Electroencephalogram (EEG) based prediction of attention deficit hyperactivity disorder (ADHD) using machine
Nitin Ahire1, R N Awale2, Abhay Wagh3
1Department of Electronics and Telecommunication, Xavier Institute of Engineering, Mumbai, India.
Applied Neuropsychology. Adult
|August 30, 2023
Summary
Electroencephalogram (EEG) analysis reveals distinct brain patterns in children with Attention-Deficit Hyperactivity Disorder (ADHD). This study achieved 96% accuracy in identifying ADHD using EEG data, offering a potential diagnostic aid.
Area of Science:
- Neuroscience
- Pediatric Psychiatry
- Biomedical Engineering
Background:
- Attention-Deficit Hyperactivity Disorder (ADHD) is a common neurodevelopmental disorder in children.
- ADHD frequently co-occurs with learning deficits, anxiety, depression, and other behavioral disorders.
- Accurate and early diagnosis of ADHD is crucial for effective intervention.
Purpose of the Study:
- To investigate distinct Electroencephalogram (EEG) patterns in children diagnosed with ADHD.
- To evaluate the efficacy of machine learning algorithms in classifying ADHD based on EEG features.
- To identify specific electrode sites associated with ADHD-related EEG characteristics.
Main Methods:
- Resting-state, open-eye EEG signals were recorded from 61 children with ADHD and 60 healthy controls.
- Morphological and Power Spectral Density (PSD) features were extracted from EEG data.
- Principal Component Analysis (PCA) was used for dimensionality reduction, followed by classification using AdaBoost, K-Nearest Neighbour (KNN), Naive Bayes, and random forest algorithms.
Main Results:
- The Bernoulli Naive Bayes classifier achieved the highest diagnostic accuracy of 96%.
- Significant EEG characteristics for ADHD classification were identified at frontal (F), central (C), and parietal (P) electrode sites.
- Distinct EEG patterns were observed in children with ADHD compared to healthy controls.
Conclusions:
- EEG signal analysis, particularly using specific features and machine learning, shows promise for ADHD diagnosis in children.
- The findings suggest that EEG can serve as a supplementary tool to aid in the diagnosis of ADHD.
- Further research can refine EEG-based diagnostic methods for improved clinical application.
