Neuraxis
ADHD Diagnostic Support
EEG-based attention and hyperactivity biomarker analysis for ADHD diagnostic decision support. The most advanced module in the SynapCore platform, with validated research results across paediatric and adult populations.
What Neuraxis Does
Neuraxis analyses resting-state EEG recordings to extract spectral power features associated with attention-deficit/hyperactivity disorder (ADHD). It processes multi-channel EEG data through SynapCore's shared pipeline, extracts frequency band features, normalises them against population baselines, and produces a probability score indicating the likelihood of ADHD-consistent neural patterns.
The output is a structured clinical decision support report designed for review by a qualified clinician. Neuraxis does not diagnose. It provides objective, data-driven information to support the clinical decision-making process.
Spectral Band Features
Neuraxis extracts features from three primary EEG frequency bands associated with attentional and cognitive processing.
Theta (4-8 Hz)
Elevated theta power, particularly over frontal regions, is one of the most consistently reported EEG markers in ADHD research. Neuraxis quantifies absolute and relative theta power across all electrode sites.
Alpha (8-13 Hz)
Alpha band activity reflects cortical arousal and attentional states. Neuraxis analyses alpha power distribution and theta/alpha ratio, a metric associated with attentional regulation differences in ADHD populations.
Beta (13-30 Hz)
Beta activity is linked to active cognitive processing and motor inhibition. Neuraxis evaluates beta power and the theta/beta ratio (TBR), which has been extensively studied as a potential ADHD biomarker.
LightGBM Classifier
Neuraxis uses a LightGBM gradient-boosted decision tree ensemble, selected for its strong performance on structured tabular data, computational efficiency, and interpretability.
LOSO Cross-Validation
All metrics are validated using leave-one-subject-out cross-validation. Each subject is held out entirely during training, ensuring the model is evaluated on completely unseen individuals. This is the most conservative and clinically realistic validation strategy.
Z-Score Normalization
Spectral features are normalised against population baselines from the CHBMP normative dataset (282 subjects). This transforms raw power values into standardised deviation scores, reducing inter-individual variability and improving cross-site generalisation.
Feature Importance
LightGBM provides native feature importance rankings that map directly to neurophysiologically meaningful frequency bands. This supports clinical interpretability, allowing clinicians to understand which EEG features contributed most to the model output.
Performance Metrics
All results obtained using LOSO cross-validation on public research datasets. These are preliminary research metrics, not clinical performance claims.
Neuraxis-Child v1.0
Research PhaseAUC
~0.845
Balanced Accuracy
~0.802
Validation
LOSO CV
Dataset
IEEE ADHD
Population
Paediatric
Age Range
5-17 years
Neuraxis-Adult v1.0
Research PhaseAUC
~0.727
Balanced Accuracy
Not reported
Validation
LOSO CV
Dataset
TDBRAIN
Population
Adult
Age Range
18-35 years
Full validation report including sensitivity, specificity and MCC in preparation. All reported metrics are preliminary research results. Research Use Only (RUO).
Research Datasets
IEEE ADHD Dataset
Publicly available paediatric EEG dataset with clinical ADHD diagnoses. Multi-channel recordings following standardised acquisition protocols. Used as the primary training and validation set for Neuraxis-Child v1.0.
TDBRAIN
Adult EEG database from the University of Twente. Subset of 72 subjects within the adult ADHD-relevant age range. Provides independent adult population data for Neuraxis-Adult validation with different acquisition parameters.
Research Use Only
Neuraxis is currently in research and development. It is not approved, cleared, or certified for clinical diagnostic use by any regulatory authority. All results are preliminary research metrics obtained under controlled experimental conditions. Neuraxis does not diagnose ADHD. It is designed to support qualified clinicians with objective, data-driven information.