In patients with drug-resistant epilepsy, electrical stimulation of the brain in response to epileptiform activity can make seizures less frequent and debilitating. When effective, this therapy, known as closed-loop responsive neurostimulation (RNS), produces long-lasting changes in brain dynamics that correlate with clinical outcomes. Since periods with frequent epileptiform activity are less conducive to neuroplasticity, we hypothesize that stimulation timing, specifically stimulation during brain states with less epileptiform activity, is critical in driving long-term changes that restore healthy brain networks. To test this, we quantified stimulation episodes during low- and high-risk epochs--that is, stimulation during periods with a low or high risk of generating seizures and less or more epileptiform activity--in a cohort of 40 patients treated with RNS. Patients were categorized into three groups: super responders (>90% reduction, n=10), intermediate responders (>= 50% reduction and <= 90% reduction), n=19, and poor responders (<50% reduction, n=11). As hypothesized, in this retrospective study, seizure reduction (median 64.6% reduction at last follow-up) was correlated with more frequent stimulation during low-risk periods compared with high-risk periods. Additionally, stimulation events were more likely to be phase-locked to prolonged episodes of abnormal activity for intermediate and poor responders when compared to super responders, consistent with the hypothesis that improved outcomes are driven by stimulation during low-risk states. These results suggest that stimulation during low-risk periods may more readily induce plasticity that, in turn, facilitates network changes leading to long-term seizure reduction.