Determination of Sensitivity and Specificity of Electrocardiography for Left Ventricular Hypertrophy in a Large, Diverse Patient Population

Postmortem genetic analysis of 17 sudden cardiac deaths identified nonsense and frameshift variants in two cases of arrhythmogenic cardiomyopathy

Sudden death, or unexpected natural death of a healthy individual, is a serious problem in all nations. Sudden cardiac death (SCD) mainly due to ischemic heart diseases is the top cause of sudden death. However, there are pathophysiological conditions, referred to as sudden arrhythmic death syndrome, in which no apparent lesion can be identified even after complete conventional or ordinary autopsy. While postmortem genetic analyses have accumulated evidence about underlying genetic abnormality in such cases, the precise relationships between genetic background and the phenotype have been largely elusive. In this study, a retrospective investigation of 17 autopsy cases in which lethal arrhythmia was suspected to be the cause of death was carried out. Genetic analysis focusing on 72 genes reported to be associated with cardiac dysfunctions was performed, in combination with detailed histopathological and postmortem imaging examination, and a family study. As a result, in two cases of suspected arrhythmogenic cardiomyopathy (ACM), we found a nonsense variant in PKP2 and frameshift variant in TRPM4 gene. In contrast, the other 15 cases showed no morphological changes in the heart despite the presence of a frameshift variant and several missense variants, leaving the clinical significance of these variants obscure. The findings of the present study suggest that nonsense and frameshift variants could be involved in the morphological abnormality in cases of SCD due to ACM, while missense variants alone rarely contribute to massive structural changes in the heart.

Deep learning assessment of left ventricular hypertrophy based on electrocardiogram

Background

Current electrocardiogram (ECG) criteria of left ventricular hypertrophy (LVH) have low sensitivity. Deep learning (DL) techniques have been widely used to detect cardiac diseases due to its ability of automatic feature extraction of ECG. However, DL was rarely applied in LVH diagnosis. Our study aimed to construct a DL model for rapid and effective detection of LVH using 12-lead ECG.

Methods

We built a DL model based on convolutional neural network-long short-term memory (CNN-LSTM) to detect LVH using 12-lead ECG. The echocardiogram and ECG of 1,863 patients obtained within 1 week after hospital admission were analyzed. Patients were evenly allocated into 3 sets at 3:1:1 ratio: the training set (n = 1,120), the validation set (n = 371) and the test set 1 (n = 372). In addition, we recruited 453 hospitalized patients into the internal test set 2. Different DL model of each subgroup was developed according to gender and relative wall thickness (RWT).

Results

The LVH was predicted by the CNN-LSTM model with an area under the curve (AUC) of 0.62 (sensitivity 68%, specificity 57%) in the test set 1, which outperformed Cornell voltage criteria (AUC: 0.57, sensitivity 48%, specificity 72%) and Sokolow-Lyon voltage (AUC: 0.51, sensitivity 14%, specificity 96%). In the internal test set 2, the CNN-LSTM model had a stable performance in predicting LVH with an AUC of 0.59 (sensitivity 65%, specificity 57%). In the subgroup analysis, the CNN-LSTM model predicted LVH by 12-lead ECG with an AUC of 0.66 (sensitivity 72%, specificity 60%) for male patients, which performed better than that for female patients (AUC: 0.59, sensitivity 50%, specificity 71%).

Conclusion

Our study established a CNN-LSTM model to diagnose LVH by 12-lead ECG with higher sensitivity than current ECG diagnostic criteria. This CNN-LSTM model may be a simple and effective screening tool of LVH.

Electrocardiographic Characteristics and Their Correlation with Echocardiographic Alterations in Fabry Disease

Fabry disease (FD) is an X-linked disorder with α-galactosidase A deficiency. Males (>30 years) and females (>40 years) often present with cardiac manifestations, predominantly left ventricular hypertrophy (LVH). The aim of this study was to evaluate electrocardiographic (ECG) characteristics within FD patients to identify gender related differences, and to additionally explore the association of ECG parameters with structural and functional alterations on transthoracic echocardiography (TTE). Retrospective cross-sectional analysis of 45 FD patients with contemporaneous ECG and TTE was performed and compared to age and gender matched healthy controls. FD patients demonstrated alterations in several ECG parameters particularly in males, including prolonged P-wave duration (91 vs. 81 ms, p = 0.022), prolonged QRS duration (96 vs. 84 ms, p < 0.001), increased R-wave amplitude in lead I (8.1 vs. 5.7 mV, p = 0.047), increased Sokolow–Lyon index (25 vs. 19 mV, p = 0.002) and were more likely to meet LVH criteria (31% vs. 7%, p = 0.006). FD patients with impaired basal longitudinal strain (LS) on TTE were more likely to meet LVH criteria (41% vs. 0%, p = 0.018). Those with more advanced FD (increased LV wall thickness on TTE) were more likely to meet LVH criteria but additionally demonstrated prolonged ventricular depolarization (QRS duration 101 vs. 88 ms, p = 0.044). Therefore, alterations on ECG demonstrating delayed atrial activation, delayed ventricular depolarization and evidence of LVH were more often seen in male FD patients. Impaired basal LS, a TTE marker of early cardiac involvement, correlated with ECG abnormalities. Increased LV wall thickness on TTE, a marker of more advanced FD, was associated with more severe ECG abnormalities.

Optimizing ECG to detect echocardiographic left ventricular hypertrophy with computer-based ECG data and machine learning

BACKGROUND

Left ventricular hypertrophy detected by echocardiography (Echo-LVH) is an independent predictor of mortality. Integration of the Philips DXL-16 algorithm into the electrocardiogram (ECG) extensively analyses the electricity of the heart. Machine learning techniques such as the C5.0 could lead to a new decision tree criterion to detect Echo-LVH.

OBJECTIVES

To search for a new combination of ECG parameters predictive of Echo-LVH. The final model is called the Cardiac Hypertrophy Computer-based model (CHCM).

METHODS

We extracted the 458 ECG parameters provided by the Philips DXL-16 algorithm in patients with Echo-LVH and controls. We used the C5.0 ML algorithm to train, test, and validate the CHCM. We compared its diagnostic performance to validate state-of-the-art criteria in our patient cohort.

RESULTS

We included 439 patients and considered an alpha value of 0.05 and a power of 99%. The CHCM includes T voltage in I (≤0.055 mV), peak-to-peak QRS distance in aVL (>1.235 mV), and peak-to-peak QRS distance in aVF (>0.178 mV). The CHCM had an accuracy of 70.5% (CI95%, 65.2-75.5), a sensitivity of 74.3%, and a specificity of 68.7%. In the external validation cohort (n = 156), the CHCM had an accuracy of 63.5% (CI95%, 55.4-71), a sensitivity of 42%, and a specificity of 82.9%. The accuracies of the most relevant state-of-the-art criteria were: Romhilt-Estes (57.4%, CI95% 49-65.5), VDP Cornell (55.7%, CI95%47.6-63.7), Cornell (59%, CI95%50.8-66.8), Dalfó (62.9%, CI95%54.7-70.6), Sokolow Lyon (53.9%, CI95%45.7-61.9), and Philips DXL-16 algorithm (54.5%, CI95%46.3-62.5).

CONCLUSION

ECG computer-based data and the C5.0 determined a new set of ECG parameters to predict Echo-LVH. The CHCM classifies patients as Echo-LVH with repolarization abnormalities or LVH with increased voltage. The CHCM has a similar accuracy, and is slightly more sensitive than the state-of-the-art criteria.

Detection of abnormal left ventricular geometry in patients without cardiovascular disease through machine learning: An ECG-based approach

Cardiac remodeling is recognized as an important aspect of cardiovascular disease (CVD) progression. Machine learning (ML) techniques were applied to basic clinical parameters and electrocardiographic features, in order to detect abnormal left ventricular geometry (LVG) even before the onset of left ventricular hypertrophy (LVH), in a population without established CVD. The authors enrolled 528 patients with and without essential hypertension, but no other indications of CVD. All patients underwent a full echocardiographic evaluation and were classified into 3 groups; normal geometry (NG), concentric remodeling without LVH (CR), and LVH. Abnormal LVG was identified as increased relative wall thickness (RWT) and/or left ventricular mass index (LVMi). The authors trained supervised ML models to classify patients with abnormal LVG and calculated SHAP values to perform feature importance and interaction analysis. Hypertension, age, body mass index over the Sokolow‐Lyon voltage, QRS‐T angle, and QTc duration were some of the most important features. Our model was able to distinguish NG from CR+LVH combined, with 87% accuracy on an unseen test set, 75% specificity, 97% sensitivity, and area under the receiver operating curve (AUC/ROC) equal to 0.91. The authors also trained our model to classify NG and CR (NG + CR) against those with LVH, with 89% test set accuracy, 93% specificity, 67% sensitivity, and an AUC/ROC value of 0.89, for a 0.4 decision threshold. Our ML algorithm effectively detects abnormal LVG even at early stages. Innovative solutions are needed to improve risk stratification of patients without established CVD, and ML may enable progress in this direction.