Left ventricular hypertrophy detection using electrocardiographic signal

Abstract

Left ventricular hypertrophy (LVH) indicates subclinical organ damage, associating with the incidence of cardiovascular diseases. From the medical perspective, electrocardiogram (ECG) is a low-cost, non-invasive, and easily reproducible tool that is often used as a preliminary diagnosis for the detection of heart disease. Nowadays, there are many criteria for assessing LVH by ECG. These criteria usually include that voltage combination of RS peaks in multi-lead ECG must be greater than one or more thresholds for diagnosis. We developed a system for detecting LVH using ECG signals by two steps: firstly, the R-peak and S-valley amplitudes of the 12-lead ECG were extracted to automatically obtain a total of 24 features and ECG beats of each case (LVH or non-LVH) were segmented; secondly, a back propagation neural network (BPN) was trained using a dataset with these features. Echocardiography (ECHO) was used as the gold standard for diagnosing LVH. The number of LVH cases (of a Taiwanese population) identified was 173. As each ECG sequence generally included 8 to 13 cycles (heartbeats) due to differences in heart rate, etc., we identified 1466 ECG cycles of LVH patients after beat segmentation. Results showed that our BPN model for detecting LVH reached the testing accuracy, precision, sensitivity, and specificity of 0.961, 0.958, 0.966 and 0.956, respectively. Detection performances of our BPN model, on the whole, outperform 7 methods using ECG criteria and many ECG-based artificial intelligence (AI) models reported previously for detecting LVH.

Searching for the Best Machine Learning Algorithm for the Detection of Left Ventricular Hypertrophy from the ECG: A Review

“…Specificity ranged from 0.53 to 0.99 (Figure 2). The highest specificity was found using the algorithm proposed by Sammani et al [41], followed closely by that of Liu et al [44] and then Khurshid et al [36].…”

“…This group found a prevalence of 18% with echocardiographic LVH. Their combination of sensitivity and specificity was the highest of any approach [44].…”

“…The range is from 0.29 to 0.966 (Figure 1). The highest sensitivity was 0.966 using the algorithm proposed by Liu et al, 2023 [44], followed by 0.867 using the algorithm proposed by Lin and Liu [31], followed by the one proposed by De la Garza-Salazar et al [33]. Specificity ranged from 0.53 to 0.99 (Figure 2).…”

“…An overall assessment indicated by AUC was reported in nine studies and ranged from 0.705 to 0.89, with the highest AUC reported for the algorithms of Angelaki et al [38] followed by Kwon et al [34] (Figure 3). Overall accuracy was detailed in eight studies, with the highest value of 0.961 from Liu et al [44] followed by that of Angelaki et al [38] (Figure 4). The next best was that of Kwon et al [34].…”

Electrocardiographic abnormalities in patients with sickle cell disease: A systematic review and meta‐analysis

“…29 It is noteworthy that these findings regarding the heightened prevalence of ventricular hypertrophy gain further significance when considering that, despite ECG's appropriate specificity and predictive values, ECG assess the electrical, not anatomical LVH, and its sensitivity in detecting ventricular hypertrophy is limited, and the actual rate is higher. [30][31][32] In a cross-sectional study of 422 participants, ECG accuracy for detecting LVH was compared with echocardiography, revealing a sensitivity of 14% in LVH detection. 33 Similarly, in a study on patients with SCD, both ECG and two-dimensional echocardiogram were employed for cardiac assessment, indicating that LVH was observed in 28% of patients through ECG and 65% of patients through echocardiogram.…”