A recent study aimed to build a personalized prediction model for patients with Alzheimer's disease (AD) and to estimate patient-specific treatment effects of donepezil, utilizing individual patient characteristics. The research involved a systematic search for all double-masked randomized controlled trials comparing oral donepezil and pill placebo in the treatment of AD, with individual participant data requested through its developer, Eisai. The primary outcome focused on cognitive function at 24 weeks, measured using the Alzheimer's Disease Assessment Scale-cognitive component (ADAS-cog).
The study included eight studies with a total of 3,156 participants. A Bayesian meta-analytical prediction model was developed for patients receiving placebo, and an individual patient data meta-analysis was conducted to estimate patient-level treatment effects. Findings from the Bayesian prediction model indicated that more severe cognitive and global function at baseline, along with younger age, were associated with worse cognitive function at 24 weeks. The individual participant data meta-analysis revealed that, on average, donepezil was superior to placebo in improving cognitive function, with ADAS-cog scores showing a significant improvement (-3.2; 95% Credible Interval (CrI) -4.2 to -2.1). Additionally, the study suggested that antipsychotic drug use at baseline might be associated with a reduced effect of donepezil on ADAS-cog scores (2.0; 95% CrI, -0.02 to 4.3).
This research underscores the potential of personalized medicine in the treatment of Alzheimer's disease, emphasizing the role of individual patient characteristics in predicting disease progression and treatment outcomes.
