Applying a statistical model-based AI method to identify prognostic factors for long-term cognitive decline in Alzheimer's disease: Evidence from pooled placebo data of four phase III trials.

Heterogeneity in the long-term progression of Alzheimer's disease (AD) challenges the efficiency of clinical trials. Identifying long-term prognostic factors is critical for enhancing trial efficiency, although it has been limited by the lack of appropriate statistical approaches. We applied a recently developed statistical model-based AI method to identify the baseline prognostic factors for long-term cognitive decline in a clinical trial population. We analyzed pooled placebo arm data (N = 1,597) from four Phase III trials in patients with mild-to-moderate AD. Long-term trajectories for the Mini-Mental State Examination (MMSE), 11- and 14-item versions of the Alzheimer's Disease Assessment Scale-Cognitive subscale (ADAS-Cog11, ADAS-Cog14), and Clinical Dementia Rating-Sum of Boxes (CDR-SB) were predicted from their short-term data (≤80 weeks). Trajectories were compared between subgroups defined by six baseline factors (age, sex, apolipoprotein E ε4 [APOE ε4] status, years of education, years from diagnosis, and years from disease onset) using the area under the curve (AUC). Longer years of education (≥13 years) was the most robust predictor associated with faster progression across all four outcomes (e.g., for 20-year ADAS-Cog11, AUC ratio, 1.11, p < 0.001). Younger age (<74 years) was associated with a faster decline in MMSE and ADAS-Cog scores, but not in CDR-SB. APOE ε4 status, sex, years from diagnosis, and years from disease onset were not significantly associated with long-term progression. Baseline educational level and age were significant prognostic factors of long-term cognitive decline. These findings will help optimize patient stratification in future clinical trials on AD.