Search

The efficacy of convolutional neural network (CNN)-enhanced electrocardiography (ECG) in detecting hypertrophic cardiomyopathy (HCM) and dilated HCM (dHCM) remains uncertain in real-world applications. This retrospective study analyzed data from 19,170 patients (including 140 HCM or dHCM) in the Shinken Database (2010–2017). We evaluated the sensitivity, positive predictive rate (PPR), and F1 score of CNN-enhanced ECG in a "basic diagnosis" model (total disease label) and a "comprehensive diagnosis" model (including disease subtypes). Using all-lead ECG in the "basic diagnosis" model, we observed a sensitivity of 76%, PPR of 2.9%, and F1 score of 0.056. These metrics improved in cases with a diagnostic probability of ≥ 0.9 and left ventricular hypertrophy (LVH) on ECG: 100% sensitivity, 8.6% PPR, and 0.158 F1 score. The "comprehensive diagnosis" model further enhanced these figures to 100%, 13.0%, and 0.230, respectively. Performance was broadly consistent across CNN models using different lead configurations, particularly when including leads viewing the lateral walls. While the precision of CNN models in detecting HCM or dHCM in real-world settings is initially low, it improves by targeting specific patient groups and integrating disease subtype models. The use of ECGs with fewer leads, especially those involving the lateral walls, appears comparably effective. [ABSTRACT FROM AUTHOR]

Measurement of flow-mediated dilatation (FMD) is the conventional non-invasive method for assessment of endothelial function; however, it requires an expensive ultrasound system and high levels of technical skill. Therefore, we developed a novel method for measurement of endothelial function, namely, measurement of ezFMD. ezFMD estimates the degree of vasodilatation from the oscillation signals transmitted to a sphygmomanometer cuff attached to the upper arm. The objective of this study was to validate the principle underlying the measurement of ezFMD, and to evaluate the repeatability of the ezFMD measurements. We observed the blood vessel behavior and oscillometric pattern in ten subjects. When the cuff was inflated to the level of the mean blood pressure, the oscillation amplitude increased with increasing degree of vasodilatation. In experiment to evaluate the repeatability of the ezFMD measurement, the average difference between the paired measurements was 3.7 %, the standard deviation was 11.5 %, and the average coefficient of variation value for the 11 paired measurements was 23.7 %. These results suggest the validity of the principle underlying the measurement of the ezFMD for the assessment of endothelial function. And, this study suggests that the repeatability of the ezFMD measurements is superior to that of the conventional measurement of FMD. [ABSTRACT FROM AUTHOR]