The concentration EEG effect relationship of heptabarbital was modeled using effect parameters derived from aperiodic EEG analysis. Male Wistar rats (n = 10) received an intravenous infusion of heptabarbital at a rate of 6-9 mg/kg per min until burst suppression with isoelectric periods of 5 sec or longer. Arterial blood samples were obtained and EEG was measured continuously until recovery of baseline EEG and subjected to aperiodic analysis for quantification. Two EEG parameters, the amplitudes per second (AMP) and the total number of waves per second (TNW), in five discrete frequency ranges and for two EEG leads were used as descriptors of the drug effect on the brain. The EEG parameters responded both qualitatively and quantitatively different to increasing concentrations of heptabarbital. Monophasic concentration effect curves (decrease) were found for the frequency ranges greater than 2.5 Hz and successfully quantified with a sigmoidal Emax model after collapsing the hysteresis by a nonparametric modeling approach. For the parameter TNW in the 2.5-30 Hz frequency range the value of the pharmacodynamic parameters EC50, Emax, and n (means +/- SD) were 78 +/- 7 mg/L, 11.4 +/- 1.7 waves/sec and 5.0 +/- 1.5, respectively. For other discrete frequency ranges, differences in EC50 were observed, indicating differences in sensitivity to the effect of heptabarbital. In the 0.5 +/- 2.5 Hz frequency range biphasic concentration effect relationships (increase followed by decrease) were observed. To fully account for the hysteresis in these concentration effect relationships, postulation of two effect compartments was necessary. To characterize these biphasic effect curves two different pharmacodynamic models were evaluated. Model 1 characterized the biphasic concentration effect relationship as the summation of two sigmoidal Emax models, whereas Model 2 assumed the biphasic effect to be the result of only one inhibitory mechanism of action. With Model 1 however realistic parameter estimation was difficult because the maximal increase could not be measured, resulting in high correlations between parameter estimates. This seriously limits the value of Model 1. Model 2 involves besides estimation of the classical pharmacodynamic parameters Emax, EC50, and n also estimation of the maximal disinhibition Amax. This model is a new approach to characterize biphasic drug effects and allows, in principle, reliable estimation of all relevant pharmacodynamic parameters.