Identifying Factors Associated with Prolonged Postoperative Mechanical Ventilation in Preterm Infants Undergoing Patent Ductus Arteriosus Ligation Using Machine Learning and SHAP Analysis: A Large-Sample Single-Center Retrospective Analysis
Qiang Gao, Yu Cao, Xiwang Liu, Xicheng Zhang, Xucong Shi, Liyang Ying, Liping Shi, Taixiang Liu, Xiangming Fan · 2026
Read Identifying Factors Associated with Prolonged Postoperative Mechanical Ventilation in Preterm Infants Undergoing Patent Ductus Arteriosus Ligation Using Machine Learning and SHAP Analysis: A Large-Sample Single-Center Retrospective Analysis by Qiang Gao, Yu Cao, Xiwang Liu, Xicheng Zhang, Xucong Shi, Liyang Ying, Liping Shi, Taixiang Liu, Xiangming Fan (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/PMC13362179.txt.
Description
Qiang Gao and co-authors used machine learning to predict long breathing support after heart surgery in preterm babies in a 2026 study. The surgery closes a ductus, a blood vessel that should shut after birth but stays open in many early babies. Some babies then need a breathing machine for a long time. The team reviewed 271 infants born at 32 weeks or less, treated from 2021 to 2025.
Babies were split at six days of support: 150 came off sooner and 121 needed longer. Birth weight, age at birth, weight at surgery, duct size, and breathing severity all differed between the groups. A method called SHAP showed which factors pushed each prediction. Flagging high-risk babies early can help teams plan care and counsel parents.
Catalog record
| CREATOR | Qiang Gao, Yu Cao, Xiwang Liu, Xicheng Zhang, Xucong Shi, Liyang Ying, Liping Shi, Taixiang Liu, Xiangming Fan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 22689 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |