An explainable and interpretable model for attention deficit hyperactivity disorder in children using EEG signals

被引:45
|
作者
Khare, Smith K. [1 ]
Acharya, U. Rajendra [2 ,3 ,4 ,5 ,6 ]
机构
[1] Aarhus Univ, Elect & Comp Engn Dept, DK-8200 Aarhus, Denmark
[2] Univ Southern Queensland, Sch Math Phys & Comp, Springfield, Australia
[3] Singapore Univ Social Sci, Sch Sci & Technol, Dept Biomed Engn, Singapore, Singapore
[4] Asia Univ, Dept Biomed Informat & Med Engn, Taichung, Taiwan
[5] Kumamoto Univ, Kumamoto, Japan
[6] Univ Malaya, Kuala Lumpur, Malaysia
关键词
Attention deficit hyperactivity disorder; Electroencephalography; Variational mode decomposition; Explainable machine learning; Interpretable machine learning; ADHD; DIAGNOSIS; DECOMPOSITION; PREVALENCE; FEATURES;
D O I
10.1016/j.compbiomed.2023.106676
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Background: Attention deficit hyperactivity disorder (ADHD) is a neurodevelopmental disorder that affects a person's sleep, mood, anxiety, and learning. Early diagnosis and timely medication can help individuals with ADHD perform daily tasks without difficulty. Electroencephalogram (EEG) signals can help neurologists to detect ADHD by examining the changes occurring in it. The EEG signals are complex, non-linear, and non -stationary. It is difficult to find the subtle differences between ADHD and healthy control EEG signals visually. Also, making decisions from existing machine learning (ML) models do not guarantee similar performance (unreliable). Method: The paper explores a combination of variational mode decomposition (VMD), and Hilbert transform (HT) called VMD-HT to extract hidden information from EEG signals. Forty-one statistical parameters extracted from the absolute value of analytical mode functions (AMF) have been classified using the explainable boosted machine (EBM) model. The interpretability of the model is tested using statistical analysis and performance measurement. The importance of the features, channels and brain regions has been identified using the glass -box and black-box approach. The model's local and global explainability has been visualized using Local Interpretable Model-agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), Partial Dependence Plot (PDP), and Morris sensitivity. To the best of our knowledge, this is the first work that explores the explainability of the model prediction in ADHD detection, particularly for children. Results: Our results show that the explainable model has provided an accuracy of 99.81%, a sensitivity of 99.78%, 99.84% specificity, an F-1 measure of 99.83%, the precision of 99.87%, a false detection rate of 0.13%, and Mathew's correlation coefficient, negative predicted value, and critical success index of 99.61%, 99.73%, and 99.66%, respectively in detecting the ADHD automatically with ten-fold cross-validation. The model has provided an area under the curve of 100% while the detection rate of 99.87% and 99.73% has been obtained for ADHD and HC, respectively. Conclusions: The model show that the interpretability and explainability of frontal region is highest compared to pre-frontal, central, parietal, occipital, and temporal regions. Our findings has provided important insight into the developed model which is highly reliable, robust, interpretable, and explainable for the clinicians to detect ADHD in children. Early and rapid ADHD diagnosis using robust explainable technologies may reduce the cost of treatment and lessen the number of patients undergoing lengthy diagnosis procedures.
引用
收藏
页数:16
相关论文
共 50 条
  • [21] Epileptiform abnormalities and quantitative EEG in children with attention-deficit/hyperactivity disorder
    Fonseca, Lineu Correa
    Tedrus, Gloria Maria A. S.
    de Moroes, Cesar
    Machado, Amanda de Vicente
    de Almeida, Marcela Pupin
    Fernandes de Oliveira, Deboro Ortolan
    ARQUIVOS DE NEURO-PSIQUIATRIA, 2008, 66 (3A) : 462 - 467
  • [22] INTER AND INTRAHEMISPHERIC EEG NONLINEAR SYNCHRONIZATION IN CHILDREN WITH ATTENTION DEFICIT HYPERACTIVITY DISORDER
    Mendez, L. D.
    Manas, S.
    Duque, M. R.
    Rodriguez, P. J.
    Pereda, E.
    De Vera, L.
    Gonzalez, J. J.
    PEDIATRIC RESEARCH, 2010, 68 : 298 - 299
  • [23] QUANTITATIVE EEG-ANALYSIS IN CHILDREN WITH ATTENTION-DEFICIT-HYPERACTIVITY DISORDER
    ANDERSON, JW
    BARRY, RJ
    CLARK, S
    GORDON, E
    LAZZARO, I
    LEONG, J
    INTERNATIONAL JOURNAL OF PSYCHOPHYSIOLOGY, 1994, 18 (02) : 89 - 90
  • [24] EEG coherence and symptom profiles of children with Attention-Deficit/Hyperactivity Disorder
    Barry, Robert J.
    Clarke, Adam R.
    Hajos, Mihaly
    Dupuy, Franca E.
    McCarthy, Rory
    Selikowitz, Mark
    CLINICAL NEUROPHYSIOLOGY, 2011, 122 (07) : 1327 - 1332
  • [25] EEG-Biocontrol Method in Treating the Attention Deficit Hyperactivity Disorder in Children
    Yu. D. Kropotov
    V. A. Ponomarev
    V. A. Grin'-Yatsenko
    Human Physiology, 2001, 27 (4) : 496 - 504
  • [26] AGE DEPENDENCE ON EEG CORTICAL CONNECTIVITY IN CHILDREN WITH ATTENTION DEFICIT HYPERACTIVITY DISORDER
    Mendez, L. D.
    Manas, S.
    Duque, M. R.
    De Vera, L.
    Pereda, E.
    Gonzalez, J. J.
    EUROPEAN JOURNAL OF NEUROLOGY, 2011, 18 : 140 - 140
  • [27] EEG Coherence in Children with Attention-Deficit/Hyperactivity Disorder and Autistic Features
    Clarke, Adam R.
    Barry, Robert J.
    McCarthy, Rory
    Selikowitz, Mark
    JOURNAL OF DEVELOPMENTAL AND PHYSICAL DISABILITIES, 2021, 33 (04) : 583 - 598
  • [28] Effects of stimulant medications on the EEG of children with attention-deficit/hyperactivity disorder
    Adam R. Clarke
    Robert J. Barry
    Dominique Bond
    Rory McCarthy
    Mark Selikowitz
    Psychopharmacology, 2002, 164 : 277 - 284
  • [29] Mutual Information Analysis of EEG of Children with Attention-Deficit/Hyperactivity Disorder
    Chen, He
    Yan, Jiaqing
    Gu, Yue
    Song, Yan
    Li, Xiaoli
    2017 CHINESE AUTOMATION CONGRESS (CAC), 2017, : 2342 - 2347
  • [30] Acute atomoxetine effects on the EEG of children with Attention-Deficit/Hyperactivity Disorder
    Barry, Robert J.
    Clarke, Adam R.
    Hajos, Mihaly
    McCarthy, Rory
    Selikowitz, Mark
    Bruggemann, Jason M.
    NEUROPHARMACOLOGY, 2009, 57 (7-8) : 702 - 707