A Patient-Specific Framework for Separating Temporal Localization from Intracranial Waveform Reconstruction of Interictal Epileptiform Discharges from Scalp EEG
- 1Massachusetts General Hospital
Abstract
ObjectiveWe developed a patient-specific framework to determine which information about interictal epileptiform discharges (IEDs) can be recovered from scalp EEG, separating temporal localization ("where") from event-specific intracranial waveform reconstruction ("what").
MethodsSix subjects from a public simultaneous high-density scalp EEG and intracranial EEG (iEEG) dataset were analyzed using patient-specific dual-branch convolutional-attention models integrating waveform/topographic and time-frequency representations. For the where task, a 640-ms scalp EEG segment was divided into eight 80-ms bins, and the model predicted the bin containing the intracranial IED peak. For the what task, a 250-ms peak-centered iEEG waveform was represented as a fixed patient-specific template plus an event-specific residual predicted from scalp EEG. Direct scalp-input controls and event-clustered bootstrap confidence intervals were used to distinguish scalp-dependent information from template-driven performance.
ResultsWhere accuracy varied markedly across subjects (0.080-0.984), with an unweighted subject-level mean of 0.333 versus a chance level of 0.125; 95% confidence intervals were above chance level in three of six subjects. Input-control analyses supported a scalp-dependent contribution in subjects with successful localization. For the what task, mean waveform correlation was 0.752 for the model and 0.754 for the fixed patient-specific template (mean difference,-0.002), while residual correlations were generally modest (-0.020 to 0.378).
ConclusionScalp EEG contained recoverable temporal information in some subjects, but event-specific single-contact morphology was not consistently recovered beyond the patient-specific template. Separating temporal localization from template-based waveform reconstruction provides a more stringent framework for evaluating noninvasive-to-intracranial inference and reduces conflation of prior-driven similarity with input-dependent reconstruction.
Related
- TMS timed to interictal epileptiform discharges
- Conditional spatial classification of expert-confirmed interictal epileptiform discharge epochs: An EEG-ECG ablation and SHAP analysis
- Report-derived interictal epileptiform discharge burden is associated with 7-day antiseizure medication decisions after pediatric video electroencephalography
- Contribution of ictal-interictal SPECT and SISCOM to preoperative localization of the epileptogenic zone in frontal lobe epilepsy
- Interictal functional ultrasound imaging in human epilepsy resection and responsive neurostimulation surgery
BibTeX
@misc{matsubara2026patientspecific,
title = {{A Patient-Specific Framework for Separating Temporal Localization from Intracranial Waveform Reconstruction of Interictal Epileptiform Discharges from Scalp EEG}},
author = {T. Matsubara and R. Koda and M. Richardson and S. Stufflebeam},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.25.26364055},
url = {https://www.medrxiv.org/content/10.64898/2026.09.25.26364055v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - A Patient-Specific Framework for Separating Temporal Localization from Intracranial Waveform Reconstruction of Interictal Epileptiform Discharges from Scalp EEG
AU - T. Matsubara
AU - R. Koda
AU - M. Richardson
AU - S. Stufflebeam
PY - 2026
DA - 2026/09/25
PB - medRxiv
DO - 10.64898/2026.09.25.26364055
UR - https://www.medrxiv.org/content/10.64898/2026.09.25.26364055v1
AB - ObjectiveWe developed a patient-specific framework to determine which information about interictal epileptiform discharges (IEDs) can be recovered from scalp EEG, separating temporal localization ("where") from event-specific intracranial waveform reconstruction ("what"). MethodsSix subjects from a public simultaneous high-density scalp EEG and intracranial EEG (iEEG) dataset were analyzed using patient-specific dual-branch convolutional-attention models integrating waveform/topographic and time-frequency representations. For the where task, a 640-ms scalp EEG segment was divided into eight 80-ms bins, and the model predicted the bin containing the intracranial IED peak. For the what task, a 250-ms peak-centered iEEG waveform was represented as a fixed patient-specific template plus an event-specific residual predicted from scalp EEG. Direct scalp-input controls and event-clustered bootstrap confidence intervals were used to distinguish scalp-dependent information from template-driven performance. ResultsWhere accuracy varied markedly across subjects (0.080-0.984), with an unweighted subject-level mean of 0.333 versus a chance level of 0.125; 95% confidence intervals were above chance level in three of six subjects. Input-control analyses supported a scalp-dependent contribution in subjects with successful localization. For the what task, mean waveform correlation was 0.752 for the model and 0.754 for the fixed patient-specific template (mean difference,-0.002), while residual correlations were generally modest (-0.020 to 0.378). ConclusionScalp EEG contained recoverable temporal information in some subjects, but event-specific single-contact morphology was not consistently recovered beyond the patient-specific template. Separating temporal localization from template-based waveform reconstruction provides a more stringent framework for evaluating noninvasive-to-intracranial inference and reduces conflation of prior-driven similarity with input-dependent reconstruction.
ER -