A Framework Proposal to Follow-Up on Preclinical Convulsive Signals of a New Molecular Entity in First-in-Human Studies Using Electroencephalographic Monitoring

Abstract

Traditionally, in dose-escalating first-in-human (FiH) studies, a dose cap with a 10-fold safety margin to the no observed effect level in animals is implemented if convulsive events are observed in animals. However, the convulsive risk seen in animals does not generally translate to humans. Several lines of evidence are summarized indicating that in a dose-escalating setting, electroencephalographic epileptiform abnormalities occur at lower doses than clinical convulsive events. Therefore, we propose to consider the occurrence of epileptiform abnormalities in toxicology studies as premonitory signals for convulsions in dose-escalating FiH studies. Compared with the traditional dose-cap approach, this may allow the exploration of higher doses in FiH and, subsequently, phase II studies without compromising human safety. Similarly, the presence or absence of electroencephalographic epileptiform abnormalities may also aid the assessment of proconvulsive risk in situations of increased perpetrator burden as potentially present in pharmacokinetic and/or pharmacodynamic drug-drug interactions.

Figure 1

Scheme of proposed algorithm to guide dose escalation in FiH studies for NMEs with a preclinical convulsive liability: preparatory steps to generate a CRM model. CRM, continual reassessment method; EA, epileptiform abnormality; EEG, electroencephalographic; FiH, first‐in‐Human; NME, new molecular entity; NOEL, no observed effect level.

Figure 2

Minimally informative prior distribution for RO‐NME‐B. The lines represent probabilities for certain EA rates by human dose. This relationship derives from estimates of EA rates by exposure based on observations made in dogs with human doses matching respective exposures in dogs. The bold solid blue line corresponds to the best estimated dose toxicity relationship; bold dashed blue lines describe pointwise lower and upper 5% ranges. The thin black lines represent 30 individual patient profiles to illustrate the range of variability. These were obtained by sampling from the bivariate prior distribution for the parameters α and β as described in the text. Dashed horizontal lines correspond to population EEG‐EA rates of 5% and 20%; dashed vertical red lines indicate the two doses of 100 and 1,750 mg, which were used to construct the prior distribution as described in the text. This minimally informative prior distribution curve estimates p(EA > 20%) at a dose of 1,750 mg in human of 50%, while p(EA > 5%) is 95% at this dose and less than 10% (3.9%) for a dose of 100 mg. Of note, the NOEL in dogs corresponds to a human dose of 1,000 mg for RO‐NME‐B and, hence, the dose of 100 mg corresponds to the dose cap according to the traditional approach of keeping a 10‐fold safety margin. EEG monitoring is suggested to start at 100 mg with the dose escalation rule staying with a p(EA > 5%) of maximum 10%. EA, epileptiform abnormality; EEG, electroencephalographic; NOEL, no observed effect level.

Figure 3

Scheme of proposed algorithm to guide dose escalation in FiH studies for NMEs with a preclinical convulsive liability: use of the CRM in an FiH trial. CRM, continual reassessment method; EA, epileptiform abnormality; EEG, electroencephalographic; FiH, first‐in‐human; NME, new molecular entity; NOEL, no observed effect level.