Automatic Detection of Left Ventricular Dilatation and Hypertrophy from Electrocardiograms Using Deep Learning

Abstract

Left ventricular dilatation (LVD) and left ventricular hypertrophy (LVH) are risk factors for heart failure, and their detection improves heart failure screening. This study aimed to investigate the ability of deep learning to detect LVD and LVH from a 12-lead electrocardiogram (ECG). Using ECG and echocardiographic data, we developed deep learning and machine learning models to detect LVD and LVH. We also examined conventional ECG criteria for the diagnosis of LVH. We calculated the area under the receiver operating characteristic (AUROC) curve, sensitivity, specificity, and accuracy of each model and compared the performance of the models. We analyzed data for 18,954 patients (mean age (standard deviation): 64.2 (16.5) years, men: 56.7%). For the detection of LVD, the value (95% confidence interval) of the AUROC was 0.810 (0.801-0.819) for the deep learning model, and this was significantly higher than that of the logistic regression and random forest methods (P < 0.001). The AUROCs for the logistic regression and random forest methods (machine learning models) were 0.770 (0.761-0.779) and 0.757 (0.747-0.767), respectively. For the detection of LVH, the AUROC was 0.784 (0.777-0.791) for the deep learning model, and this was significantly higher than that of the logistic regression and random forest methods and conventional ECG criteria (P < 0.001). The AUROCs for the logistic regression and random forest methods were 0.758 (0.751-0.765) and 0.716 (0.708-0.724), respectively. This study suggests that deep learning is a useful method to detect LVD and LVH from 12-lead ECGs.

Construction and validation of a nomogram to predict left ventricular hypertrophy in low‐risk patients with hypertension

“…For example, the LVH of 1120 inpatients in China was predicted using a deep learning model of a convolution neural network. However, the AUC was only 0.62 (with a sensitivity of 68% and specificity of 57%), which is still insufficient 29 . Moreover, as most models lack demographic data and other cardiovascular risk factors, diagnostic efficiency has not improved 30 .…”

Pediatric ECG-Based Deep Learning to Predict Left Ventricular Dysfunction and Remodeling

“…[36][37][38][39] Analysis of ECG waveforms provides a rapid, easy-to-implement, and cost-effective application for artificial intelligence. Its use in adults has been wideranging, including prediction of ventricular dysfunction, [3][4][5][6][7] ventricular hypertrophy, 8-10 ventricular dilation, 9,11 atrial fibrillation and other arrhythmias, 17,26,40,41 and age, 42,43 sex, 42 and time to death. 8,43 Our findings provide proof-ofconcept evidence that similar ECG applications can be explored in children and suggest that deep learning may also be applicable to other data streams (eg, wearable biosensor data) that could aid in predicting outcomes for children 44 similar to what has been performed in adults.…”

“…This has historically motivated the development of computer-generated interpretations on the basis of predefined rules and feature recognition algorithms that may not capture subtleties of an ECG. 2 Recent work has demonstrated that deep learning-based artificial intelligence-enhanced ECG (AI-ECG) algorithms may result in greater diagnostic fidelity; studies of this approach in adult populations have reliably predicted a range of adult cardiovascular phenotypes, including ventricular dysfunction, [3][4][5][6][7] ventricular hypertrophy, [8][9][10] and ventricular dilation. 9,11 Progressive anatomic and physiological changes occurring from birth to adolescence lead to agedependent variations in pediatric ECGs.…”

“…2 Recent work has demonstrated that deep learning-based artificial intelligence-enhanced ECG (AI-ECG) algorithms may result in greater diagnostic fidelity; studies of this approach in adult populations have reliably predicted a range of adult cardiovascular phenotypes, including ventricular dysfunction, [3][4][5][6][7] ventricular hypertrophy, [8][9][10] and ventricular dilation. 9,11 Progressive anatomic and physiological changes occurring from birth to adolescence lead to agedependent variations in pediatric ECGs. The epidemiology and patterns of normal versus abnormal pediatric ECGs differ significantly from those of adults, which may be expected to limit generalizability of applying adult AI-ECG algorithms to pediatric cohorts.…”

“…2 Recent work has demonstrated that deep learning–based artificial intelligence–enhanced ECG (AI-ECG) algorithms may result in greater diagnostic fidelity; studies of this approach in adult populations have reliably predicted a range of adult cardiovascular phenotypes, including ventricular dysfunction, 3–7 ventricular hypertrophy, 8–10 and ventricular dilation. 9,11…”