Automated classification of attention deficit hyperactivity disorder and conduct disorder using entropy features with ECG signals

Joel E W Koh; Chui Ping Ooi; Nikki Sj Lim-Ashworth; Jahmunah Vicnesh; Hui Tian Tor; Oh Shu Lih; Ru-San Tan; U Rajendra Acharya; Daniel Shuen Sheng Fung

doi:10.1016/j.compbiomed.2021.105120

Automated classification of attention deficit hyperactivity disorder and conduct disorder using entropy features with ECG signals

Comput Biol Med. 2022 Jan:140:105120. doi: 10.1016/j.compbiomed.2021.105120. Epub 2021 Dec 4.

Authors

Joel E W Koh¹, Chui Ping Ooi², Nikki Sj Lim-Ashworth³, Jahmunah Vicnesh¹, Hui Tian Tor², Oh Shu Lih¹, Ru-San Tan⁴, U Rajendra Acharya⁵, Daniel Shuen Sheng Fung³

Affiliations

¹ School of Engineering, Ngee Ann Polytechnic, Singapore.
² School of Science and Technology, Singapore University of Social Sciences, Singapore.
³ Developmental Psychiatry, Institute of Mental Health, Singapore.
⁴ National Heart Centre Singapore, Singapore. Electronic address: tanrsnhc@gmail.com.
⁵ School of Engineering, Ngee Ann Polytechnic, Singapore; School of Science and Technology, Singapore University of Social Sciences, Singapore; Department of Bioinformatics and Medical Engineering, Asia University, Taiwan, ROC; School of Management and Enterprise University of Southern Queensland, Springfield, Australia. Electronic address: aru@np.edu.sg.

PMID: 34896884
DOI: 10.1016/j.compbiomed.2021.105120

Abstract

Background: 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.

Method: 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.

Results: 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.

Conclusion: The proposed expert system can potentially assist mental health professionals in the stratification of the three classes, for appropriate intervention using accessible ECG signals.

Keywords: Attention deficit hyperactivity disorder; Conduct disorder; Empirical wavelet transform; Ensemble classifiers; Entropies; Machine learning; Ten-fold validation.