Long-Term Forecasting of Alzheimer’s Disease Progression Using Time-Aware Models
Alzheimer’s disease (AD) is a progressive neurodegenerative disorder and the most common cause of dementia worldwide. Early and accurate forecasting of cognitive decline in AD patients is essential for personalized treatment planning and effective clinical trial design. However, modeling disease progression is complicated by the irregular timing of clinical visits and heterogeneous data sources. This study presents a Time-aware Long Short-Term Memory (T-LSTM) model that captures temporal dependencies in patient data by integrating time gaps between visits directly into the learning process. Data from multiple large-scale cohorts—including ADNI, NACC, and CPAD—are harmonized and preprocessed to construct a unified longitudinal dataset for training and evaluation. Our approach forecasts Mini-Mental State Examination (MMSE) scores for an unlimited time horizon, demonstrating strong predictive performance and highlighting the effectiveness of temporally sensitive neural network architectures for long-term cognitive trajectory modeling in AD.