CoChat

The DOI matches its Crossref record; the references it cites are not checked yet.

AI-enabled diagnosis and localization of myocardial ischemia and coronary artery stenosis from magnetocardiographic recordings

Open access
Tao, Rong, Zhang, Shunlin, Zhang, Rui, Shen, Chengxing, Ma, Jian, Cui, Jianguo, Chen, Yundai, Wang, Bo, Li, Hailing, Xie, Xiaoming, Zheng, Guoyan · 2025 · Scientific Reports

Abstract

Early diagnosis and localization of myocardial ischemia (MS) and coronary artery stenosis (CAS) play a crucial role in the effective prevention and management of ischemic heart disease (IHD). Magnetocardiography (MCG) has emerged as a promising approach for non-invasive, non-contact, and high-sensitivity assessment of cardiac dysfunction. This study presents a multi-center, AI-enabled diagnosis and localization of myocardial ischemia and coronary artery stenosis from MCG data. To this end, we collected a large-scale dataset consisting of 2,158 MCG recordings from eight clinical centers. We then proposed a multiscale vision transformer-based network for extracting spatio-temporal information from multichannel MCG recordings. Anatomical prior knowledge of the coronary artery and the irrigated left ventricular regions was incorporated by a carefully designed graph convolutional network (GCN)-based feature fusion module. The proposed approach achieved an accuracy of 84.7%, a sensitivity of 83.8%, and a specificity of 85.6% in diagnosing IHD, an average accuracy of 78.4% in localization of five MS regions, and an average accuracy of 65.3% in localization of stenosis in three coronary arteries. Subsequent validation on an independent validation dataset consisting of 268 MCG recordings collected from four clinical centers demonstrated an accuracy of 82.3%, a sensitivity of 83.8%, and a specificity of 81.3% in diagnosing IHD, an average accuracy of 77.3% in localization of five myocardial ischemic regions, and an average accuracy of 65.6% in localization of stenosis in three coronary arteries. The proposed approach can be used as a fast and accurate diagnosis tool, boosting the integration of MCG examination into clinical routine.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-025-90615-x

Cites

Statistics

Figures

Figure 1 Patient enrollment and study design flowchart. From an initial pool of 1562 patients presenting with chest pain or suspected CAD between January 2020 and December 2023, 926 patients met the inclusion criteria after excluding those with previous cardiac interventions (n = 324), unstable conditions (n=158), and inadequate imaging quality (n = 154).
Figure 1 Patient enrollment and study design flowchart. From an initial pool of 1562 patients presenting with chest pain or suspected CAD between January 2020 and December 2023, 926 patients met the inclusion criteria after excluding those with previous cardiac interventions (n = 324), unstable conditions (n=158), and inadequate imaging quality (n = 154).CC BY-NC-ND · PubMed Central
Figure 2 IHD diagnostic ROC curves of the proposed approach when evaluated on the combined group (A), the SPECT group (B), and the CAG group (C) of the development dataset. The mean ROC curves and standard deviation (shaded region) are plotted for each group.
Figure 2 IHD diagnostic ROC curves of the proposed approach when evaluated on the combined group (A), the SPECT group (B), and the CAG group (C) of the development dataset. The mean ROC curves and standard deviation (shaded region) are plotted for each group.CC BY-NC-ND · PubMed Central
Figure 3 Qualitative examples of IHD diagnosis of the proposed approach from the MCG recordings. For each subject, we show the reference diagnosis (2nd column), the predicted IHD probability (3rd column), the averaged waveform (4th column) and the samples of magnetic field maps during the TT interval (5th column).
Figure 3 Qualitative examples of IHD diagnosis of the proposed approach from the MCG recordings. For each subject, we show the reference diagnosis (2nd column), the predicted IHD probability (3rd column), the averaged waveform (4th column) and the samples of magnetic field maps during the TT interval (5th column).CC BY-NC-ND · PubMed Central
Figure 4 Four cases when the proposed method failed. For each subject, we visualized the magnetic field maps and the corresponding Grad-CAM maps.
Figure 4 Four cases when the proposed method failed. For each subject, we visualized the magnetic field maps and the corresponding Grad-CAM maps.CC BY-NC-ND · PubMed Central
Figure 5 Illustration of the proposed pipeline which consists of (1) MCG data recording and preprocessing; (2) cardiac event extraction and (3) model development.
Figure 5 Illustration of the proposed pipeline which consists of (1) MCG data recording and preprocessing; (2) cardiac event extraction and (3) model development.CC BY-NC-ND · PubMed Central
Figure 6 (A) Overall network architecture design for the proposed multi-task learning framework, including IHD diagnosis, localization of ischemic cardiac regions and localization of obstructed coronary arteries, (B) design of the multiscale spatio-temporal feature extractor (MSFE) unit.
Figure 6 (A) Overall network architecture design for the proposed multi-task learning framework, including IHD diagnosis, localization of ischemic cardiac regions and localization of obstructed coronary arteries, (B) design of the multiscale spatio-temporal feature extractor (MSFE) unit.CC BY-NC-ND · PubMed Central
Figure 7 (A) Illustration of the incorporated anatomical prior knowledge, featuring the relationship between three coronary arteries and five LV regions, (B) design of the graph convolution based feature fusion (GCN) unit and the output feature selection process for GCN unit corresponding to IHD diagnosis ({GCN}_{IHD}), localization of ischemic region ({GCN}_{SPECT}) and localization of coronary artery stenosis ({GCN}_{CAG}), respectively.
Figure 7 (A) Illustration of the incorporated anatomical prior knowledge, featuring the relationship between three coronary arteries and five LV regions, (B) design of the graph convolution based feature fusion (GCN) unit and the output feature selection process for GCN unit corresponding to IHD diagnosis ({GCN}_{IHD}), localization of ischemic region ({GCN}_{SPECT}) and localization of coronary artery stenosis ({GCN}_{CAG}), respectively.CC BY-NC-ND · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

The citation lists are queued

They are fetched later and appear here then.

References 36 · Cited by 14

Metadata

Authors
Tao, R., Zhang, S., Zhang, R., Shen, C., Ma, J., Cui, J., Chen, Y., Wang, B., Li, H., Xie, X., & Zheng, G.
Affiliations
  • Shanghai Jiao Tong University (CN)
  • Chinese Academy of Sciences (CN)
  • Shanghai Sixth People's Hospital (CN)
  • Chinese People's Liberation Army (CN)
  • Tongji University (CN)
Venue
Scientific Reports
Published
2025-02-19
Volume
15
Issue
1
Pages
6094-6094
ISSN
2045-2322 (ISSN-L)
OpenAlex
W4407736593
Cited by
14
References
36
Citations by year
2026: 9 · 2025: 5
FWCI
9.70
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • CityU Scholars (submittedVersion, cc-by-nc-nd)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • National Natural Science Foundation of China (U20A20199)
  • National Key laboratory of functional materials for informatics open funding project (SKL2022)
  • National Key Research and Development Program of China (2022YFC2407004)
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
magnetocardiography, myocardial ischemia, coronary artery stenosis, ischemic heart disease, ischemia localization, graph convolutional networks, feature fusion, anatomical prior knowledge, noninvasive cardiac assessment
MeSH terms
Aged, Female, Humans, Male, Middle Aged, Myocardial Ischemia, Coronary Stenosis, 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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: AI-enabled diagnosis and localization of myocardial ischemia and coronary artery stenosis from magnetocardiographic recordings. https://app.cochat.ai/papers/10.1038/s41598-025-90615-x
The paper
Tao, R., Zhang, S., Zhang, R., Shen, C., Ma, J., Cui, J., Chen, Y., Wang, B., Li, H., Xie, X., & Zheng, G. (2025). AI-enabled diagnosis and localization of myocardial ischemia and coronary artery stenosis from magnetocardiographic recordings. Scientific Reports. https://doi.org/10.1038/s41598-025-90615-x

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.