Prediction of 2-Year Cognitive Outcomes in Very Preterm Infants Using Machine Learning Methods
Andrea K. Bowe, Gordon Lightbody, Anthony Staines, Deirdre M. Murray, Mikael Norman · 2023
Read Prediction of 2-Year Cognitive Outcomes in Very Preterm Infants Using Machine Learning Methods by Andrea K. Bowe, Gordon Lightbody, Anthony Staines, Deirdre M. Murray, Mikael Norman (2023) 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-10751596.txt.
Description
Babies born very early face a real risk of slow thinking at age two, and help works best when it starts early, so spotting the risk at discharge matters. Andrea Bowe and co-authors build a prediction model in a 2023 Swedish study, trained on a national register of newborn care. Ninety routine facts about pregnancy, birth, and the hospital stay fed the models.
A model using about a quarter of those facts caught most of the children who later showed delay, though it also flagged many who developed well. The strongest signals were the home language, a long hospital stay, low birth weight, discharge somewhere other than home, and no breast milk at discharge. The authors frame the tool as a way to aim scarce early help where the odds of need run highest.
Catalog record
| CREATOR | Andrea K. Bowe, Gordon Lightbody, Anthony Staines, Deirdre M. Murray, Mikael Norman |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 29 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |