Annals of clinical and translational neurology
A Two-Stage Plasma Biomarker Algorithm Reduces Amyloid PET Use and the p-Tau217 Gray Zone
By Parankusham H, Vanderlip C, Birkenbihl C and 5 others.
Abstract
Objective
Plasma p-Tau217 leaves 30%-50% of patients in an indeterminate "gray zone" often requiring Aβ-PET. We developed GRAD (Gatekeeper-Reflex for Alzheimer's Disease), a two-stage Aβ-positivity prediction model to improve classification while reserving Aβ-PET for residual uncertainty.
Methods
GRAD was developed in 145 cognitively impaired ADNI participants and externally validated in 1644 cognitively unimpaired A4/LEARN participants. Stage 1 used p-Tau217 alone; probabilities between 0.25 and 0.75 were considered indeterminate. Stage 2 used L2-regularized logistic regression combining plasma-biomarkers, genetic and demographic features. Aβ-PET served as the reference standard (ADNI florbetapir SUVR > 1.11; A4 Centiloid ≥ 20).