Harnessing vaginal inflammation and microbiome: a machine learning model for predicting IVF success

Abstract Humans are the only species with a commensal Lactobacillus-dominant vaginal microbiota. Reproductive tract microbes have been linked to fertility outcomes, as has intrauterine inflammation, suggesting immune response may mediate adverse outcomes. In this pilot study, we compared vaginal mic...

Full description

Saved in:
Bibliographic Details
Main Authors: Ofri Bar, Stylianos Vagios, Omer Barkai, Joseph Elshirbini, Irene Souter, Jiawu Xu, Kaitlyn James, Charles Bormann, Makiko Mitsunami, Jorge E. Chavarro, Philipp Foessleitner, Douglas S. Kwon, Moran Yassour, Caroline Mitchell
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:npj Biofilms and Microbiomes
Online Access:https://doi.org/10.1038/s41522-025-00732-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850136683591237632
author Ofri Bar
Stylianos Vagios
Omer Barkai
Joseph Elshirbini
Irene Souter
Jiawu Xu
Kaitlyn James
Charles Bormann
Makiko Mitsunami
Jorge E. Chavarro
Philipp Foessleitner
Douglas S. Kwon
Moran Yassour
Caroline Mitchell
author_facet Ofri Bar
Stylianos Vagios
Omer Barkai
Joseph Elshirbini
Irene Souter
Jiawu Xu
Kaitlyn James
Charles Bormann
Makiko Mitsunami
Jorge E. Chavarro
Philipp Foessleitner
Douglas S. Kwon
Moran Yassour
Caroline Mitchell
author_sort Ofri Bar
collection DOAJ
description Abstract Humans are the only species with a commensal Lactobacillus-dominant vaginal microbiota. Reproductive tract microbes have been linked to fertility outcomes, as has intrauterine inflammation, suggesting immune response may mediate adverse outcomes. In this pilot study, we compared vaginal microbiota composition and immune marker concentrations between patients with unexplained or male factor infertility (MFI), as a control. We applied a supervised machine learning algorithm that integrated microbiome and inflammation data to predict pregnancy outcomes. Twenty-eight participants provided vaginal swabs at three IVF cycle time points; 18 achieved pregnancy. Pregnant participants had lower microbial diversity and inflammation. Among them, MFI cases had higher diversity but lower inflammation than those with unexplained infertility. Our model showed the highest prediction accuracy at time point 2 of the IVF cycle. These findings suggest that vaginal microbiota and inflammation jointly impact fertility and can inform predictive tools in reproductive medicine.
format Article
id doaj-art-e2be7ce2dc3d48e19089be47e845d664
institution OA Journals
issn 2055-5008
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series npj Biofilms and Microbiomes
spelling doaj-art-e2be7ce2dc3d48e19089be47e845d6642025-08-20T02:31:03ZengNature Portfolionpj Biofilms and Microbiomes2055-50082025-06-0111111010.1038/s41522-025-00732-8Harnessing vaginal inflammation and microbiome: a machine learning model for predicting IVF successOfri Bar0Stylianos Vagios1Omer Barkai2Joseph Elshirbini3Irene Souter4Jiawu Xu5Kaitlyn James6Charles Bormann7Makiko Mitsunami8Jorge E. Chavarro9Philipp Foessleitner10Douglas S. Kwon11Moran Yassour12Caroline Mitchell13Department of Obstetrics and Gynecology, Massachusetts General HospitalDepartment of Obstetrics & Gynecology, Tufts University Medical CenterHarvard Medical SchoolRagon Institute of MGH, MIT, and Harvard, Massachusetts General HospitalDivision of Reproductive Endocrinology and Infertility, Department of Obstetrics and Gynecology, Harvard Medical School, Massachusetts General Hospital Fertility CenterRagon Institute of MGH, MIT, and Harvard, Massachusetts General HospitalDepartment of Obstetrics and Gynecology, Massachusetts General HospitalDivision of Reproductive Endocrinology and Infertility, Department of Obstetrics and Gynecology, Harvard Medical School, Massachusetts General Hospital Fertility CenterDivision of Reproductive Endocrinology and Infertility, Department of Obstetrics and Gynecology, Harvard Medical School, Massachusetts General Hospital Fertility CenterDivision of Reproductive Endocrinology and Infertility, Department of Obstetrics and Gynecology, Harvard Medical School, Massachusetts General Hospital Fertility CenterDepartment of Obstetrics and Gynecology, Massachusetts General HospitalHarvard Medical SchoolDepartment of Microbiology and Molecular Genetics, Faculty of Medicine, Hebrew University of JerusalemDepartment of Obstetrics and Gynecology, Massachusetts General HospitalAbstract Humans are the only species with a commensal Lactobacillus-dominant vaginal microbiota. Reproductive tract microbes have been linked to fertility outcomes, as has intrauterine inflammation, suggesting immune response may mediate adverse outcomes. In this pilot study, we compared vaginal microbiota composition and immune marker concentrations between patients with unexplained or male factor infertility (MFI), as a control. We applied a supervised machine learning algorithm that integrated microbiome and inflammation data to predict pregnancy outcomes. Twenty-eight participants provided vaginal swabs at three IVF cycle time points; 18 achieved pregnancy. Pregnant participants had lower microbial diversity and inflammation. Among them, MFI cases had higher diversity but lower inflammation than those with unexplained infertility. Our model showed the highest prediction accuracy at time point 2 of the IVF cycle. These findings suggest that vaginal microbiota and inflammation jointly impact fertility and can inform predictive tools in reproductive medicine.https://doi.org/10.1038/s41522-025-00732-8
spellingShingle Ofri Bar
Stylianos Vagios
Omer Barkai
Joseph Elshirbini
Irene Souter
Jiawu Xu
Kaitlyn James
Charles Bormann
Makiko Mitsunami
Jorge E. Chavarro
Philipp Foessleitner
Douglas S. Kwon
Moran Yassour
Caroline Mitchell
Harnessing vaginal inflammation and microbiome: a machine learning model for predicting IVF success
npj Biofilms and Microbiomes
title Harnessing vaginal inflammation and microbiome: a machine learning model for predicting IVF success
title_full Harnessing vaginal inflammation and microbiome: a machine learning model for predicting IVF success
title_fullStr Harnessing vaginal inflammation and microbiome: a machine learning model for predicting IVF success
title_full_unstemmed Harnessing vaginal inflammation and microbiome: a machine learning model for predicting IVF success
title_short Harnessing vaginal inflammation and microbiome: a machine learning model for predicting IVF success
title_sort harnessing vaginal inflammation and microbiome a machine learning model for predicting ivf success
url https://doi.org/10.1038/s41522-025-00732-8
work_keys_str_mv AT ofribar harnessingvaginalinflammationandmicrobiomeamachinelearningmodelforpredictingivfsuccess
AT stylianosvagios harnessingvaginalinflammationandmicrobiomeamachinelearningmodelforpredictingivfsuccess
AT omerbarkai harnessingvaginalinflammationandmicrobiomeamachinelearningmodelforpredictingivfsuccess
AT josephelshirbini harnessingvaginalinflammationandmicrobiomeamachinelearningmodelforpredictingivfsuccess
AT irenesouter harnessingvaginalinflammationandmicrobiomeamachinelearningmodelforpredictingivfsuccess
AT jiawuxu harnessingvaginalinflammationandmicrobiomeamachinelearningmodelforpredictingivfsuccess
AT kaitlynjames harnessingvaginalinflammationandmicrobiomeamachinelearningmodelforpredictingivfsuccess
AT charlesbormann harnessingvaginalinflammationandmicrobiomeamachinelearningmodelforpredictingivfsuccess
AT makikomitsunami harnessingvaginalinflammationandmicrobiomeamachinelearningmodelforpredictingivfsuccess
AT jorgeechavarro harnessingvaginalinflammationandmicrobiomeamachinelearningmodelforpredictingivfsuccess
AT philippfoessleitner harnessingvaginalinflammationandmicrobiomeamachinelearningmodelforpredictingivfsuccess
AT douglasskwon harnessingvaginalinflammationandmicrobiomeamachinelearningmodelforpredictingivfsuccess
AT moranyassour harnessingvaginalinflammationandmicrobiomeamachinelearningmodelforpredictingivfsuccess
AT carolinemitchell harnessingvaginalinflammationandmicrobiomeamachinelearningmodelforpredictingivfsuccess