AutoGluon-based interpretable machine learning for clinical risk stratification of retinopathy of prematurity in very preterm infants
Siyu Chen, Shuyue Deng, Xinyi Liu, Wanting Xu, Wenbin Dong, Linxiao Wan, Lan Kang · 2026
Read AutoGluon-based interpretable machine learning for clinical risk stratification of retinopathy of prematurity in very preterm infants by Siyu Chen, Shuyue Deng, Xinyi Liu, Wanting Xu, Wenbin Dong, Linxiao Wan, Lan Kang (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/pmc-13585999.txt.
Description
Siyu Chen and co-authors build in this 2026 study a machine learning screen for eye disease in very preterm babies. Retinopathy of prematurity can blind, and current screening leans on birth weight and age alone. The team trained an automated ensemble on fifteen routine clinical measures from 236 infants, about half with the disease, checking it in rotating folds.
The ensemble scored an area under the curve of 0.823, with fair sensitivity and specificity for screening. A companion model named the strongest signals: days on breathing machines and oxygen, birth weight, lung disease, and hospital stay. The authors pitch the tool for in-hospital risk sorting, pending wider tests. Eye exams could then go first to the highest-risk infants.
Catalog record
| CREATOR | Siyu Chen, Shuyue Deng, Xinyi Liu, Wanting Xu, Wenbin Dong, Linxiao Wan, Lan Kang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |