A Multimodal Dataset for Neurophysiological and AI Applications.

Area of Science:

• Neuroscience
• Computational Psychiatry
• Developmental Psychology

Background:

• Attention Deficit Hyperactivity Disorder (ADHD) is a common neurodevelopmental disorder.
• Current ADHD diagnosis relies on subjective clinical assessments, lacking objectivity.
• Objective neurophysiological measures (EEG, eye tracking, EDA) show promise but require large datasets.

Purpose of the Study:

• To introduce the BALLADEER ADHD Dataset, a multimodal resource for ADHD research.
• To provide a public dataset integrating EEG, eye-tracking, and physiological signals.
• To facilitate the development of objective ADHD diagnostic tools and biomarker discovery.

Main Methods:

• Collected simultaneous EEG, eye-tracking, and electrodermal activity (EDA) data.
• Included children and adolescents diagnosed with ADHD and neurotypical controls.
• Utilized cognitive tasks targeting attentional control, response inhibition, and cognitive flexibility.

Main Results:

• The BALLADEER ADHD Dataset is now publicly available.
• The dataset enables cross-modal analysis of neurophysiological and physiological signals.
• Facilitates machine learning model development for ADHD classification.

Conclusions:

• The BALLADEER ADHD Dataset addresses the need for large, public, multimodal data in ADHD research.
• Publicly releasing this dataset promotes transparency, reproducibility, and innovation.
• This resource supports advancements in computational neuroscience for understanding and diagnosing ADHD.