Deep neural network technique for automated detection of ADHD and CD using ECG signal
Background and objective: Attention Deficit Hyperactivity problem (ADHD) is a common neurodevelopment problem in children and adolescents that can lead to long-term challenges in life outcomes if left untreated. Also, ADHD is frequently associated with Conduct Disorder (CD), and multiple research ha...
| Main Authors: | , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/174063 |
| _version_ | 1824455574636462080 |
|---|---|
| author | Loh, Hui Wen Ooi, Chui Ping Oh, Shu Lih Barua, Prabal Datta Tan, Yi Ren Molinari, Filippo March, Sonja Acharya, U. Rajendra Fung, Daniel Shuen Sheng |
| author2 | Lee Kong Chian School of Medicine (LKCMedicine) |
| author_facet | Lee Kong Chian School of Medicine (LKCMedicine) Loh, Hui Wen Ooi, Chui Ping Oh, Shu Lih Barua, Prabal Datta Tan, Yi Ren Molinari, Filippo March, Sonja Acharya, U. Rajendra Fung, Daniel Shuen Sheng |
| author_sort | Loh, Hui Wen |
| collection | NTU |
| description | Background and objective: Attention Deficit Hyperactivity problem (ADHD) is a common neurodevelopment problem in children and adolescents that can lead to long-term challenges in life outcomes if left untreated. Also, ADHD is frequently associated with Conduct Disorder (CD), and multiple research have found similarities in clinical signs and behavioral symptoms between both diseases, making differentiation between ADHD, ADHD comorbid with CD (ADHD+CD), and CD a subjective diagnosis. Therefore, the goal of this pilot study is to create the first explainable deep learning (DL) model for objective ECG-based ADHD/CD diagnosis as having an objective biomarker may improve diagnostic accuracy. Methods: The dataset used in this study consist of ECG data collected from 45 ADHD, 62 ADHD+CD, and 16 CD patients at the Child Guidance Clinic in Singapore. The ECG data were segmented into 2 s epochs and directly used to train our 1-dimensional (1D) convolutional neural network (CNN) model. Results: The proposed model yielded 96.04% classification accuracy, 96.26% precision, 95.99% sensitivity, and 96.11% F1-score. The Gradient-weighted class activation mapping (Grad-CAM) function was also used to highlight the important ECG characteristics at specific time points that most impact the classification score. Conclusion: In addition to achieving model performance results with our suggested DL method, Grad-CAM's implementation also offers vital temporal data that clinicians and other mental healthcare professionals can use to make wise medical judgments. We hope that by conducting this pilot study, we will be able to encourage larger-scale research with a larger biosignal dataset. Hence allowing biosignal-based computer-aided diagnostic (CAD) tools to be implemented in healthcare and ambulatory settings, as ECG can be easily obtained via wearable devices such as smartwatches. |
| first_indexed | 2025-02-19T03:40:22Z |
| format | Journal Article |
| id | ntu-10356/174063 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:40:22Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1740632024-03-17T15:38:41Z Deep neural network technique for automated detection of ADHD and CD using ECG signal Loh, Hui Wen Ooi, Chui Ping Oh, Shu Lih Barua, Prabal Datta Tan, Yi Ren Molinari, Filippo March, Sonja Acharya, U. Rajendra Fung, Daniel Shuen Sheng Lee Kong Chian School of Medicine (LKCMedicine) Duke-NUS Medical School Yong Loo Lin School of Medicine, NUS Institute of Mental Health Medicine, Health and Life Sciences Explainable artificial intelligence Deep learning Background and objective: Attention Deficit Hyperactivity problem (ADHD) is a common neurodevelopment problem in children and adolescents that can lead to long-term challenges in life outcomes if left untreated. Also, ADHD is frequently associated with Conduct Disorder (CD), and multiple research have found similarities in clinical signs and behavioral symptoms between both diseases, making differentiation between ADHD, ADHD comorbid with CD (ADHD+CD), and CD a subjective diagnosis. Therefore, the goal of this pilot study is to create the first explainable deep learning (DL) model for objective ECG-based ADHD/CD diagnosis as having an objective biomarker may improve diagnostic accuracy. Methods: The dataset used in this study consist of ECG data collected from 45 ADHD, 62 ADHD+CD, and 16 CD patients at the Child Guidance Clinic in Singapore. The ECG data were segmented into 2 s epochs and directly used to train our 1-dimensional (1D) convolutional neural network (CNN) model. Results: The proposed model yielded 96.04% classification accuracy, 96.26% precision, 95.99% sensitivity, and 96.11% F1-score. The Gradient-weighted class activation mapping (Grad-CAM) function was also used to highlight the important ECG characteristics at specific time points that most impact the classification score. Conclusion: In addition to achieving model performance results with our suggested DL method, Grad-CAM's implementation also offers vital temporal data that clinicians and other mental healthcare professionals can use to make wise medical judgments. We hope that by conducting this pilot study, we will be able to encourage larger-scale research with a larger biosignal dataset. Hence allowing biosignal-based computer-aided diagnostic (CAD) tools to be implemented in healthcare and ambulatory settings, as ECG can be easily obtained via wearable devices such as smartwatches. Ministry of Education (MOE) Published version This work was supported by MOE Start-up Research Fund (RF10018C). 2024-03-13T03:34:43Z 2024-03-13T03:34:43Z 2023 Journal Article Loh, H. W., Ooi, C. P., Oh, S. L., Barua, P. D., Tan, Y. R., Molinari, F., March, S., Acharya, U. R. & Fung, D. S. S. (2023). Deep neural network technique for automated detection of ADHD and CD using ECG signal. Computer Methods and Programs in Biomedicine, 241, 107775-. https://dx.doi.org/10.1016/j.cmpb.2023.107775 0169-2607 https://hdl.handle.net/10356/174063 10.1016/j.cmpb.2023.107775 37651817 2-s2.0-85169001367 241 107775 en RF10018C Computer Methods and Programs in Biomedicine © 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/bync-nd/4.0/). application/pdf |
| spellingShingle | Medicine, Health and Life Sciences Explainable artificial intelligence Deep learning Loh, Hui Wen Ooi, Chui Ping Oh, Shu Lih Barua, Prabal Datta Tan, Yi Ren Molinari, Filippo March, Sonja Acharya, U. Rajendra Fung, Daniel Shuen Sheng Deep neural network technique for automated detection of ADHD and CD using ECG signal |
| title | Deep neural network technique for automated detection of ADHD and CD using ECG signal |
| title_full | Deep neural network technique for automated detection of ADHD and CD using ECG signal |
| title_fullStr | Deep neural network technique for automated detection of ADHD and CD using ECG signal |
| title_full_unstemmed | Deep neural network technique for automated detection of ADHD and CD using ECG signal |
| title_short | Deep neural network technique for automated detection of ADHD and CD using ECG signal |
| title_sort | deep neural network technique for automated detection of adhd and cd using ecg signal |
| topic | Medicine, Health and Life Sciences Explainable artificial intelligence Deep learning |
| url | https://hdl.handle.net/10356/174063 |
| work_keys_str_mv | AT lohhuiwen deepneuralnetworktechniqueforautomateddetectionofadhdandcdusingecgsignal AT ooichuiping deepneuralnetworktechniqueforautomateddetectionofadhdandcdusingecgsignal AT ohshulih deepneuralnetworktechniqueforautomateddetectionofadhdandcdusingecgsignal AT baruaprabaldatta deepneuralnetworktechniqueforautomateddetectionofadhdandcdusingecgsignal AT tanyiren deepneuralnetworktechniqueforautomateddetectionofadhdandcdusingecgsignal AT molinarifilippo deepneuralnetworktechniqueforautomateddetectionofadhdandcdusingecgsignal AT marchsonja deepneuralnetworktechniqueforautomateddetectionofadhdandcdusingecgsignal AT acharyaurajendra deepneuralnetworktechniqueforautomateddetectionofadhdandcdusingecgsignal AT fungdanielshuensheng deepneuralnetworktechniqueforautomateddetectionofadhdandcdusingecgsignal |