Predicting amyloid risk by machine learning algorithms based on the A4 screen data: Application to the Japanese Trial-Ready Cohort study

September 19, 2021

Authors: Kenichiro Sato, Ryoko Ihara, Kazushi Suzuki, Yoshiki Niimi, Tatsushi Toda, Gustavo Jimenez-Maggiora, Oliver Langford, Michael C Donohue, Rema Raman, Paul S Aisen, Reisa A Sperling, Atsushi Iwata, Takeshi Iwatsubo

Journal: Alzheimer's & Dementia

DOI: 10.1002/trc2.12135

Year Published: 2021


Selecting cognitively normal elderly individuals with higher risk of brain amyloid deposition is critical to the success of prevention trials for Alzheimer’s disease (AD).


Based on the Anti-Amyloid Treatment in Asymptomatic Alzheimer’s Disease study data, we built machine-learning models and applied them to our ongoing Japanese Trial-Ready Cohort (J-TRC) webstudy participants registered within the first 9 months (n = 3081) of launch to predict standard uptake value ratio (SUVr) of amyloid positron emission tomography.


Age, family history, online Cognitive Function Instrument and CogState scores were important predictors. In a subgroup of J-TRC webstudy participants with known amyloid status (n = 37), the predicted SUVr corresponded well with the self-reported amyloid test results (area under the curve = 0.806 [0.619-0.992]).


Our algorithms may be usable for automatic prioritization of candidate participants with higher amyloid risks to be preferentially recruited from the J-TRC webstudy to in-person study, maximizing efficiency for the identification of preclinical AD participants.

Back to Publications