Chest-X-ray based deep feature-driven framework for anemia detection insights from a large hospital cohort
Hao-Chun Liao, Dung-Jang Tsai, Shan-Yueh Chang, Chin Lin, Shih-Hua Lin, Wen-Hui Fang · 2026
Read Chest-X-ray based deep feature-driven framework for anemia detection insights from a large hospital cohort by Hao-Chun Liao, Dung-Jang Tsai, Shan-Yueh Chang, Chin Lin, Shih-Hua Lin, Wen-Hui Fang (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/PMC13555854.txt.
Description
Hao-Chun Liao leads a six-author team detecting hidden anemia from routine chest X-rays in a 2026 Taiwan study. Anemia is usually found by blood tests, yet chest images are taken far more often. Their dataset held more than three hundred thousand adults from one hospital system. A pretrained vision model pulled features from each image, and a simple classifier judged anemia from those features alone.
The approach scored strongly on both internal and outside test sets. It caught about seven in ten cases while clearing more than eight in ten healthy people. Accuracy ran best on certain image types and in middle-aged men, and weakest in younger women. Adding clinical details improved results further. The authors propose opportunistic screening during routine care.
Catalog record
| CREATOR | Hao-Chun Liao, Dung-Jang Tsai, Shan-Yueh Chang, Chin Lin, Shih-Hua Lin, Wen-Hui Fang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47973 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |