Artificial Intelligence (AI) is changing how we tackle health issues, especially mental health. Depression, a common and serious mental illness, is set to become the leading cause of disability by 2040. To diagnose it early, we need simple, affordable methods using clear signs. This study uses machine learning and deep learning to analyze brainwave patterns from EEG (electroencephalogram) tests. Researchers extracted different features from these brainwaves and tested three different models: 1D Convolutional Neural Network (1DCNN), Support Vector Machine (SVM), and Logistic Regression (LR). They tested these models on EEG data from 34 people with Major Depressive Disorder (MDD) and 30 healthy individuals. The data was collected in three scenarios: when the person was doing a task, with eyes closed, and with eyes open. Each model was applied to all three types of brainwaves, making nine experiments. The results showed that brainwaves from task-doing gave the highest accuracy rates for all models. This technique even outdid some current top methods. These findings show that EEG tests could be a game-changer for depression diagnosis and open doors for future research. The methods were also found to be reliable and robust, with statistical significance proven.

Brainwaves in Depression: A New Machine Learning Approach

Actions