From single conventional regression to ensemble modelling: relative importance of the Healthy Eating Index-2015 components in relation to adverse pregnancy outcomes
Julie M Petersen, Lisa M Bodnar, Ashley I Naimi, Sharon I Kirkpatrick · 2026
Read From single conventional regression to ensemble modelling: relative importance of the Healthy Eating Index-2015 components in relation to adverse pregnancy outcomes by Julie M Petersen, Lisa M Bodnar, Ashley I Naimi, Sharon I Kirkpatrick (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-13311460.txt.
Description
Julie Petersen, Lisa Bodnar, Ashley Naimi, and Sharon Kirkpatrick ask whether a standard diet quality score weights its parts sensibly for pregnancy research. Their study appeared in 2026. The Healthy Eating Index gives its thirteen parts roughly equal weight. The team used a United States cohort of 7,882 first-time mothers, with diet around conception scored from food questionnaires and outcomes drawn from medical records. An ensemble learning method combined many algorithms to judge each part's importance without rigid model assumptions.
Six of the thirteen parts carried most of the signal for outcomes like gestational diabetes, pre-eclampsia, early delivery, and small babies. Importance was measured two ways: by global prediction loss and by shifts in each woman's predicted risk. The authors suggest pregnancy studies may want tailored weights rather than the equal-weight default.
Catalog record
| CREATOR | Julie M Petersen, Lisa M Bodnar, Ashley I Naimi, Sharon I Kirkpatrick |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |