beijing Hospitals Authority's Ascent Plan (grant number DFL20220603), Project of The Beijing Lab for Cardiovascular Precision Medicine (grant number PXM2018_014226_000013) and High-level public health technical talent construction project of Beijing Municipal Health Commission (Leading Talent-02-01).