AI Science Tracker
EN

Predicting preterm birth using machine learning techniques in oral microbiome.

Department of Obstetrics and Gynecology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea; Department of Biomedical Engineering, Ulsan National Institute of Science and Technology, Republic of Korea; Department of Obstetrics and Gynecology, Jeonbuk National University Medical School, Republic of Korea; Research Institute of Clinical Medicine, Jeonbuk National University Hospital, Republic of Korea; Helixco Inc., Republic of Korea; Department of Pharmacology, Jeonbuk National University Medical School, Republic of Korea · 30 Nov 2023 · medicine

Discovery

Predicting preterm birth using machine learning techniques in oral microbiome.

Source check: Source checked. Not independent scientific confirmation.

Finding: In 59 singleton pregnancies, random-forest analysis of oral microbiome data reported 25 differentially abundant taxa and a nine-taxon classifier with balanced accuracy 0.765 ± 0.071 under five-fold cross-validation. A separate nine-pregnancy twin sample had reported accuracy of 87.5%; both samples are small and do not establish clinical utility.

Technology: A random-forest classifier used oral microbiome composition to predict preterm birth and rank informative taxa; differential-abundance analysis separately identified candidate taxa.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Machine-learning analysis identified oral microbiome taxa associated with preterm birth and reported predictive performance in small pregnancy cohorts.
Test and result
The singleton cohort yielded 25 differentially abundant taxa; a nine-taxon classifier reported balanced accuracy 0.765 ± 0.071, while the separate twin sample had reported accuracy 87.5%.
Limitation / still unknown
Stratified five-fold cross-validation in 59 singleton pregnancies and a separate nine-twin sample. The cohorts are small and from the study setting; prospective utility and multicenter validation are not established.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://www.nature.com/articles/s41598-023-48466-x

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: linked separately.

Review date: 22 Nov 2026. Review scope: Primary Scientific Reports full text, including cohort, model evaluation and Results; publication date checked against the publisher record..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.