A Pilot Study of High-Definition Transcranial Direct Current Stimulation in Refractory Status Epilepticus: The SURESTEP Trial

Abstract

Refractory status epilepticus (RSE) is a life-threatening emergency with high mortality and poor functional outcomes in survivors. Treatment is typically limited to intravenous anesthetic infusions and multiple anti-seizure medications. While ongoing seizures can cause permanent neurological damage, medical therapies also pose severe and life-threatening side effects. We tested the feasibility of using high-definition transcranial direct current stimulation (hd-tDCS) in the treatment of RSE. We conducted 20-min hd-tDCS sessions at an outward field orientation, intensity of 2-mA, 4 + 1 channels, and customized for deployment over the electrographic maximum of epileptiform activity ("spikes") determined by real-time clinical EEG monitoring. There were no adverse events from 32 hd-tDCS sessions in 10 RSE patients. Over steady dosing states of infusions and medications in 29 included sessions, median spike rates/patient fell by 50% during hd-tDCS on both automated (p = 0.0069) and human (p = 0.0277) spike counting. Median spike rates for any given stimulation session also fell by 50% during hd-tDCS on automated spike counting (p = 0.0032). Immediately after hd-tDCS, median spike rates/patient remained down by 25% on human spike counting (p = 0.018). Compared to historical controls, hd-tDCS subjects were successfully discharged from the intensive care unit (ICU) 45.8% more often (p = 0.004). When controls were selected using propensity score matching, the discharge rate advantage improved to 55% (p = 0.002). Customized EEG electrode targeting of hd-tDCS is a safe and non-invasive method of hyperacutely reducing epileptiform activity in RSE. Compared to historical controls, there was evidence of a cumulative chronic clinical response with more hd-tDCS subjects discharged from ICU.

Fig. 1

Patient flowchart. 10 included RSE patients comprised the “per-patient” analysis dataset. 29 included hd-tDCS sessions comprised the “per-session” analysis dataset

Fig. 2

Change in median automated spike rate per-patient during hd-tDCS. Spike rates: relative (purple, y-axis on left), absolute (orange, y-axis on right). Relative reduction of −100% denotes spike quiescence. Filled triangle indicates relative spike increase beyond 100%. Relative differences were exaggerated when a few rare spikes emerged from a baseline of quiescence. Note quiescence in patient #10. All but two patients experienced relative reductions. All but one patient experienced absolute reductions. Patient #4 experienced a relative median increase (+23.1%) corresponding to an absolute median increase of +0.001 spikes/sec. Patient #6 experienced a relative median increase (+1060.2%) corresponding to an absolute median decrease (−0.03 spikes/sec), which was driven by session 2/2 (relative +2204.7% increase but only +0.016 absolute increase in spikes/second). Although session 1/2 showed relative spiking reduction of −84.3%, this was overwhelmed by the relative rate in session 2/2

Fig. 3

Two types of hd-tDCS artifact: “ramping” and “stimulating ” Referential montage EEG: low frequency filter 1 Hz, high-frequency filter 70 Hz, notch filter 60 Hz, sensitivity 7 μV/mm, timebase 30 mm/sec. Left and right panels. Examples of typical “ramping” artifact occurring 30 seconds immediately before hd-tDCS begins, and 30 seconds immediately after hd-tDCS ends, on every EEG. No spikes were counted during these technical ramping periods. Middle panel. Example of typical minor focal “stimulating” artifact after ramping-on artifact (left panel) abruptly ends and when actual hd-tDCS stimulation begins. After 20 min of active hd-tDCS stimulation ends, ramping-off artifact (right panel) abruptly begins. In this example, active hd-tDCS stimulation was targeted around the Pz electrode

Fig. 4

Change in median human spike rate per-patient during hd-tDCS. Spike rates: relative (purple, y-axis on left), absolute (orange, y-axis on right). Relative reduction of −100% denotes spike quiescence (patient #6). All but one patient experienced relative reductions. All patients experienced absolute reductions. Patient #5 experienced a relative median increase (+51.4%) at the same time as an absolute median decrease (−0.01 spikes/sec)

Fig. 5

Change in median automated spike rate per-session during hd-tDCS. Spike rates: relative (purple, y-axis on left), absolute (orange, y-axis on right). Relative reduction of −100% denotes spike quiescence. A filled triangle symbol indicates relative spike increase beyond 100%. Relative differences were exaggerated when a few rare spikes emerged from a baseline of quiescence. Note quiescence in session #3 of patient #1 and session #2 of patient #10. In session #2 of patient #6, relative spike rate increase was +2204.7% and absolute spike increase was +0.01 spikes/sec from a very low baseline of just 0.0007 to 0.0167 spikes/sec. In session #5 of patient #7, relative spike rate increase was +249.3% and absolute spike increase was + 0.25 spikes/sec

Fig. 6

Example of longitudinal spike rate improvement over days with hd-tDCS in patient #10. Referential montage EEG: low-frequency filter 1 Hz, high-frequency filter 70 Hz, notch filter 60 Hz, sensitivity 7 μV/mm, timebase 30 mm/sec. (A) Baseline status epilepticus in the absence of intravenous anesthetic therapy (IVAT) after having failed a previous trial of weaning IVAT. (B) Steady-state pre-stimulation EEG (session #1 on day #6 of admission to the intensive care unit) with the presence of concomitant intravenous midazolam infusion. Boxes indicate residual spikes from status epilepticus breaking through effects of midazolam infusion. (C, D) Respective examples of steady-state during-stimulation and after-stimulation EEG (session #2 on day #7 of admission to the intensive care unit) with absence of spikes (“quiescence”) and absence of IVAT (i.e., midazolam), which had been successfully weaned between sessions #1 and #2. During-stimulation and after-stimulation EEG from session #1 are available in Supplementary Fig. 1J

Fig. 7

Change in median human spike rate per-patient after hd-tDCS. Spike rates: relative (purple, y-axis on left), absolute (orange, y-axis on right). All patients experienced absolute spike reduction. All but one patient experienced relative spike reduction. Patient #7 experienced a relative median increase (+3.6%) at the same time as an absolute median decrease (−0.08 spikes/sec)