Comparing the performance of artificial intelligence and conventional diagnosis criteria for detecting left ventricular hypertrophy using electrocardiography

Abstract

Aims Although left ventricular hypertrophy (LVH) has a high incidence and clinical importance, the conventional diagnosis criteria for detecting LVH using electrocardiography (ECG) has not been satisfied. We aimed to develop an artificial intelligence (AI) algorithm for detecting LVH. Methods and results This retrospective cohort study involved the review of 21 286 patients who were admitted to two hospitals between October 2016 and July 2018 and underwent 12-lead ECG and echocardiography within 4 weeks. The patients in one hospital were divided into a derivation and internal validation dataset, while the patients in the other hospital were included in only an external validation dataset. An AI algorithm based on an ensemble neural network (ENN) combining convolutional and deep neural network was developed using the derivation dataset. And we visualized the ECG area that the AI algorithm used to make the decision. The area under the receiver operating characteristic curve of the AI algorithm based on ENN was 0.880 (95% confidence interval 0.877–0.883) and 0.868 (0.865–0.871) during the internal and external validations. These results significantly outperformed the cardiologist’s clinical assessment with Romhilt-Estes point system and Cornell voltage criteria, Sokolov-Lyon criteria, and interpretation of ECG machine. At the same specificity, the AI algorithm based on ENN achieved 159.9%, 177.7%, and 143.8% higher sensitivities than those of the cardiologist’s assessment, Sokolov-Lyon criteria, and interpretation of ECG machine. Conclusion An AI algorithm based on ENN was highly able to detect LVH and outperformed cardiologists, conventional methods, and other machine learning techniques.

Artificial intelligence algorithm for detecting myocardial infarction using six-lead electrocardiography

“…Deep learning is a type of artificial intelligence approach that extracts and uses meaningful patterns from complex digital data and has recently been used to analyze ECGs for diagnosing an arrhythmia, heart failure, left ventricular hypertrophy, valvular heart disease, age, and sex [11][12][13][14][15][16] . To develop a reliable MI detecting method based on ECG, we used deep learning.…”

ECG Monitoring Systems: Review, Architecture, Processes, and Key Challenges

“…Table 5 summarizes the aforementioned service-based ECG monitoring system classification. In Table 5, we further classify the systems focusing on disease diagnosis into two main categories: (1) general CVDs, having three subcategories including Arrhythmia, AF, and other abnormalities, such as, such as left ventricular hypertrophy [11]; unexplained syncope [162]; long QT syndrome [163]; depression [164] and coronary heart disease [165], and (2) sleep apnea.…”

“…As a result, ECG monitoring systems have been developed and widely used in the healthcare sector for the past few decades and have significantly evolved over time due to the emergence of smart enabling technologies [10][11][12][13]. Nowadays, ECG monitoring systems are used in hospitals [14][15][16][17], homes [18][19][20], outpatient ambulatory settings [21][22][23], and in remote contexts [24].…”

Artificial intelligence algorithm for predicting cardiac arrest using electrocardiography

“…The most important aspect of deep learning is its ability to extract features from high dimensional complex data and formulate algorithms from various types of data, such as images, two-dimensional (2D) data, and waveforms [ 20 ]. Recently, deep learning has been used to analyze ECGs for diagnosing left ventricular hypertrophy, aortic stenosis, atrial fibrillation, heart failure, and even determining age and sex [ 21 – 24 ]. We hypothesized that DLAs could effectively predict cardiac arrests.…”