1
|
Loh HW, Ooi CP, Oh SL, Barua PD, Tan YR, Molinari F, March S, Acharya UR, Fung DSS. Deep neural network technique for automated detection of ADHD and CD using ECG signal. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 241:107775. [PMID: 37651817 DOI: 10.1016/j.cmpb.2023.107775] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/24/2023] [Revised: 08/09/2023] [Accepted: 08/22/2023] [Indexed: 09/02/2023]
Abstract
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.
Collapse
Affiliation(s)
- Hui Wen Loh
- School of Science and Technology, Singapore University of Social Sciences, Singapore
| | - Chui Ping Ooi
- School of Science and Technology, Singapore University of Social Sciences, Singapore
| | - Shu Lih Oh
- Cogninet Australia, Sydney, NSW 2010, Australia
| | - Prabal Datta Barua
- Cogninet Australia, Sydney, NSW 2010, Australia; Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW 2007, Australia; School of Business (Information System), University of Southern Queensland, Australia; Australian International Institute of Higher Education, Sydney, NSW 2000, Australia; School of Science & Technology, University of New England, Australia; School of Biosciences, Taylor's University, Malaysia; School of Computing, SRM Institute of Science and Technology, India; School of Science and Technology, Kumamoto University, Japan; Sydney School of Education and Social work, University of Sydney, Australia
| | - Yi Ren Tan
- Developmental Psychiatry, Institute of Mental Health, Singapore
| | - Filippo Molinari
- Biolab, Department of Electronics and Telecommunications, Politecnico di Torino, 10129 Torino, Italy
| | - Sonja March
- Centre for Health Research and School of Psychology and Wellbeing, University of Southern Queensland, Springfield, Australia
| | - U Rajendra Acharya
- School of Mathematics, Physics, and Computing, University of Southern Queensland, Springfield, Australia.
| | - Daniel Shuen Sheng Fung
- Developmental Psychiatry, Institute of Mental Health, Singapore; Lee Kong Chian School of Medicine, Nanyang Technological University, DUKE NUS Medical School, Yong Loo Lin School of Medicine, National University of Singapore
| |
Collapse
|
2
|
Abstract
WHO defined in 1976 psychopharmaca as drugs affecting psychological functions, behaviour and self-perception. Psychopharmacology is the study of pharmacological agents that affect mental and emotional functions. Creative approach to psychopharmacotherapy reflects a transdisciplinary, integrative and person-centered psychiatry. Psychiatric disorders often occur in cardiac patients and can affect the clinical presentation and morbidity. Cardiovascular (CV) side effects (SE) caused by psychopharmaceutic agents require comprehensive attention. Therapeutic approach can increase placebo and decrease nocebo reactions. The main purpose of this review is to comprehend CV SE of psychotropic drugs (PD). Critical overview of CV SE of PD will be presented in this review. Search was directed but not limited to CV effects of psychopharmacological substances, namely antipsychotics, anxiolytics, hypnotics, sedatives, antidepressants and stimulants. Literature review was performed and data identified by searches of Medline and PubMed for period from 2004 to 2015. Only full articles and abstracts published in English were included. SE of PD are organized according to the following types of CV effects: cardiac and circulatory effects, abnormalities of cardiac repolarisation and arrhythmias and heart muscle disease. There is wide spectrum and various CV effects of PD. Results of this review are based on literature research. The reviewed data came largely from prevalence studies, case reports, and cross-sectional studies. Psychopharmacotherapy of psychiatric disorders is complex and when concomitantly present with CV disease, presentation of drug SEs can significantly contribute to illness course. Further development of creative psychopharmacotherapy is required to deal with CV effects of PD.
Collapse
|
3
|
Lamberti M, Italiano D, Guerriero L, D'Amico G, Siracusano R, Ingrassia M, Germanò E, Calabrò MP, Spina E, Gagliano A. Evaluation of acute cardiovascular effects of immediate-release methylphenidate in children and adolescents with attention-deficit hyperactivity disorder. Neuropsychiatr Dis Treat 2015; 11:1169-74. [PMID: 26056451 PMCID: PMC4431494 DOI: 10.2147/ndt.s79866] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/18/2022] Open
Abstract
Attention-deficit hyperactivity disorder is a frequent condition in children and often extends into adulthood. Use of immediate-release methylphenidate (MPH) has raised concerns about potential cardiovascular adverse effects within a few hours after administration. This study was carried out to investigate acute effects of MPH on electrocardiogram (ECG) in a pediatric population. A total of 54 consecutive patients with attention-deficit hyperactivity disorder (51 males and 3 females; mean age =12.14±2.6 years, range 6-19 years), receiving a new prescription of MPH, underwent a standard ECG 2 hours before and after the administration of MPH 10 mg per os. Basal and posttreatment ECG parameters, including mean QT (QT interval when corrected for heart rate [QTc]), QTc dispersion (QTd) interval duration, T-peak to T-end (TpTe) intervals, and TpTe/QT ratio were compared. Significant modifications of both QTc and QTd values were not found after drug administration. QTd fluctuated slightly from 25.7±9.3 milliseconds to 25.1±8.4 milliseconds; QTc varied from 407.6±12.4 milliseconds to 409.8±12.7 milliseconds. A significant variation in blood pressure (systolic blood pressure 105.4±10.3 vs 109.6±11.5; P<0.05; diastolic blood pressure 59.2±7.1 vs 63.1±7.9; P<0.05) was observed, but all the data were within normal range. Heart rate moved from 80.5±15.5 bpm to 87.7±18.8 bpm. No change in TpTe values was found, but a statistically significant increase in TpTe/QTc intervals was found with respect to basal values (0.207±0.02 milliseconds vs 0.214±0.02 milliseconds; P<0.01). The findings of this study show no significant changes in ECG parameters. TpTe values can be an additional parameter to evaluate borderline cases.
Collapse
Affiliation(s)
- Marco Lamberti
- Division of Child Neurology and Psychiatry, Department of Pediatrics, University of Messina, Messina, Italy ; Department of Clinical and Experimental Medicine, University of Messina, Messina, Italy
| | - Domenico Italiano
- Department of Clinical and Experimental Medicine, University of Messina, Messina, Italy
| | - Laura Guerriero
- Division of Child Neurology and Psychiatry, Department of Pediatrics, University of Messina, Messina, Italy
| | - Gessica D'Amico
- Division of Pediatric Cardiology, Department of Pediatrics, University of Messina, Messina, Italy
| | - Rosamaria Siracusano
- Division of Child Neurology and Psychiatry, Department of Pediatrics, University of Messina, Messina, Italy ; Institution of Clinical Physiology, CNR, Pisa, Italy
| | - Massimo Ingrassia
- Division of Psychology, Department of Humanities and Social Sciences, University of Messina, Messina, Italy
| | - Eva Germanò
- Division of Child Neurology and Psychiatry, Department of Pediatrics, University of Messina, Messina, Italy
| | - Maria Pia Calabrò
- Division of Pediatric Cardiology, Department of Pediatrics, University of Messina, Messina, Italy
| | - Edoardo Spina
- Department of Clinical and Experimental Medicine, University of Messina, Messina, Italy
| | - Antonella Gagliano
- Division of Child Neurology and Psychiatry, Department of Pediatrics, University of Messina, Messina, Italy
| |
Collapse
|
4
|
Nilsen CV. Hjerterisiko ved AD/HD-behandling hos barn. TIDSSKRIFT FOR DEN NORSKE LEGEFORENING 2014; 134:689. [DOI: 10.4045/tidsskr.14.0326] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/02/2022] Open
|