AI-enabled OPM-magnetocardiography for pre-angiography infarct-related artery probability estimation in NSTEMI: a two-campus prospective cohort study
7 affiliations
- 1Department of Cardiology, Beijing Anzhen Hospital, Capital Medical University, No. 2 Anzhen Road, Chaoyang District, Beijing 100029, China.
- 2Arrhythmia Center, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100037, China.
- 3Department of Cardiovascular Surgery, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100037, China.
- 4Department of Cardiac Surgery, Beijing Anzhen Hospital, Capital Medical University, Beijing 100029, China.
- 5Beijing X-MAGTECH Technology Co., Ltd, Beijing 100096, China.
- 6School of Instrumentation Science and Opto-electronics Engineering, Beihang University, Beijing 100191, China.
- 7Department of Cardiology, Beijing Friendship Hospital, Capital Medical University, No. 95 Yong'an Road, Xicheng District, Beijing 100050, China.
Abstract
Aims
Identifying the infarct-related artery (IRA) before coronary angiography in non-ST-segment elevation myocardial infarction (NSTEMI) is difficult because current approaches have limited sensitivity. We evaluated whether a non-invasive 90-s optically pumped magnetometer magnetocardiography (OPM-MCG) recording can estimate pre-angiography IRA probabilities in these patients and provide information beyond standard-care variables.Methods and results
This prospective two-campus study within one hospital system included a Campus 1 development cohort (n = 493) and a geographically separate Campus 2 test cohort (n = 118). All patients underwent OPM-MCG before angiography. An XGBoost model using 65 prespecified OPM-MCG features was developed with nested cross-validation, locked, and evaluated once in Campus 2. IRA adjudication followed a core-laboratory hierarchy. Discrimination, calibration, and clinical utility were compared with ECG and TTE. Among 611 patients, 43% had LAD, 23% LCx, and 34% RCA IRA. In Campus 2, overall accuracy was 63.6%, macro-F1 was 60.0%; LAD/LCx/RCA vessel-specific areas under the receiver operating characteristic curve were 0.87/0.79/0.79 and top-1 sensitivity was 76.6%/34.5%/69.0%. Accuracy was 51.7% for matched ECG-only XGBoost and 55.9% for integrated standard care. In an exploratory stacked analysis, adding locked OPM-MCG probabilities to standard care increased accuracy to 67.8% (paired difference 11.9%, 95% CI 4.2-19.5; P = 0.008).Conclusion
In haemodynamically stable patients with NSTEMI already selected for invasive management, a locked OPM-MCG model provided informative vessel-level probabilities in Campus 2 and complementary signal with standard care. Performance was strongest for LAD and RCA. Prospective multicentre, cross-platform testing is needed before clinical use.Trial registration number
ChiCTR2300070211.
Related
- Global trends and knowledge structure of cardiovascular magnetocardiography research: a bibliometric analysis
- HSPiP, computational, and thermodynamic models-based solubility validation of tofacitinib in PEG400 – water system, shelf-life estimation, and GastroPlus-enabled predictive in vivo performance
- Imaging Correlation of Color Doppler Ultrasound, CT Angiography, and MR Angiography Findings in Extracranial Carotid and Vertebral Artery Disease Among Ischemic Stroke Patients: A Prospective Observational Study.
- Diagnostic Accuracy and Feasibility of Quantitative Flow Ratio at Low Frame Rate Angiography: The Prospective Multicentre Australian AVALON Study
- Clinical Usefulness of Artificial Intelligence-Enabled Electrocardiography for Pulmonary Hypertension Detection: A Meta-analysis Based on Pre- and Post-Test Probability
BibTeX
@article{liu2026aienabled,
title = {{AI-enabled OPM-magnetocardiography for pre-angiography infarct-related artery probability estimation in NSTEMI: a two-campus prospective cohort study}},
author = {Linqi Liu and Yilin Pan and Jie Ji and Hai Gao and Yanlong Ren and Min Zhang and Mingduo Zhang and Ming Ding and Chenchen Tu and Xiantao Song},
journal = {European heart journal. Digital health},
year = {2026},
month = oct,
doi = {10.1093/ehjdh/ztag161},
url = {https://europepmc.org/article/PMC/PMC13718593},
note = {CC BY-NC},
}
RIS
TY - JOUR
TI - AI-enabled OPM-magnetocardiography for pre-angiography infarct-related artery probability estimation in NSTEMI: a two-campus prospective cohort study
AU - Linqi Liu
AU - Yilin Pan
AU - Jie Ji
AU - Hai Gao
AU - Yanlong Ren
AU - Min Zhang
AU - Mingduo Zhang
AU - Ming Ding
AU - Chenchen Tu
AU - Xiantao Song
PY - 2026
DA - 2026/10/10
JO - European heart journal. Digital health
DO - 10.1093/ehjdh/ztag161
UR - https://europepmc.org/article/PMC/PMC13718593
AB - Aims Identifying the infarct-related artery (IRA) before coronary angiography in non-ST-segment elevation myocardial infarction (NSTEMI) is difficult because current approaches have limited sensitivity. We evaluated whether a non-invasive 90-s optically pumped magnetometer magnetocardiography (OPM-MCG) recording can estimate pre-angiography IRA probabilities in these patients and provide information beyond standard-care variables.Methods and results This prospective two-campus study within one hospital system included a Campus 1 development cohort (n = 493) and a geographically separate Campus 2 test cohort (n = 118). All patients underwent OPM-MCG before angiography. An XGBoost model using 65 prespecified OPM-MCG features was developed with nested cross-validation, locked, and evaluated once in Campus 2. IRA adjudication followed a core-laboratory hierarchy. Discrimination, calibration, and clinical utility were compared with ECG and TTE. Among 611 patients, 43% had LAD, 23% LCx, and 34% RCA IRA. In Campus 2, overall accuracy was 63.6%, macro-F1 was 60.0%; LAD/LCx/RCA vessel-specific areas under the receiver operating characteristic curve were 0.87/0.79/0.79 and top-1 sensitivity was 76.6%/34.5%/69.0%. Accuracy was 51.7% for matched ECG-only XGBoost and 55.9% for integrated standard care. In an exploratory stacked analysis, adding locked OPM-MCG probabilities to standard care increased accuracy to 67.8% (paired difference 11.9%, 95% CI 4.2-19.5; P = 0.008).Conclusion In haemodynamically stable patients with NSTEMI already selected for invasive management, a locked OPM-MCG model provided informative vessel-level probabilities in Campus 2 and complementary signal with standard care. Performance was strongest for LAD and RCA. Prospective multicentre, cross-platform testing is needed before clinical use.Trial registration number ChiCTR2300070211.
SN - 2634-3916
ER -