Microbiome Preterm Birth DREAM Challenge: Crowdsourcing Machine Learning Approaches to Advance Preterm Birth Research.
Journal
medRxiv : the preprint server for health sciences
Titre abrégé: medRxiv
Pays: United States
ID NLM: 101767986
Informations de publication
Date de publication:
11 Apr 2023
11 Apr 2023
Historique:
pubmed:
23
3
2023
medline:
23
3
2023
entrez:
22
3
2023
Statut:
epublish
Résumé
Globally, every year about 11% of infants are born preterm, defined as a birth prior to 37 weeks of gestation, with significant and lingering health consequences. Multiple studies have related the vaginal microbiome to preterm birth. We present a crowdsourcing approach to predict: (a) preterm or (b) early preterm birth from 9 publicly available vaginal microbiome studies representing 3,578 samples from 1,268 pregnant individuals, aggregated from raw sequences via an open-source tool, MaLiAmPi. We validated the crowdsourced models on novel datasets representing 331 samples from 148 pregnant individuals. From 318 DREAM challenge participants we received 148 and 121 submissions for our two separate prediction sub-challenges with top-ranking submissions achieving bootstrapped AUROC scores of 0.69 and 0.87, respectively. Alpha diversity, VALENCIA community state types, and composition (via phylotype relative abundance) were important features in the top performing models, most of which were tree based methods. This work serves as the foundation for subsequent efforts to translate predictive tests into clinical practice, and to better understand and prevent preterm birth.
Identifiants
pubmed: 36945505
doi: 10.1101/2023.03.07.23286920
pmc: PMC10029035
pii:
doi:
Types de publication
Preprint
Langues
eng
Déclaration de conflit d'intérêts
Competing Interests Antonio Parraga-Leo and Patricia Diaz-Gimeno are receiving hononaria from the IVI Foundation. The remaining authors declare no Competing Financial or Non-Financial Interests.