Background: A paradox in epilepsy and psychiatry is that temporal lobe epilepsy is often predisposed to schizophrenic-like psychosis, whereas convulsive therapy can relieve schizophrenic symptoms. We have previously demonstrated that the nucleus accumbens is a key structure in mediating postictal psychosis induced by a hippocampal electrographic seizure. Objective/hypothesis: The purpose of this study is to test a hypothesis that accumbens kindling cumulating in a single (1-time) or repeated (5-times) convulsive seizures have different effects on animal models of psychosis. Methods: Electrical stimulation at 60 Hz was applied to nucleus accumbens to evoke afterdischarges until one, or five, convulsive seizures that involved the hind limbs (stage 5 seizures) were attained. Behavioral tests, performed at 3 days after the last seizure, included gating of hippocampal auditory evoked potentials (AEP) and prepulse inhibition to an acoustic startle response (PPI), tested without drug injection or after ketamine (3 mg/kg s.c.) injection, as well as locomotion induced by ketamine or methamphetamine (1 mg/kg i.p.). Results: Compared to non-kindled control rats, 1-time, but not 5-times, convulsive seizures induced PPI deficit and decreased gating of hippocampal AEP, without drug injection. Compared to non-kindled rats, 5-times, but not 1-time, convulsive seizures antagonized ketamine-induced hyperlocomotion, ketamine-induced PPI deficit and AEP gating decrease. However, both 1- and 5-times convulsive seizures significantly enhanced methamphetamine-induced locomotion as compared to non-kindled rats. Conclusions: Accumbens kindling ending with 1 convulsive seizure may induce schizophrenic-like behaviors, while repeated (>= 5) convulsive seizures induced by accumbens kindling may have therapeutic effects on dopamine independent psychosis. (C) 2016 Elsevier Inc. All rights reserved.