Ensemble survival analysis for preclinical cognitive decline prediction in Alzheimer's disease using longitudinal biomarkers

BackgroundPredicting the risk of clinical progression from cognitively normal (CN) status to mild cognitive impairment (MCI) or Alzheimer's disease (AD) is critical for early intervention in AD. Traditional survival models often fail to capture complex longitudinal biomarker patterns associated with disease progression.ObjectiveWe propose an ensemble survival analysis framework integrating multiple survival models to improve early prediction of clinical progression in initially cognitively normal individuals.MethodsWe analyzed longitudinal biomarker data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort, including 721 participants, limiting analysis to up to three visits (baseline, 6-month follow-up, 12-month follow-up). Of these, 142 (19.7%) experienced clinical progression to MCI or AD. Our approach combined penalized Cox regression (LASSO, Elastic Net) with advanced survival models (Random Survival Forest, DeepSurv, XGBoost). Model predictions were aggregated using ensemble averaging and Bayesian Model Averaging (BMA). Predictive performance was assessed using Harrell's concordance index (C-index) and time-dependent area under the curve (AUC).ResultsThe ensemble model achieved a peak C-index of 0.907 and an integrated time dependent AUC of 0.904, outperforming baseline-only models (C-index 0.608). One follow-up visit after baseline significantly improved prediction accuracy (48.1% C-index, 48.2% AUC gains), while adding a second follow-up provided only marginal gains (2.1% C-index, 2.7% AUC).ConclusionsOur ensemble survival framework effectively integrates diverse survival models and aggregation techniques to enhance early prediction of preclinical AD progression. These findings highlight the importance of leveraging longitudinal biomarker data, particularly one follow-up visit, for accurate risk stratification and personalized intervention strategies.