Attention deficit and hyperactivity disorder classification in quantitative EEG signals using machine learning algorithms - Abstract

Aug 4, 2026

Machine learning-based classification for attention deficit and hyperactivity disorder (ADHD) is increasingly used to support clinical practice with quantitative observation. The study proposes a feature extraction pipeline for quantitative EEG (qEEG) using continuous wavelet transform (CWT) features, then evaluates classification of children with ADHD versus healthy subjects. Classifier performance is compared before and after applying principal component analysis (PCA) to features prior to k-nearest neighbors (KNN), multilayer perceptron (MLP), and support vector machine (SVM). Results show overall improvement after PCA, with KNN accuracy rising from 61.84% to 69.21%, while other classifiers decline.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Abstract

Introduction

ADHD and clinical diagnosis

EEG and quantitative EEG (qEEG)

Frequency bands and prior findings

Continuous wavelet transform (CWT) and features

Machine learning approaches for EEG classification

Attention deficit and hyperactivity disorder classification in quantitative EEG signals using machine learning algorithms Syifani Ihfadza Aliyah1, Sastra Kusuma Wijaya1, Yetty Ramli2 1Department of Physics, Faculty of Mathematics and Natural Sciences, Universitas Indonesia, Depok, Indonesia 2Department of Neurology, Faculty of Medicine, Universitas Indonesia, Depok, Indonesia | Article history:
Received Nov 21, 2023 Revised Oct 2, 2024 Accepted Oct 7, 2024 | Attention deficit and hyperactivity disorder (ADHD) classification method as a quantitative observation has been continually improved to assist medical practitioners. Currently, machine learning algorithms such as k-nearest neighbors (KNN), multilayer perceptron (MLP), and support vector machine (SVM) are widely used. This study proposed a feature extraction method for quantitative electroencephalography (qEEG) data derived from the continuous wavelet transform (CWT) to classify children with ADHD versus healthy subjects. Subsequently, this study compared the performance of the classification pipeline before and after the implementation of principal component analysis (PCA) on the features prior to processing with machine learning algorithms. The results revealed that the overall performance of the classifiers consistently improved after the implementation of PCA. The results highlight the varying impact of PCA on classifier performance, with KNN showing an improvement in testing accuracy from 61.84% to 69.21% following PCA implementation, while the other classifiers showed deterioration in performance. These findings suggest that while PCA may be beneficial for some classifiers, its impact on performance varies depending on the specific characteristics of the dataset and the classifier utilized. Moreover, this study provides insight for future implementation of the classification method for ADHD patients across a more specific clinical range of the spectrum.
This is an open access article under the CC BY-SA license.
| | --- | --- | | Keywords:
ADHD
Machine learning classification Principal component analysis Quantitative EEG
Wavelet transform | | Corresponding Author: Sastra Kusuma Wijaya Department of Physics, Faculty of Mathematics and Natural Sciences, Universitas Indonesia Depok, West Java, Indonesia Email: [skwijaya@sci.ui.ac.id](skwijaya@sci.ui.ac.id) Article Info ABSTRACT 1. INTRODUCTION Attention deficit and hyperactivity disorder (ADHD) is a neurodevelopmental disorder that affects millions of children and adults worldwide, and is characterized by disruptive inattention, excessive activity, and impulsive actions [1] . ADHD impacts around 5–7% of children and 2–5% of adults globally [2] . The most common methods for psychiatrists, pediatricians, neurologists, and psychologists on ADHD are clinical observations [3] . However, in recent years, methods based on brain electrical signals through spectral analysis have aided healthcare professionals in the diagnosis of ADHD [4] . Electroencephalography (EEG) is a non-invasive method for acquiring electrical activity originating from neurons in the brain that can be measured through the scalp [5] . This procedure involves placing electrodes on the scalp to record EEG signals. EEG has proven to be valuable tool in assisting the quantitative diagnosis of ADHD as it provides information about brain electrical activity [6] . EEG has evolved into quantitative EEG (qEEG), where EEG signals are mapped for their brain activity patterns using digital signals and mathematical algorithms [7] . In 2005, Niedermeyer [8] highlighted the role of qEEG in understanding brain activity patterns and their associations with cognitive disorders. The qEEG signal is a useful tool for measuring and analyzing brain activity that plays a crucial role in identifying specific patterns that indicate certain symptoms and aiding in the treatment of various mental health disorders, such as ADHD [9] . The frequen

FAQs

What features are used for classifying ADHD from quantitative EEG signals?

The approach extracts features from qEEG using the continuous wavelet transform (CWT), producing time-frequency and nonlinear representations for classification.

How does principal component analysis (PCA) affect classifier performance?

Applying PCA to the extracted features improves the overall performance of the classification pipeline, but the impact varies by classifier.

Which classifier showed the strongest improvement after PCA?

KNN improved testing accuracy from 61.84% to 69.21% after PCA, while other classifiers experienced performance deterioration.

Aug 4, 2026

Upload by Evangeline