Leakage-aware machine learning reveals structured clinical and vaginal microbiome patterns associated with preterm birth in a Mexican cohort
Martín Ruhle, Carolina Espinosa-Maldonado, Guillermo de Anda-Jáuregui, Felipe Vadillo-Ortega, Enrique Hernández-Lemus · 2026
Read Leakage-aware machine learning reveals structured clinical and vaginal microbiome patterns associated with preterm birth in a Mexican cohort by Martín Ruhle, Carolina Espinosa-Maldonado, Guillermo de Anda-Jáuregui, Felipe Vadillo-Ortega, Enrique Hernández-Lemus (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-13190461.txt.
Description
Martin Ruhle and co-authors look for patterns tied to preterm birth in a Mexican cohort, in a 2026 study. Preterm birth is a leading cause of newborn illness and death, and Latino populations are underrepresented in microbiome studies. Forty-three pregnant women in Mexico City gave one hundred and ten samples over time, with fourteen preterm births.
Machine learning was set up to avoid data leakage, with whole women kept apart in validation folds. Twelve model setups joined two algorithms with choices of clinical features and microbe profiles. The best setup showed a strong descriptive score, which the authors stress shows internal structure, not clinic-ready prediction. One microbe genus stood out after strict correction. Body weight measures and two genera ranked as stable signals across folds. The authors present the work as careful pattern description in a small cohort.
Catalog record
| CREATOR | Martín Ruhle, Carolina Espinosa-Maldonado, Guillermo de Anda-Jáuregui, Felipe Vadillo-Ortega, Enrique Hernández-Lemus |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 114 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |