Deep‐learning‐based Polygenic Dementia Risk for Alzheimer’s Disease
Linke Li, Metin Nafi Gurcan, Sheng Luo, Da Ma · 2025
Read Deep‐learning‐based Polygenic Dementia Risk for Alzheimer’s Disease by Linke Li, Metin Nafi Gurcan, Sheng Luo, Da Ma (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-11716426.txt.
Description
Gene-based risk scores for Alzheimer's disease can miss curved effects, and a 2025 study by Linke Li and co-authors uses deep learning to catch them. Classic scores add gene effects in a straight line. The team drew genetic data for close to eight hundred patients from a large national initiative.
After quality checks, about seven hundred sixty patients stayed in the study. A genome scan picked the chromosome to study in depth. A neural network then learned which gene variants split patients by diagnosis. Age, sex, and diagnosis data came from linked clinical records. The authors argue that learned scores may flag at-risk adults sooner than straight-line scores, aiding early support.
Catalog record
| CREATOR | Linke Li, Metin Nafi Gurcan, Sheng Luo, Da Ma |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |