Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Niayesh Highway, Valiasr Ave., Tehran, 19969111541, Iran.
Behyan Clinic, Pardis New Town, Tehran, Iran.
Cardiovasc Eng Technol. 2023 Dec;14(6):786-800. doi: 10.1007/s13239-023-00687-x. Epub 2023 Oct 17.
An electrocardiogram (ECG) has been extensively used to detect rhythm disturbances. We sought to determine the accuracy of different machine learning in distinguishing abnormal ECGs from normal ones in children who were examined using a resting 12-Lead ECG machine, and we also compared the manual and automated measurement using the modular ECG Analysis System (MEANS) algorithm of ECG features.
Altogether, 10745 ECGs were recorded for students aged 6 to 18. Manual and automatic ECG features were extracted for each participant. Features were normalized using Z-score normalization and went through the student's t-test and chi-squared test to measure their relevance. We applied the Boruta algorithm for feature selection and then implemented eight classifier algorithms. The dataset was split into training (80%) and test (20%) partitions. The performance of the classifiers was evaluated on the test data (unseen data) by 1000 bootstrap, and sensitivity (SEN), specificity (SPE), AUC, and accuracy (ACC) were reported.
In univariate analysis, the highest performance was heart rate and RR interval in the manual dataset and heart rate in an automated dataset with AUC of 0.72 and 0.71, respectively. The best classifiers in the manual dataset were random forest (RF) and quadratic-discriminant-analysis (QDA) with AUC, ACC, SEN, and SPE equal to 0.93, 0.98, 0.69, 0.99, and 0.90, 0.95, 0.75, 0.96, respectively. In the automated dataset, QDA (AUC: 0.89, ACC:0.92, SEN:0.71, SPE:0.93) and stack learning (SL) (AUC:0.89, ACC:0.96, SEN:0.61, SPE:0.99) reached best performances.
This study demonstrated that the manual measurement of 12-Lead ECG features had better performance than the automated measurement (MEANS algorithm), but some classifiers had promising results in discriminating between normal and abnormal cases. Further studies can help us evaluate the applicability and efficacy of machine-learning approaches for distinguishing abnormal ECGs in community-based investigations in both adults and children.
心电图（ECG）已广泛用于检测节律紊乱。我们旨在确定不同机器学习在使用静止 12 导联心电图机检查的儿童中区分正常心电图和异常心电图的准确性，我们还比较了使用模块化心电图分析系统（MEANS）算法的手动和自动测量心电图特征。
共记录了 10745 名 6 至 18 岁学生的心电图。为每位参与者提取手动和自动心电图特征。使用 Z 分数标准化对特征进行标准化，并通过学生 t 检验和卡方检验来测量其相关性。我们应用 Boruta 算法进行特征选择，然后实现了 8 种分类器算法。数据集分为训练（80%）和测试（20%）两个部分。通过 1000 次自举，在测试数据（未见数据）上评估分类器的性能，并报告灵敏度（SEN）、特异性（SPE）、AUC 和准确性（ACC）。
在单变量分析中，手动数据集中表现最好的特征是心率和 RR 间期，自动数据集中表现最好的特征是心率，其 AUC 分别为 0.72 和 0.71。在手动数据集中表现最好的分类器是随机森林（RF）和二次判别分析（QDA），其 AUC、ACC、SEN 和 SPE 分别为 0.93、0.98、0.69、0.99 和 0.90、0.95、0.75、0.96。在自动数据集，QDA（AUC：0.89，ACC：0.92，SEN：0.71，SPE：0.93）和堆叠学习（SL）（AUC：0.89，ACC：0.96，SEN：0.61，SPE：0.99）达到了最佳性能。
本研究表明，12 导联心电图特征的手动测量比自动测量（MEANS 算法）性能更好，但一些分类器在区分正常和异常病例方面有很好的效果。进一步的研究可以帮助我们评估机器学习方法在成人和儿童社区调查中区分异常心电图的适用性和效果。
