Predicting Individual’s Cognitive Performance Through Multi‐Omics Blood Data Using Hierarchical Input Neural Network ‐ HINN
Yashu Vashishath, Sarah Beaver, Serdar Bozdag, Fahad Saeed · 2025
Read Predicting Individual’s Cognitive Performance Through Multi‐Omics Blood Data Using Hierarchical Input Neural Network ‐ HINN by Yashu Vashishath, Sarah Beaver, Serdar Bozdag, Fahad Saeed (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-11712636.txt.
Description
Yashu Vashishath and co-authors published a research paper in 2025 on a learning model that predicts thinking test scores from blood data. The model reads three layers of biology at once: gene variants, gene activity, and chemical marks on DNA. Most models use one layer, but the layers shape each other, so the team fed them in as a stacked set.
Hundreds of gene variants tied to test scores anchored the search for nearby marks and genes. The stacked model forecast scores on four standard tests with modest error. It beat simpler models the team tried as yardsticks. A blood-based forecast could one day flag people who need a full memory work-up.
Catalog record
| CREATOR | Yashu Vashishath, Sarah Beaver, Serdar Bozdag, Fahad Saeed |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |