Machine learning to improve the prediction of Large for Gestational Age (LGA) neonates: a cohort study
Gabriel Cubillos, Max Monckeberg, Alejandra Plaza, Maria Morgan, Pablo A Estevez, Mahesh Choolani, Matthew W Kemp, Sarah W L Li, Sebastian E Illanes, Claudio A Perez · 2026
Read Machine learning to improve the prediction of Large for Gestational Age (LGA) neonates: a cohort study by Gabriel Cubillos, Max Monckeberg, Alejandra Plaza, Maria Morgan, Pablo A Estevez, Mahesh Choolani, Matthew W Kemp, Sarah W L Li, Sebastian E Illanes, Claudio A Perez (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/PMC13520273.txt.
Description
Gabriel Cubillos and nine colleagues train machine learning models in 2026 to predict which babies will be born large for their gestational age. Such size is a risk factor for delivery injury to mother and child. Twelve algorithms were tuned and tested using routine prenatal variables, with data augmentation and feature selection to sharpen performance.
The leading model balanced sensitivity and specificity at 0.84 each using 14 variables, while a leaner 10-variable model reached 97 percent specificity, beating the classic ultrasound formula's balance of errors. Maternal body mass index, maternal weight at first and last checkups, and estimated fetal weight drove predictions most. Cubillos's team argues standard clinic data, gathered early, can flag risky pregnancies in time to act.
Catalog record
| CREATOR | Gabriel Cubillos, Max Monckeberg, Alejandra Plaza, Maria Morgan, Pablo A Estevez, Mahesh Choolani, Matthew W Kemp, Sarah W L Li, Sebastian E Illanes, Claudio A Perez |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 54969 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |