Related Experiment Video
Updated: Jun 19, 2026
Brain State-dependent Brain Stimulation with Real-time Electroencephalography-Triggered Transcranial Magnetic Stimulation
Published on: August 20, 2019
Optimizing responsive neurostimulation targeting based on interictal high-frequency oscillations and phase-amplitude
Sotaro Kanai1, Atsuro Daida1, Yipeng Zhang2
1Division of Pediatric Neurology, Department of Pediatrics, UCLA Mattel Children's Hospital, David Geffen School of Medicine, Los Angeles, California, USA.
Objective:
This study was undertaken to determine whether interictal high-frequency oscillations (HFOs) and phase-amplitude coupling (PAC) can serve as spatial biomarkers on intracranial electroencephalography (iEEG) to guide responsive neurostimulation (RNS) targeting.
Methods:
We conducted a retrospective study of patients with drug-resistant epilepsy who underwent iEEG monitoring and subsequent RNS implantation. Eligible participants had ≥60 min of slow-wave sleep iEEG data and ≥6 months of post-RNS follow-up. Patients with simultaneous or subsequent resective surgery or exclusively thalamic RNS electrodes were excluded. Interictal HFOs and delta-HFO PAC (via modulation index [MI]) were calculated using open-source tools (PyHFO, PACTv0.31). Weighted median distances from each iEEG electrode to the nearest RNS electrode were computed, adjusted by the proportion of HFO and MI. The primary outcome was ≥50% seizure reduction (good outcome group [G]) vs. <50% reduction (poor outcome group [P]) at the last follow-up. Predictive performance was evaluated using receiver operating characteristic (ROC) analysis with leave-one-out cross-validation.
Results:
Eighteen patients (median follow-up = 36 months in group G, 33 months in group P; median age = 14.5 years, range = 6-28) met the inclusion criteria, with 10 achieving good outcomes. Weighted median distances from RNS electrodes to peak HFO and MI sites were significantly shorter in group G than in group P (rank-biserial correlation = .30-.45, p < .0001). ROC analysis indicated that distances within 20-30 mm between stimulation sites and peak biomarker locations were optimal (area under the curve > .70 for both HFOs and PAC), outperforming seizure onset zone (SOZ)-based targeting. Exploratory analysis showed favorable outcomes for patients with thalamic electrodes stimulating areas of elevated HFO or MI.
Significance:
RNS electrode placement guided by interictal HFOs and delta-HFO PAC distribution may offer a feasible, effective alternative to conventional SOZ-based approaches. These findings have immediate clinical relevance due to validated open-source analytical tools, facilitating widespread implementation and prospective validation across multiple institutions.
