Machine Learning-Based ADHD Detection From fNIRs Signal During Reverse Stroop Tasks

Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by the symptoms of inattention, hyperactivity, and impulsivity that significantly affect daily functioning. It is usually 1st diagnosed in childhood and often lasts into adulthood. Various researchers introduced different statistical tools to identify children with ADHD based on phonotype, vision, and image-based data. The main causes of children with ADHD are still unknown and its diagnostic accuracy rate remains low. There is still some scopes to establish valid biomarkers for ADHD and improve the classification accuracy, which will help for children enhance their quality of life. This study aimed to establish and determine potential biomarkers for children with ADHD and then proposed a machine learning (ML)-based ADHD detection system. A multicenter approach was employed to collect Reverse Stroop Task (RST) data, including age, behavioral, and physiological indicators from 72 children with ADHD (aged 6–13 years) and 171 typically developing (TD) children. Moreover, we also collected the signal information from each subject using functional near-infrared spectroscopy (fNIRs) and quantified the change in prefrontal cortex oxygenated hemoglobin during RST. At the same time, we also computed the mean signal for every channel during the last 20 seconds of RST. We selected 70% of the dataset as a training set (ADHD: 51 and TD: 120) and the remaining dataset was used as a testing set (ADHD: 21 and TD: 51). To determine the potential biomarkers for ADHD, we employed independent t-test (p<0.05) on training data that contained behavioral, physiological, and signal indicators. These significant biomarkers were used to train six ML-based approaches, including support vector machine, k-nearest neighbors, logistic regression, neural network, linear discriminate analysis and random forest (RF) with 10-fold cross-validation and repeated 10 times for selecting the optimum value of hyperparameters using the classification accuracy. The trained ML-based approaches were used to predict children with ADHD and validate their performance on the testing data. The experimental results showed that the RF-based model obtained a classification accuracy of 91.67%, sensitivity of 95.92%, specificity of 82.61%, precision of 92.16%, F1-Score of 94.00%, Cohen’s Kappa of 80.38%, geometric mean of 89.02%, positive likelihood ratio of 5.51%, negative likelihood ratio of 0.05%, and area under the curve of 0.955. Our proposed system can be used for the diagnosis of children with ADHD.