Entropy-Based Quantitative Electroencephalogram Analysis for Diagnosing Attention-Deficit Hyperactivity Disorder in...

Area of Science:

• Neuroscience
• Biomedical Engineering
• Psychiatry

Background:

• Current attention-deficit hyperactivity disorder (ADHD) diagnosis relies on subjective symptom checklists, leading to potential misdiagnosis.
• The Federal Drug Administration-approved theta/beta ratio (TBR) from electroencephalogram (EEG) has shown inconsistent results in differentiating ADHD from controls.
• Distinct ADHD presentations in boys and girls necessitate sex-specific diagnostic approaches.

Purpose of the Study:

• To develop and evaluate a novel EEG analysis method using approximate entropy (ApEn) for diagnosing ADHD in girls.
• To compare the diagnostic efficacy of ApEn with the established TBR method.

Main Methods:

• The study enrolled 30 girls diagnosed with ADHD and 30 age-matched controls.
• Electroencephalogram (EEG) data were analyzed using approximate entropy (ApEn) to measure brain signal complexity.
• Feature descriptors derived from ApEn were compared against those from the theta/beta ratio (TBR) for diagnostic performance.

Main Results:

• ApEn analysis revealed significantly higher complexity in most brain areas for the control group compared to the ADHD group.
• ApEn-based feature descriptors demonstrated superior diagnostic performance over TBR.
• Key metrics for ApEn included an average true positive rate of 0.846, average true negative rate of 0.814, average accuracy of 0.817, and an average area under the receiver operating characteristic curve of 0.862.

Conclusions:

• Approximate entropy (ApEn) analysis of EEG signals shows greater potential than the theta/beta ratio (TBR) for differentiating girls with ADHD from controls.
• ApEn offers a more objective and potentially more accurate method for ADHD diagnosis in this demographic.
• Further research into ApEn-based EEG analysis could refine ADHD diagnostic tools.