Key result
KNN and XGBoost framework achieves ~90% sensitivity and perfect specificity for EEG artifact classification.
Why the study?
Artifacts degrade EEG recording quality and increase false positive rates in anomaly detection, while most existing methods detect or remove only a single artifact type rather than classifying multiple types alongside normal and pathological activity.
Does a unified multi-class machine learning framework accurately classify multiple EEG artifact types alongside normal and pathological brain activity?
Does a unified multi-class machine learning framework accurately classify multiple EEG artifact types alongside normal and pathological brain activity?
A unified machine learning approach using KNN and XGBoost effectively classifies multiple EEG artifact types with high sensitivity and specificity.
Artifacts are noisy signals that commonly contaminate electroencephalographic (EEG) recordings, mixing with underlying brain activity and degrading the quality of neurophysiological data. Previous research on epileptic Anomaly Detection has shown that this approach is also sensitive to unlabelled artifacts, often leading to an increased False Positive rate. While most methods focus on detecting or removing a single type of artifact, this work proposes a unified multi-class framework to classify several artifact types alongside normal and pathological brain activity within a recording using a single, simple Machine Learning classifier. A set of spectral, temporal and statistical features commonly associated with different artifact types is extracted. KNN and XGBoost classifiers are trained and evaluated under a cross-validation scheme. The results demonstrate strong performance for both models, achieving approximately 90% sensitivity across all classes while maintaining a 100% specificity. These findings highlight the effectiveness of a unified and interpretable approach for multi-class EEG artifact classification.
No takes yet. Share an insight, caveat, or question.
Martins et al. (2026) studied EEG artifacts. KNN and XGBoost classifiers was evaluated on Multi-class EEG artifact classification. A unified multi-class framework using KNN and XGBoost classifiers achieved approximately 90% sensitivity across all classes and 100% specificity for EEG artifact classification.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: