Services
Company
Legal and Governance
Publication Library / Publications
Post-hoc assessment of cognitive efficacy in Alzheimer’s disease using a latent growth mixture model in AMBAR, a phase 2B randomized controlled trial
Background
Disease progression in Alzheimer’s Dementia (AD) is typically characterized by accelerated cognitive and functional decline, where heterogeneous trajectories can impact the observed treatment response.
Methods
We hypothesized that unobserved heterogeneity could obscure treatment benefits in AD. The effect of unobserved heterogeneity was empirically quantified within the Alzheimer’s Management By Albumin Replacement (AMBAR) phase 2b trial data. The ADAS-Cog 12 cognition endpoint was reanalyzed in a 2-class latent growth mixture model initially fit to the treatment arm. The model with the best fit was then applied across both treatment arms to a larger (n=1000) simulated dataset that was representative of AMBAR trial cognitive data.
Results
Two classes of patients were observed: a stable cognitive trajectory class and a highly variable class. Removal of the latter (n=48, 22%) from the analysis and refitting efficacy models comparing the stable class to full placebo yielded significant treatment efficacy on cognition (p=0.007, Cohen’s D=-0.4). Comparison of the stable class of each arm within the simulated dataset revealed a significant difference in treatment efficacy favoring the simulated stable treatment arm.
Conclusion
This post hoc exploratory analysis suggests that prespecified strategies for addressing unobserved heterogeneity may yield improved effect detection in AD trials. The generalizability of the analytic strategy is limited by latent stratification in only the treatment arm, a requirement given the small placebo arm in AMBAR. This limitation was partially addressed by the simulation modeling.
Authors
N D Ayasse, W F Stewart, R B Lipton, D Gomez-Ulloa, M C Runken
Journal
Current Alzheimer Research
Therapeutic Area
Neurology
Center of Excellence
Real-world Evidence & Data Analytics
Year
2025
Read full article