# Digital cognition plus plasma p‐Tau217 and Aβ42/40 powerfully predict Alzheimer's progression

## TL;DR

Combining digital cognitive tests with plasma biomarkers like p-tau217 and Aβ42/Aβ40 can accurately predict Alzheimer's progression and identify fast progressors.

## Contribution

A novel multimodal approach using plasma biomarkers and digital cognition achieves superior prediction of Alzheimer's progression compared to traditional methods.

## Key findings

- Plasma p-tau217 is the strongest predictor of rapid amyloid and tau accumulation (OR up to 6.6).
- Digital cognitive tests combined with plasma biomarkers match or exceed traditional tests in predictive accuracy (AUC up to 0.92).
- A minimal panel of p-tau217, Aβ42/Aβ40, and digital cognition robustly predicts clinical conversion to MCI/dementia.

## Abstract

Alzheimer's disease is characterized by amyloid‐β (Aβ) and tau accumulation. Identifying individuals with rapid proteinopathy progression is crucial for timely intervention and trial enrichment.

We analyzed longitudinal data from 456 Alzheimer's Disease Neuroimaging Initiative (ADNI) participants, including 375 with digital cognitive test scores. Amyloid and tau accumulation rates were estimated from positron emission tomography (PET) imaging using linear mixed‐effects models. Participants were classified as fast or slow accumulators via Gaussian modeling. Predictors of accumulation and clinical conversion were assessed with logistic and Cox regression models, incorporating demographics, cognitive measures and plasma biomarkers.

Plasma p‐tau217 and Aβ42/Aβ40 predicted rapid accumulation and conversion, with p‐tau217 the strongest marker (odds ratio [OR] up to 6.6). Baseline digital cognitive measures contributed significantly to the prediction, achieving comparable or superior predictive accuracy to traditional cognitive tests (area under the curve [AUC] up to 0.92; C‐index 0.82).

Plasma p‐tau217 and Aβ42/Aβ40 emerged as robust predictors of the progression of disease pathology, supported by cognitive measures.

Plasma p‐tau217 and amyloid‐β (Aβ) 42/Aβ40 ratio powerfully predict rapid amyloid and tau accumulation patterns, enabling identification of fast progressorsDigital cognitive tests achieve comparable or superior predictive accuracy to traditional neuropsychological tests when combined with plasma biomarkersA minimal multimodal panel of plasma p‐tau217, Aβ42/Aβ40 ratio, and digital cognitive assessment robustly predicts clinical conversion from normal cognition to mild cognitive impairment (MCI)/dementia, supporting scalable screening approaches

Plasma p‐tau217 and amyloid‐β (Aβ) 42/Aβ40 ratio powerfully predict rapid amyloid and tau accumulation patterns, enabling identification of fast progressors

Digital cognitive tests achieve comparable or superior predictive accuracy to traditional neuropsychological tests when combined with plasma biomarkers

A minimal multimodal panel of plasma p‐tau217, Aβ42/Aβ40 ratio, and digital cognitive assessment robustly predicts clinical conversion from normal cognition to mild cognitive impairment (MCI)/dementia, supporting scalable screening approaches