Investigates the relationship between chronic cannabis use and temporal lobe epilepsy using EEG-derived machine learning features. Spectral and connectivity biomarkers extracted from HD-EEG recordings are used to characterize network-level differences in affected populations, with classification performance evaluated across seizure onset zones.

Presents Argus, a multi-scale convolutional and bidirectional LSTM network with an attention mechanism for automated seizure detection. Trained and evaluated on the Temple University Seizure Corpus (TUSZ v1.5.2) using a 22-channel TCP bipolar montage at 200 Hz, achieving 98.06% ROC-AUC. The architecture is designed with clinical deployment in mind, prioritizing low false positive rates in continuous long-term monitoring settings.

Abstract placeholder. Replace with your actual publication details, including the key findings, methodology, and clinical significance of the work.

Ongoing work developing a forecasting pipeline to predict seizure onset windows in long-term EEG monitoring patients. Focuses on identifying stable preictal biomarkers from spectral and connectivity features, with the goal of producing clinically actionable warning horizons. No manuscript in preparation at this stage.

Active development of a sleep staging and consciousness monitoring system targeting coma, post-cardiac arrest, and stroke patients in ICU settings. Leverages EEG spectral features and deep learning classifiers to track arousal state transitions in populations where standard behavioral assessments are unreliable. No manuscript in preparation at this stage.