A machine learning approach to predict tau positivity using clinical features in amyloid‐positive individuals
Daniel Arnold, Wyllians Vendramini Borelli, Luiza Santos Machado, Nesrine Rahmouni, Joseph Therriault, Stijn Servaes, Jenna Stevenson, Arthur C. Macedo, Artur Francisco Schumacher‐Schuh, Christian Mattjie, Rodrigo C. Barros, Marco Antônio de Bastiani, Firoza Z Lussier, Mira Chamoun, Gleb Bezgin, And · 2025
Read A machine learning approach to predict tau positivity using clinical features in amyloid‐positive individuals by Daniel Arnold, Wyllians Vendramini Borelli, Luiza Santos Machado, Nesrine Rahmouni, Joseph Therriault, Stijn Servaes, Jenna Stevenson, Arthur C. Macedo, Artur Francisco Schumacher‐Schuh, Christian Mattjie, Rodrigo C. Barros, Marco Antônio de Bastiani, Firoza Z Lussier, Mira Chamoun, Gleb Bezgin, And (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11715221.txt.
Description
Daniel Arnold and co-authors train a machine learning model to guess, from ordinary clinical facts, whether a person with brain amyloid also carries tau, the second protein hallmark of Alzheimer's disease. Anti-amyloid drugs seem to help amyloid-and-tau-positive patients most, yet trials admit on amyloid alone, and tau testing needs costly scans or spinal fluid. The team pooled 1,191 amyloid-positive participants from three major datasets.
The model used ten shared clinical features, including age, memory test scores, diagnosis, sex, education, and common health conditions. It separated tau-positive from tau-negative patients with an area under the curve of 0.81, catching seventy-six percent of positives while clearing eighty-six percent of negatives. Age, being cognitively normal, and memory score carried the most weight. The authors pitch the model as a cheap triage step for trial recruitment and treatment planning.
Catalog record
| CREATOR | Daniel Arnold, Wyllians Vendramini Borelli, Luiza Santos Machado, Nesrine Rahmouni, Joseph Therriault, Stijn Servaes, Jenna Stevenson, Arthur C. Macedo, Artur Francisco Schumacher‐Schuh, Christian Mattjie, Rodrigo C. Barros, Marco Antônio de Bastiani, Firoza Z Lussier, Mira Chamoun, Gleb Bezgin, And |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |