Koh Joel E W, Ooi Chui Ping, Lim-Ashworth Nikki Sj, Vicnesh Jahmunah, Tor Hui Tian, Lih Oh Shu, Tan Ru-San, Acharya U Rajendra, Fung Daniel Shuen Sheng
School of Engineering, Ngee Ann Polytechnic, Singapore.
School of Science and Technology, Singapore University of Social Sciences, Singapore.
Comput Biol Med. 2022 Jan;140:105120. doi: 10.1016/j.compbiomed.2021.105120. Epub 2021 Dec 4.
The most prevalent neuropsychiatric disorder among children is attention deficit hyperactivity disorder (ADHD). ADHD presents with a high prevalence of comorbid disorders such as conduct disorder (CD). The lack of definitive confirmatory diagnostic tests for ADHD and CD make diagnosis challenging. The distinction between ADHD, ADHD + CD and CD is important as the course and treatment are different. Electrocardiography (ECG) signals may become altered in behavioral disorders due to brain-heart autonomic interactions. We have developed a software tool to categorize ADHD, ADHD + CD and CD automatically on ECG signals.
ECG signals from participants were decomposed using empirical wavelet transform into various modes, from which entropy features were extracted. Robust ten-fold cross-validation with adaptive synthetic sampling (ADASYN) and z-score normalization were performed at each fold. Analysis of variance (ANOVA) technique was employed to determine the variability within the three classes, and obtained the most discriminatory features. Highly significant entropy features were then fed to classifiers.
Our model yielded the best classification results with the bagged tree classifier: 87.19%, 87.71% and 86.29% for accuracy, sensitivity and specificity, respectively.
The proposed expert system can potentially assist mental health professionals in the stratification of the three classes, for appropriate intervention using accessible ECG signals.
儿童中最常见的神经精神障碍是注意力缺陷多动障碍（ADHD）。ADHD常伴有品行障碍（CD）等共病，其患病率很高。由于缺乏针对ADHD和CD的确定性确诊诊断测试，使得诊断具有挑战性。区分ADHD、ADHD + CD和CD很重要，因为它们的病程和治疗方法不同。由于脑-心自主神经相互作用，行为障碍可能会使心电图（ECG）信号发生改变。我们开发了一种软件工具，可根据ECG信号自动对ADHD、ADHD + CD和CD进行分类。
使用经验小波变换将参与者的ECG信号分解为各种模式，并从中提取熵特征。在每一折上进行稳健的十折交叉验证，并采用自适应合成采样（ADASYN）和z分数归一化。采用方差分析（ANOVA）技术确定三类之间的变异性，并获得最具区分性的特征。然后将高度显著的熵特征输入分类器。
我们的模型在袋装树分类器上取得了最佳分类结果：准确率、灵敏度和特异性分别为87.19%、87.71%和86.29%。
所提出的专家系统有可能帮助心理健康专业人员对这三类进行分层，以便使用可获取的ECG信号进行适当干预。
