Feature-Based Machine-Learning Spike Marking in Signal and Source Space EEG: A Proof-of-Principle Case Study of Focal Epilepsy

Source abstract

Accurate detection of interictal epileptiform discharges (IEDs) in electroencephalography (EEG) plays a crucial role in epilepsy diagnosis. Our work investigates the classification of IEDs using Artificial Neural Networks (ANNs) trained on EEG data represented in both signal and source space, in a proof-of-principle case study of focal epilepsy. Source waveforms were computed using a standard clinical source analysis procedure for the dipolar IED topographies, an equivalent current dipole model in a three-compartment head volume conductor model fitted using either a 1-parameter fixed-orientation or a 3-parameter projection approach, both localized to a single best-fit position during the rising flank of the IED. The ANN was trained on raw and feature-extracted versions of signal space and source space data. Feature extraction significantly improved performance across all domains. The highest accuracy (0.98) was achieved in signal space using Katz Fractional Dimension (KFD). In source space analyses, the 1-parameter and 3-parameter models achieved a maximum accuracy of 0.84, with statistical features performing best for the fixed-orientation model and KFD for the free orientation model. Additionally, annotations from three independent expert markers showed considerable variability, with ANN performance falling within the range of inter-expert agreement. While the findings of our proof-of-principle case study support the potential of feature-informed ANN tools to assist expert evaluation in clinical workflows, data from a single patient cannot capture inter-individual variability. Future work on a large, multi-patient cohort is needed to develop a population-generalizable detector.