Detection of coronary artery disease in patients with chest pain: A machine learning model based on magnetocardiography parameters
The DOI matches its Crossref record; 20 of the 21 references it cites were found in a registry or an index.
Abstract
BACKGROUD: Patients with chest pain and suspected of coronary artery disease(CAD) need further test to confirm the diagnosis. Magnetocardiography (MCG) is a non-invasive and emission-free technology which can detect and measure the weak magnetic fields created by the electrical activity of the heart. OBJECTIVE: This study aimed to investigate the usefulness of the 10 MCG parameters to detect CAD in patients with chest pain by means of a machine learning method of multilayer perceptron(MLP) neural network. METHODS: 209 patients who were suffering from chest pain and suspected of CAD were enrolled in this cross-sectional study. In all patients, 12-lead electrocardiography(ECG) and MCG test were performed before percutaneous coronary angiography(PCA). 10 MCG parameters were analyzed by MLP neural networks. RESULTS: 11 diagnostic models(M1 to M11) were established after MLP analysis. The accuracies ranged from 71.2% to 90.5%. Two models(M10 and M11) were further analyzed. The accuracy, sensitivity, specificity, PPV, NPV, PLR and NLR were 89.5%, 89.8%, 88.9%, 92.7%, 84.7%, 11.10 and 0.11, of M10, and were 90.0%, 91.4%, 87.7%, 92.1%, 86.6%, 7.43 and 0.10, of M11. CONCLUSIONS: By a method of MLP neural network, MCG is applicable in identifying CAD in patients with chest pain, which seems beneficial for detection of CAD.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Collectively, these studies established feasibility but were constrained by handcrafted features, small datasets, and limited external validation [69,70,71,72,73] [Table 2].”
Citations
Cites
Roffi, M., Patrono, C., Collet, J.-P., Mueller, C., Valgimigli, M., Andreotti, F., Bax, J. J., Borger, M. A., Brotons, C., Chew, D. P., et al. (2016) · European Heart Journal · doi:10.1093/eurheartj/ehv320 · Cited by 8,261
Lower bounds on sample size in structural equation modeling
Christopher Westland, J. (2010) · Electronic Commerce Research and Applications · doi:10.1016/j.elerap.2010.07.003 · Cited by 1,846 · cited 1×
“The number of enrollments and the generated results has statistical power of analysis beyond 90% [15].”
Magnetocardiography Predicts Coronary Artery Disease in Patients with Acute Chest Pain
Park, J., Hill, P. M., Chung, N., Hugenholtz, P. G., & Jung, F. (2005) · Annals of Noninvasive Electrocardiology · doi:10.1111/j.1542-474x.2005.00634.x · Cited by 109 · cited 1×
“Studies have shown that MCGs was superior to conventional ECG for identifying myocardial ischemia or CAD [11, 12].”
Pena, M. E., Pearson, C. L., Goulet, M. P., Kazan, V. M., DeRita, A. L., Szpunar, S. M., & Dunne, R. B. (2020) · IJC Heart & Vasculature · doi:10.1016/j.ijcha.2019.100466 · Cited by 70
HAILER, B., CHAIKOVSKY, I., AUTH‐EISERNITZ, S., SCHÄFER, H., & VAN LEEUWEN, P. (2005) · Pacing and Clinical Electrophysiology · doi:10.1111/j.1540-8159.2005.09318.x · Cited by 54 · cited 1×
“%) in a population of 177 patients with angiographically documented CAD (stenosis ≥ 50%), 123 symptomatic patients without hemodynamically relevant stenosis (non-CAD) and 117 healthy subjects [20].”
Lim, H. K., Kwon, H., Chung, N., Ko, Y.-G., Kim, J.-M., Kim, I.-S., & Park, Y.-K. (2009) · The American Journal of Cardiology · doi:10.1016/j.amjcard.2008.10.013 · Cited by 52 · cited 4×
“…usefulness of 10 parameters generated from magnetic field map and current density maps to diagnose unstable angina pectoris and non-ST elevation myocardial infarction, and the combination of the binary boundaries of the 10 parameters had 96.4% sensitivity and 85% specificity to detect NSTEMI [13].”
InfluentialKwon, H., Kim, K., Lee, Y.-H., Kim, J.-M., Yu, K. K., Chung, N., & Ko, Y.-G. (2010) · Circulation Journal · doi:10.1253/circj.cj-09-0975 · Cited by 47 · cited 3×
“…study of their group showed a sensitivity of 84.0% and a specificity of 85.0% of these parameters to identify CAD patients(a stenosis (cid:2) 50% in at least one of 16 segments of the 3 major coronary arteries and their branches), when ECG had a sensitivity of 44.7% and a specificity of 89.8% [10].”
InfluentialClinical utility of magnetocardiography in cardiology for the detection of myocardial ischemia
Camm, A. J., Henderson, R., Brisinda, D., Body, R., Charles, R. G., Varcoe, B., & Fenici, R. (2019) · Journal of Electrocardiology · doi:10.1016/j.jelectrocard.2019.07.009 · Cited by 42 · cited 1×
“MCG technology and diagnostic criteria for CAD have evolved during several decades, but there were still numerous limitations restrict the application of MCG in clinical practice [16].”
Park, J.-W., & Jung, F. (2004) · Biomedizinische Technik/Biomedical Engineering · doi:10.1515/bmt.2004.050 · Cited by 37
Goernig, M., Liehr, M., Tute, C., Schlosser, M., Haueisen, J., Figulla, H. R., & LEDER, U. (2008) · Annals of Biomedical Engineering · doi:10.1007/s10439-008-9598-5 · Cited by 25 · cited 1×
“Studies have shown that MCGs was superior to conventional ECG for identifying myocardial ischemia or CAD [11, 12].”
Cited by
Garavand, A., Behmanesh, A., Aslani, N., Sadeghsalehi, H., & Ghaderzadeh, M. (2023) · International Journal of Intelligent Systems · doi:10.1155/2023/6442756 · Cited by 71
Magnetocardiography for the detection of myocardial ischemia
Her, A., Dischl, D., Kim, Y. H., Kim, S., & Shin, E. (2023) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2023.1242215 · Cited by 68
Tao, R., Zhang, S., Wang, Y., Mi, X., Ma, J., Shen, C., & Zheng, G. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3128169 · Cited by 31
Han, X., Pang, J., Xu, D., Wang, R., Xie, F., Yang, Y., Sun, J., Li, Y., Li, R., Yin, X., et al. (2023) · Physiological Measurement · doi:10.1088/1361-6579/ad0f70 · Cited by 25
Samaras, A.-D., Moustakidis, S., Apostolopoulos, I. D., Papandrianos, N. I., & Papageorgiou, E. I. (2023) · Scientific Reports · doi:10.1038/s41598-023-33500-9 · Cited by 24
Han, X., Pang, J., Xu, D., Xie, F., Li, Y., Xiang, M., Sun, J., Chen, Y., & Ning, X. (2025) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2025.108764 · Cited by 21
Botha, N. N., Ansah, E. W., Segbedzi, C. E., Dumahasi, V. K., Maneen, S., Kodom, R. V., Tsedze, I. S., Akoto, L. A., & Atsu, F. S. (2024) · BMC Digital Health · doi:10.1186/s44247-024-00091-y · Cited by 20
“It is widely reported [44, 50, 58, 62, 63, 65–67, 92, 110, 115] that AI applications would significantly improve the accuracy of clinical diagnosis.”
BackgroundInfluentialHu, Z., Lin, Y., Ye, K., & Lin, Q. (2022) · IEEE Access · doi:10.1109/access.2022.3193769 · Cited by 13
Tao, R., Zhang, S., Zhang, R., Shen, C., Ma, J., Cui, J., Chen, Y., Wang, B., Li, H., Xie, X., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-90615-x · Cited by 14
“Huang et al. 25 investigated the usefulness of 10 MCG parameters to detect coronary artery disease (CAD) in 209 patients with chest pain by means of a multilayer perceptron (ML) neural network.”
Advances of magnetocardiography in application of adult and fetal cardiac diseases
Li, J., Shen, Y., Shen, C., Ning, X., & Xiang, M. (2025) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2025.1522467 · Cited by 15
“Bayesian neural networks and multilayer perceptron demonstrated high sensitivity, making them suitable for high-risk population screening (51 – 54).”
Multi-channel MCG signals filtering method based on multivariate variational mode decomposition
Yang, K. Y., Xu, T., Pan, D., Zhang, Z., Wang, H., & Kong, X. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106806 · Cited by 13
Khan, W. U., Alissa, M., Ma, H., Bhatti, U. A., Alghamdi, A. A., Alshehri, M. A., & Albelasi, A. (2025) · Materials Today Bio · doi:10.1016/j.mtbio.2025.102259 · Cited by 15
“In addition to ECG-based approaches, Huang et al. [170] explored the utility of magnetocardiogram (MCG) parameters for detecting coronary artery disease (CAD).”
Introduction to biomedical signals and biomedical imaging
Popov, A., & Ivanko, K. O. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-19073-5.00013-6 · Cited by 8
Xu, Y., Han, X., Guo, M., Li, R., Dong, Y., Fan, J., Yin, X., Xie, F., Pang, J., & Chen, Y. (2023) · Emergency and Critical Care Medicine · doi:10.1097/ec9.0000000000000085 · Cited by 8
Automated Acute Myocardial Infarction Detection Using Machine Learning From Phonocardiogram
Puspasari, I., Ahmadi, N., Pramudyo, M., Watanabe, N., Mengko, T. L. R., Setiawan, A. W., & Adiono, T. (2024) · IEEE Access · doi:10.1109/access.2024.3491073 · Cited by 7
Samaras, A.-D., Moustakidis, S., Apostolopoulos, I. D., Papageorgiou, E. I., & Papandrianos, N. I. (2023) · Applied Sciences · doi:10.3390/app13148120 · Cited by 11
Bao, N., Han, T., Shan, D., Miao, Y., Cui, J., Liu, L., Wang, X., Tian, C., & Tian, F. (2026) · Cardiology · doi:10.1159/000550445 · Cited by 3
Ma, C., Pang, J., Wang, R., Xu, D., Xiang, M., & Wang, Z. (2024) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2024.3486119 · Cited by 3
“However, with the rise in the number of MCG channels—from 15 channels [10], 16 channels [11], 36 channels [12], 37 channels [13], 64 channels [6], to as many as 81 channels [14]—the volume of available cardiac information obtained also escalates.”
Palantzas, A., & Anagnostouli, M. (2026) · Sensors · doi:10.3390/s26051738 · Cited by 1
Bai, G.-H., Cui, Y., Huang, Z., Zhang, Y., Ren, Q., Pang, J., & Shang, R. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.110000 · Cited by 1
Non-Invasive Detection of Coronary Artery Disease Symptoms using Cardiocare Application
Garapati, N. S., Seelam, K., Sateesh, J., Kasani, T., & Palanki, S. S. (2023) · International Conference on Computing Methodologies and Communication (ICCMC) · doi:10.1109/iccmc56507.2023.10084255 · Cited by 1
The Physical Origin of Waves in Magnetocardiography Technique and their Applications in Imaging
Fioranelli, M., Roccia, M. G., Beesham, A., Flavin, D., & Shoorvazi, S. (2022) · NeuroQuantology · doi:10.14704/nq.2022.20.5.nq22294 · Cited by 2
Wang, P., & Sun, X. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/5473346
Recent advances in magnetocardiography
Kong, X., Yang, K., Zhang, Z., Pan, D., & Guo, C. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-41624-8.00001-2 · Cited by 2
Intelligent Diagnosis of Coronary Artery Disease Using Radiomic Features from Magnetocardiography
Yan, M., Han, X., Xiang, M., & Li, J. (2025) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist66504.2025.11268437
Li, J. (2025) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist66504.2025.11268424
“Bayesian neural networks and multilayer perceptron demonstrated high sensitivity, making them suitable for high-risk population screening [14-17].”
Establishment of magnetocardiogromics platform with reference range for normal magnetocardiogram
Guo, Y., Ma, J., Shen, H., Zhang, G., Zang, J., Zhang, Y., & Shen, C. (2025) · BMC Medical Imaging · doi:10.1186/s12880-025-02010-7
Jiang, Y., Xu, S., Zhao, L., & Zhou, Y. F. (2026) · The International Journal of Cardiovascular Imaging · doi:10.1007/s10554-026-03602-2
Meta-analysis of magnetocardiography in diagnosing coronary artery disease and myocardial ischemia
Li, J., Yan, M., Xiang, M., & Ning, X. (2026) · Next research. · doi:10.1016/j.nexres.2026.101496 · Cited by 1
Transformer-Riemannian approach for MCG signal classification
Wang, J., Shen, H., Guo, Y., Xu, X., Liu, L., Ma, J., & Shen, C. (2026) · The Visual Computer · doi:10.1007/s00371-025-04258-0
Guo, J., Bao, C., Gong, L., & Zhang, Z. (2026) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2026.1892900
Devadas, R. M., & Sowmya, T. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-01063-0
“…Mohammed 2024; Rostamzadeh et al. 2021; Yu et al. 2024; Han et al. 2023; Fan et al. 2024; Xie et al. 2023; Beadle et al. 2021; Varghese et al. 2023; Huang et al. 2021; Zhang et al. 2021; Xiao et al. 2023; Kumar et al. 2021; Wei et al. 2022; Mahesh-wari et al. 2023; Kurashima et al. 2023; Prabhu et…”
InfluentialWang, Q., Zhang, L., & Huang, Z. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111658
Metadata
- Authors
- Huang, X., Chen, P., Tang, F., & Hua, N.
- Affiliations
- Chinese PLA General Hospital (CN)
- Corresponding author
- Tang, Fakuan
- Hua, Ning
- Venue
- Clinical Hemorheology and Microcirculation
- Publisher
- SAGE Publications
- Published
- 2021-08-03
- Volume
- 78
- Issue
- 3
- Pages
- 227-236
- ISSN
- 1386-0291 (ISSN-L)
- 1875-8622
- OpenAlex
- W3113216408
- Cited by
- 33
- References
- 21
- Citations by year
- 2026: 9 · 2025: 8 · 2024: 5 · 2023: 7 · 2022: 3 · 2021: 1
- FWCI
- 1.72
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Clinical Hemorheology and Microcirculation (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Cardiac Imaging and Diagnostics
- Keywords
- coronary artery disease, chest pain, magnetocardiography, multilayer perceptron, machine learning diagnosis, cardiac magnetic field, electrocardiogram, percutaneous coronary angiography, diagnostic accuracy
- MeSH terms
- Machine Learning, Chest Pain, Coronary Artery Disease, Cross-Sectional Studies, Electrocardiography, Humans, Prospective Studies, Coronary Angiography, Magnetocardiography
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.