Article Impact Level: HIGH Data Quality: STRONG Summary of Clinical Cardiology, 46(6), 639–647. https://doi.org/10.1002/clc.24019 Ying Wang et al.
Points
- The research paper introduces the cardiodynamicsgram (CDG), a noninvasive method that extracts dynamic ST-T segment information from an electrocardiogram (ECG) using deterministic learning.
- The study assessed the CDG’s ability to reflect anomalous functional information in coronary artery disease (CAD) patients.
- The research included 456 patients with suspected CAD who underwent coronary computed tomography angiography (CCTA) and standard 12-lead ECG acquisition.
- The CDG demonstrated an accuracy of 79.56% in diagnosing CAD, with a sensitivity of 75.60% and a specificity of 82.99%.
- The CDG showed potential as a screening tool for suspected CAD patients, exhibiting a correlation with CT-derived fractional flow reserve (CT-FFR) and accurately diagnosing CAD cases confirmed by invasive coronary angiography (ICA).
Summary
This research paper introduces the cardiodynamicsgram (CDG), a novel noninvasive technique that utilizes deterministic learning to extract dynamic ST-T segment information from an electrocardiogram (ECG). The study aims to investigate whether the CDG can effectively reflect anomalous functional information in patients with coronary artery disease (CAD).
The research was conducted retrospectively, involving 456 patients with suspected CAD who underwent coronary computed tomography angiography (CCTA) between January 2020 and 2022. The patients also underwent standard 12-lead ECG acquisition immediately after the CCTA. CAD positivity was defined as CCTA ≥ 50% or CT-derived fractional flow reserve (CT-FFR) ≤ 0.8. The CDG values were categorized as negative (<0) or positive, and the diagnostic performance of the CDG was evaluated in the ECG-diagnosis-negative subgroup and in patients who underwent invasive coronary angiography (ICA) following CCTA.
The results showed that out of the 362 patients analyzed, 168 (46.41%) tested positive for CAD, with 178 (49.17%) male. The CDG demonstrated an accuracy of 79.56% in diagnosing CAD, with a sensitivity of 75.60%, specificity of 82.99%, and an area under the receiver operating characteristic curve (AUC) of 0.836 (95% CI: 0.794−0.878). Furthermore, the CDG exhibited an accuracy of 80.27% in the ECG-diagnosis–negative subgroup (n = 223), with an AUC of 0.842 (95% CI: 0.790−0.895). Among the 11 patients who underwent ICA and were confirmed to have CAD, ten were accurately diagnosed as positive by the CDG. Additionally, there was a correlation between CDG values and CT-FFR (r = −.395; p < .001).
In conclusion, the CDG, based on ECG data, demonstrated notable specificity and accuracy in diagnosing CAD and providing functional cardiac information. The CDG has the potential to be used as a screening tool for patients suspected of having CAD before undergoing CCTA.
Link to the article: https://onlinelibrary.wiley.com/doi/10.1002/clc.24019
References Wang, Y., Sun, J., Sun, K., Li, L., Yu, X., Wang, C., Gu, H., Sun, Q., & Wang, X. (2023). ECG‐based cardiodynamicsgram can reflect anomalous functional information in coronary artery disease. Clinical Cardiology, 46(6), 639–647. https://doi.org/10.1002/clc.24019
