EEG Connectivity as Predictor of ICAN ADHD Children's Improvement After Completion of Theta Beta Ratio Neurofeedback: Machine Learning Analyses.

Journal: Applied psychophysiology and biofeedback
Published Date: May 26, 2025

Abstract

Attention deficit hyperactivity disorder is a prevalent syndrome that costs billions of dollars annually. Finding meaningful interventions based upon predictive baseline EEG values can reduce uncertainty in symptom remediation. This study aims to deepen the understanding of ADHD neurophysiology and contribute to the development of personalized approaches in its treatment. This study retrospectively assessed EEG connectivity of participants in the International Collaborative ADHD Neurofeedback (ICAN) randomized controlled trial (7-10YO, N = 83) of theta/beta ratio neurofeedback (TBR-NFB). Using machine learning, it examined the relationship between inattention improvement on the Conners' Teacher and Parent Rating Scales (CTPRS) and specific baseline frequency connections within networks relevant to ADHD to find predictors of clinical improvement. Analyses were also performed considering specific comorbidities, slow cognitive tempo, ADHD presentation, pre-to-post network changes, and treatment group. Dysregulation in the ventral and dorsal attention networks, and delta and hibeta frequency bands throughout all networks were the strongest baseline connectivity predictors of clinical improvement on the CTPRS. The connectivity patterns predicting improvement differed significantly between active NFB and control. Other findings included predictors of improvements in EEG connectivity dysregulations, demographics, and connectivity patterns of comorbidity. Machine learning algorithms identified EEG features in connectivity, network, and frequency to assess when considering ADHD interventions. There was evidence, albeit weak, that the EEG features we studied predicted improvement with the ICAN TBR-NFB protocol. When considering interventions for ADHD symptoms, a multi-channel EEG evaluation that focuses on specific brain connectivity patterns may offer insight into treatment choice.

Authors

  • Cynthia Kerson
    Department of Applied Psychophysiology, Saybrook University, Pasadena, CA, USA. ckerson@saybrook.edu.
  • Maha Yazbeck
    Integrated Systems Engineering, The Ohio State University, Columbus, OH, USA.
  • Behnoosh Shahsavaripoor
    Department of Psychiatry and Behavioral Health, Nisonger Center, College of Medicine, Ohio State University Wexner Medical Center, Columbus, OH, USA.
  • Rebekah Walker
    iSyncBrain, Arcadia, CA, USA.
  • Phoebe Manalang-Monnier
    Department of Applied Psychophysiology, Saybrook University, Pasadena, CA, USA.
  • Theodore Allen
    Integrated Systems Engineering, The Ohio State University, Columbus, OH, USA.
  • L Eugene Arnold
    Ohio State University, Columbus, OH, U.S.A.
  • Joel Lubar
    Posthumous, Southeastern Neurofeedback Institute, Pompano Beach, FL, USA.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals