Improvement of electrocardiographic diagnostic accuracy of left ventricular hypertrophy using a Machine Learning approach

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

Background: Left ventricular hypertrophy (LVH) is a powerful predictor of future cardiovascular events. Objectives: The objectives of this study were to conduct a systematic review of machine learning (ML) algorithms for the identification of LVH and compare them with respect to the classical features of test sensitivity, specificity, accuracy, ROC and the traditional ECG criteria for LVH. Methods: A search string was constructed with the operators "left ventricular hypertrophy, electrocardiogram" AND machine learning; then, Medline and PubMed were systematically searched. Results: There were 14 studies that examined the detection of LVH utilizing the ECG and utilized at least one ML approach. ML approaches encompassed support vector machines, logistic regression, Random Forest, GLMNet, Gradient Boosting Machine, XGBoost, AdaBoost, ensemble neural networks, convolutional neural networks, deep neural networks and a back-propagation neural network. Sensitivity ranged from 0.29 to 0.966 and specificity ranged from 0.53 to 0.99. A comparison with the classical ECG criteria for LVH was performed in nine studies. ML algorithms were universally more sensitive than the Cornell voltage, Cornell product, Sokolow-Lyons or Romhilt-Estes criteria. However, none of the ML algorithms had meaningfully better specificity, and four were worse. Many of the ML algorithms included a large number of clinical (age, sex, height, weight), laboratory and detailed ECG waveform data (P, QRS and T wave), making them difficult to utilize in a clinical screening situation. Conclusions: There are over a dozen different ML algorithms for the detection of LVH on a 12-lead ECG that use various ECG signal analyses and/or the inclusion of clinical and laboratory variables. Most improved in terms of sensitivity, but most also failed to outperform specificity compared to the classic ECG criteria. ML algorithms should be compared or tested on the same (standard) database.

Electrocardiogram Interpretation Using Artificial Intelligence: Diagnosis of Cardiac and Extracardiac Pathologic Conditions. How Far Has Machine Learning Reached?

Artificial intelligence (AI) is already widely used in different fields of medicine, making possible the integration of the paraclinical exams with the clinical findings in patients, for a more accurate and rapid diagnosis and treatment decision. The electrocardiogram remains one of the most important, fastest, cheapest, and noninvasive methods of diagnosis in cardiology, despite the rapid development and progression of the technology. Even if studied a long time ago, it still has a lot of less understood features that, with a better understanding, can give more clues to a correct and prompt diagnosis in a short time. The use of AI in the interpretation of the ECG improved the accuracy and the time to diagnosis in different cardiovascular diseases, and more than this, explaining the decision to make AI diagnosis improved the human understanding of the different features of the ECG that might be considered for a more accurate diagnosis. The purpose of this article is to provide an overview of the most recently published articles about the use of AI in ECG interpretation.

Left ventricular hypertrophy detection using electrocardiographic signal

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.

Automated Classification of Left Ventricular Hypertrophy on Cardiac MRI

Left ventricular hypertrophy is an independent predictor of coronary artery disease, stroke, and heart failure. Our aim was to detect LVH cardiac magnetic resonance (CMR) scans with automatic methods. We developed an ensemble model based on a three-dimensional version of ResNet. The input of the network included short-axis and long-axis images. We also introduced a standardization methodology to unify the input images for noise reduction. The output of the network is the decision whether the patient has hypertrophy or not. We included 428 patients (mean age: 49 ± 18 years, 262 males) with LVH (346 hypertrophic cardiomyopathy, 45 cardiac amyloidosis, 11 Anderson–Fabry disease, 16 endomyocardial fibrosis, 10 aortic stenosis). Our control group consisted of 234 healthy subjects (mean age: 35 ± 15 years; 126 males) without any known cardiovascular diseases. The developed machine-learning-based model achieved a 92% F1-score and 97% recall on the hold-out dataset, which is comparable to the medical experts. Experiments showed that the standardization method was able to significantly boost the performance of the algorithm. The algorithm could improve the diagnostic accuracy, and it could open a new door to AI applications in CMR.

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.

Spatial Feature Extraction of Vectorcardiography via Minimum Volume Ellipsoid Enclosure in Classifying Left Ventricular Hypertrophy

The voltage criteria used to diagnose left ventricular hypertrophy (LVH) in the chest and limb leads are by no means absolute. In addition to QRS voltages, QRS axis and duration, and P wave characteristics, repolarization (STT) changes have been focused attention due to their representing left ventricular overload. Vectorcardiography (VCG) has been studied specifically on its repolarization abnormality. The present study aims to devise spatial feature extraction of VCG and assess it in the LVH classification task. A minimum volume ellipsoid enclosure was applied to six segments obtained from upstroke and downstroke of each P, QRS, and T loops of a single-beat VCG. For the evaluation, VCG and 12 lead ECG dataset along with LVH labels of 61 subjects were derived from public open data, PTB-XL. These classification performances were compared with the LVH diagnosis criteria in the standard 12 lead ECG. As a result, the Random Forest classifier trained by the proposed spatial VCG feature resulted in accuracy of 0.904 (95% confidence interval: 0.861-0.947) when the classbalanced dataset was evaluated, which slightly exceeded the feature of 12 lead ECG. The feature importance analysis provided the quantitative ranking of the spatial feature of VCG, which were practically similar to those of ECG in the LVH classification task. Since the VCG are spatially comparable with three-dimensional data of CT, MRI, or Echocardiography, VCG will shed light on the spatial behavior of electrical depolarization and repolarization abnormalities in cardiac diseases.