Related Experiment Video
Updated: Aug 23, 2026
Preterm EEG: A Multimodal Neurophysiological Protocol
Published on: February 18, 2012
Microbiome preterm birth DREAM challenge: Crowdsourcing machine learning approaches to advance preterm birth research
Jonathan L Golob1, Tomiko T Oskotsky2, Alice S Tang2
1Division of Infectious Disease, Department of Internal Medicine, University of Michigan, Ann Arbor, MI, USA; March of Dimes Prematurity Research Center at the University of California San Francisco, San Francisco, CA, USA.
Insights
Researchers developed predictive models for preterm birth using vaginal microbiome data. Top models accurately predicted early preterm birth, highlighting microbiome composition as a key factor.
Area of Science:
- Microbiome Research
- Reproductive Health
- Computational Biology
Background:
- Preterm birth affects 11% of infants annually, posing significant health risks.
- The vaginal microbiome is recognized as a contributing risk factor for preterm birth.
Purpose of the Study:
- To crowdsource and validate predictive models for preterm birth (PTB) and early preterm birth (ePTB).
- To identify key vaginal microbiome features associated with PTB and ePTB.
Main Methods:
- Aggregated data from 9 vaginal microbiome studies (3,578 samples).
- Developed and validated predictive models using crowdsourced submissions.
- Utilized phylogenetic harmonization for data standardization.
- Evaluated model performance using area under the receiver operator characteristic (AUROC) curves.
Main Results:
- Top models achieved AUROC scores of 0.69 for PTB and 0.87 for ePTB.
- Alpha diversity, VALENCIA community state types, and microbiome composition were crucial features.
- Tree-based methods predominated among top-performing models.
Conclusions:
- Vaginal microbiome data can be translated into clinically relevant predictive models for preterm birth.
- Microbiome composition offers valuable insights for understanding and potentially preventing preterm birth.
Abstract:
Every year, 11% of infants are born preterm with significant health consequences, with the vaginal microbiome a risk factor for preterm birth. We crowdsource models to predict (1) preterm birth (PTB; <37 weeks) or (2) early preterm birth (ePTB; <32 weeks) from 9 vaginal microbiome studies representing 3,578 samples from 1,268 pregnant individuals, aggregated from public raw data via phylogenetic harmonization. The predictive models are validated on two independent unpublished datasets representing 331 samples from 148 pregnant individuals. The top-performing models (among 148 and 121 submissions from 318 teams) achieve area under the receiver operator characteristic (AUROC) curve scores of 0.69 and 0.87 predicting PTB and ePTB, respectively. Alpha diversity, VALENCIA community state types, and composition are important features in the top-performing models, most of which are tree-based methods. This work is a model for translation of microbiome data into clinically relevant predictive models and to better understand preterm birth.
Related Concept Videos
01:22Introduction to the Human Microbiota
01:30Development of Human Microbiota
01:28Development of the Oral Microbiota
01:21Microbiota Modulation by Antibiotics