Applying ensemble machine learning techniques to MRI scans to predict Alzheimer’s disease
Georgios Theocharidis, Sotirios Bisdas, John Pazarzis, Stavros Zervoudakis, Dongnanzi Zheng, Georgios Angelidis, Antonios Saravanos · 2026
Read Applying ensemble machine learning techniques to MRI scans to predict Alzheimer’s disease by Georgios Theocharidis, Sotirios Bisdas, John Pazarzis, Stavros Zervoudakis, Dongnanzi Zheng, Georgios Angelidis, Antonios Saravanos (2026) 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/PMC13578294.txt.
Description
Georgios Theocharidis and co-authors build a 2026 system that reads brain scans to flag who may later develop Alzheimer's disease. Catching the disease before symptoms start could open a window for early care. Their system works only with standard structural scans, the kind many hospitals already take, and studies five slices from each brain.
A network first trained on photos pulled features from each slice. Three classic learning models then voted together on the risk call. The data held just over a thousand people whose thinking was normal at scan time, split so no person leaked across test groups. Across two hundred repeat runs the blend scored well on sorting future cases from stable ones, which the authors offer as a low cost screening aid.
Catalog record
| CREATOR | Georgios Theocharidis, Sotirios Bisdas, John Pazarzis, Stavros Zervoudakis, Dongnanzi Zheng, Georgios Angelidis, Antonios Saravanos |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63870 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |