Aim: This study aimed to compare three commonly used analysis methods for clinical trials in epilepsy in terms of statistical efficiency, nonefficacious exposure, and cost.
Method: A realistic seizure diary simulator was employed to produce 102 000 trials, which were analyzed by the 50%-responder rate method (RR50), median percentage change (MPC), and time to prerandomization (TTP). Half the trials compared a placebo to a drug that was 20% better, and the other half compared two placebos. The former were used to calculate statistical power; the latter were used for type 1 error rates. Based on the number of patients needed to achieve 90% power, expected number of patient-days of nonefficacious exposures and expected cost were calculated for each method.
Results: MPC demonstrated the highest efficacy, lowest exposure, and lowest cost. RR50 demonstrated the lowest efficacy, highest exposure, and highest cost. Costs were: MPC $1 295 000, TTP $1 315 720, and RR50 $2 331 000. Selecting an optimal analysis method for a primary outcome in an epilepsy trial can have consequences in terms of nonefficacious exposure and cost.
Summary: This study provides evidence supporting the use of median percentage change (preferred) or time to prerandomization, and evidence suggesting that the 50%-responder rate method would incur high costs and excess exposures.