This research aims to reconstruct and forecast Alzheimer's disease trajectories using routine data in resource-constrained settings. It proposes a unified framework for bidirectional prediction of cognitive scores from irregular visits, enabling interpolation and extrapolation, and providing calibrated uncertainty estimates.
An XGBoost classifier was developed using clinical features from the ADNI dataset for multi-class detection of normal cognition, mild cognitive impairment, and Alzheimer's disease. The model achieved a high mean macro AUC of 0.983 and an accuracy of 0.944, with SHAP values providing feature explainability.
This research investigates the trustworthiness and fairness of nonparametric deep survival models for analyzing Alzheimer's Disease (AD) progression. It addresses the lack of studies considering learned bias in existing deep learning models for AD and proposes novel fairness metrics to ensure reliable predictions.
This paper introduces a residual gap-aware transformer for forecasting 24-month Alzheimer's disease progression using ADNI clinical and biomarker histories. The research analyzes changes in CDR-SB scores, anchoring samples at mild cognitive impairment visits.