Abstract
C-Triadem, our novel developed deep neural network, accurately predicts moderate cognitive impairment (MCI) and Alzheimer's disease (AD) while identifying potential blood biomarkers for AD. Current diagnostic methods have limitations, emphasizing the critical need for early AD detection. Our model integrates genetic, gene expression, and clinical data to differentiate among cognitively normal individuals, MCI, and AD cases. Training and validation using Alzheimer's Disease Neuroimaging Initiative (ADNI) data demonstrate superior performance, with a 97% AUC and 89% accuracy, surpassing previous models. SHapley Additive exPlanations (SHAP) analysis highlights key clinical features (e.g., MMSE scores, brain volume) and genes (e.g., CASP9, LCK, SDC3), revealing potential genetic markers and pathways in blood associated with AD. By incorporating Reactome pathways, our approach enhances interpretability, providing insight into the biological context of predictions. In summary, c-Triadem represents a significant advancement in AD diagnostics, enabling earlier and more accurate diagnoses for improved treatment strategies.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call