ABSTRACT
Objective: To establish valid, objective biomarkers for ADHD using machine learning. Method: Machine learning was used to predict disorder severity from new brain function data, using a support vector machine (SVM). A multicenter approach was used to collect data for machine learning training, including behavioral and physiological indicators, age, and reverse Stroop task (RST) data from 108 children with ADHD and 108 typically developing (TD) children. Near-infrared spectroscopy (NIRS) was used to quantify change in prefrontal cortex oxygenated hemoglobin during RST. Verification data were from 62 children with ADHD and 37 TD children from six facilities in Japan. Results: The SVM general performance results showed sensitivity of 88.71%, specificity of 83.78%, and an overall discrimination rate of 86.25%. Conclusion: A SVM using an objective index from RST may be useful as an auxiliary biomarker for diagnosis for children with ADHD.
Subject(s)
Attention Deficit Disorder with Hyperactivity , Attention Deficit Disorder with Hyperactivity/diagnosis , Child , Humans , Japan , Machine Learning , Prefrontal Cortex , Spectroscopy, Near-InfraredABSTRACT
BACKGROUND: The neural correlates of executive function disorders are thought to be predominantly localized within the prefrontal cortex (PFC). However, no study to date has investigated changes in this system across different age groups in children with attention deficit hyperactivity disorder (ADHD). Thus, this study aimed to explore changes in PFC function in children with ADHD. METHODS: Study participants included typically developing (TD) children (nâ¯=â¯140) and children with ADHD (nâ¯=â¯67) of primary school age. Behavioral executive functions and their neural basis were evaluated between the TD children and children with ADHD and also across different age periods (younger and older children). To examine executive function, inhibitory control was assessed using the reverse Stroop task, and PFC near-infrared spectroscopic measurements were used to investigate the neural mechanisms involved. RESULTS: Both ADHD symptoms and the ability to inhibit color interference improved with age. Compared to TD children, children with ADHD demonstrated decreased activation of the right and middle PFC across all age groups. Interestingly, the left PFC appeared to play a compensatory role. CONCLUSION: Children with ADHD exhibited changes in PFC function that varied with age. Longitudinal studies are required to assess the potential of using PFC function as an early biomarker of ADHD.
Subject(s)
Attention Deficit Disorder with Hyperactivity/physiopathology , Frontal Lobe/physiopathology , Age Factors , Attention Deficit Disorder with Hyperactivity/diagnostic imaging , Attention Deficit Disorder with Hyperactivity/metabolism , Brain Mapping/methods , Child , Executive Function/physiology , Female , Frontal Lobe/diagnostic imaging , Humans , Image Processing, Computer-Assisted/methods , Magnetic Resonance Imaging/methods , Male , Prefrontal Cortex/diagnostic imaging , Prefrontal Cortex/physiopathology , Spectroscopy, Near-Infrared/methodsABSTRACT
Failure of executive function (EF) is a core symptom of attention-deficit/hyperactivity disorder (ADHD). However, various results have been reported and sufficient evidence is lacking. In the present study, we evaluated the characteristics of children with ADHD using the Stroop task (ST) and reverse Stroop task (RST) that reflects the inhibition function of EF. We compared children with ADHD, typically developing children (TDC), and children with autism spectrum disorder (ASD), which is more difficult to discriminate from ADHD. A total of 10 children diagnosed with ADHD, 15 TDC, and 11 children diagnosed with ASD, all matched by age, sex, language ability, and intelligence quotient, participated in this study. While each subject performed computer-based ST and RST with a touch panel, changes in oxygenated hemoglobin (oxy-Hb) were measured in the prefrontal cortex (PFC) by near-infrared spectroscopy (NIRS) to correlate test performance with neural activity. Behavioral performance significantly differed among 3 groups during RST but not during ST. The ADHD group showed greater color interference than the TDC group. In addition, there was a negative correlation between right lateral PFC (LPFC) activity and the severity of attention deficit. Children with ADHD exhibit several problems associated with inhibition of color, and this symptom is affected by low activities of the right LPFC. In addition, it is suggested that low hemodynamic activities in this area are correlated with ADHD.
