Research use only. NeuroPD studies EEG-biomarker robustness across datasets. It does not diagnose Parkinson's disease and is not a medical device.
Why it fails

Dataset identity is the loudest thing in the signal

Turn the same features to a different question — which dataset is this? — and a classifier answers far more accurately than it predicts disease. Site and acquisition dominate the feature space, which is exactly why the biomarker does not travel.

ROC-AUC · dataset identity vs. disease
Predict which dataset (logistic regression) 0.95
Predict which dataset (random forest) 0.89
Predict disease within a cohort 0.72
Predict disease across cohorts 0.67

This is a result about dataset shift, not brain biology — the kind of negative result that keeps a field honest.

Which features the model leans on

Top standardized coefficients on the development cohort. Cross-dataset agreement of feature importance is Pearson r = +0.04 — near zero: the model relies on different features in each cohort.

featuremean coefsign consistency
log_power_beta__occipital__iqr-0.6911.00
abs_power_theta__central__iqr-0.6101.00
rel_power_beta__occipital__iqr+0.6011.00
log_power_theta__frontal__iqr+0.5971.00
rel_power_theta__occipital__iqr+0.5881.00
paf__parietal__iqr-0.5311.00
hjorth_complexity__occipital__median+0.5061.00
paf__occipital__iqr-0.5051.00
abs_power_beta__temporal__iqr+0.4461.00
log_power_alpha__frontal__iqr+0.4321.00