Machine learning and Voronoi-based decision boundaries for Bacterial vaginosis to determine population- specific microbial interactions
- 1J. Crayton Pruitt Department of Biomedical Engineering, University of Florida, Gainesville, Florida, United States of America
- 2Emerging Pathogens Institute, University of Florida, Gainesville, Florida, United States of America
- 3Department of African American Studies, University of Florida, Gainesville, Florida, United States of America
Abstract
In this study we utilize machine learning techniques to create predictive models and determine key bacterial interactions for the diagnosis of Bacterial vaginosis. Bacterial vaginosis (BV) is a common vaginal syndrome affecting reproductive-age women globally. It is associated with various adverse obstetric and gynecological out-comes including increased risk of sexually transmitted infections, HIV, cervical cancer, and pre-term birth. While it is known that BV is caused by a shift in abundance between Lactobacilli and anaerobic bacteria, it is unknown how gradual shifts in that balance lead towards BV status. Here we perform a rigorous comparison of machine learning architectures and feature selection methods used to train models on 16s rRNA data of patients presenting with BV. Using the highest-performing models, we employ explainable AI methods to determine the most important bacteria for BV diagnosis. Furthermore, we implement Voronoi-based decision boundaries to show how the relative abundances between pairs of these bacteria results in BV positive or BV negative outcomes. Results: We find that support vector machine and random forest models in combination with feature selection predict BV diagnosis with the most balanced accuracy. Using those models, we identify four Lactobacilli spp and six anaerobes to be key in to be key to the diagnosis of BV. The determination of key bacteria can inform BV diagnostics and pathogenesis research to species that have previously eluded scientific focus. Additionally, decision boundary plots offer a diagnostic point of reference for how the relative abundances of key vaginal flora are indicative of BV outcomes. Author summary: Bacterial vaginosis (BV) is one of the most common vaginal syndromes among women of reproductive age. It impacts 23% to 29% of women globally and is linked to an increased risk of gynecological complications. Over the past decades research has yielded innovations in BV diagnosis and treatment, yet very little is known about how the microbial species interact with each other to progress into BV. Additionally, while evidence suggests that women have complex and diverse vaginal microbiomes that can vary in a population specific manner, many diagnostic methods and treatments ignore personalized factors. Here, we use machine learning models across populations to identify important microbes for BV diagnosis using machine learning. Furthermore, we characterize how abundances of these microbes determines BV. To do this, we identify the best models for each population among the 150 trained to determine BV in patients. We use these models to identify the bacteria that are most important in BV using feature importance. We highlight 10 bacteria that are important for BV determination, 3 of which have not previously been studied in the context of BV. We also use a novel method to create machine learning decision boundary plots to show how the abundance of bacterial pairings can be indicative of BV. With further accompanying research, these plots have the potential to be used as a diagnostic tool or screening reference.
Related
- Effectiveness of male partner treatment in reducing recurrence of bacterial vaginosis: a systematic review and meta-analysis
- Large-scale metagenomic characterization of the vaginal microbiome and uropathogens in women with recent bacterial vaginosis and urinary tract infections
- Exploratory pilot study of a spray-type probiotic delivery system for vaginal health in women at risk for bacterial vaginosis
- Effect of pHyph, A novel antibiotic-free treatment, on bacterial vaginosis symptoms and vaginal microbiome composition
- Comparative Performance of Aptima BV/CV-TV and Vaginal Real Time Assays for the Molecular Diagnosis of Bacterial Vaginosis and Vaginitis.
BibTeX
@article{celeste2026machine,
title = {{Machine learning and Voronoi-based decision boundaries for Bacterial vaginosis to determine population- specific microbial interactions}},
author = {Cameron G. Celeste and Carleigh C. Sokolik and Wambui Gachunga and Ivana K. Parker},
journal = {PLOS Computational Biology},
year = {2026},
month = oct,
doi = {10.1371/journal.pcbi.1014767},
url = {https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014767},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Machine learning and Voronoi-based decision boundaries for Bacterial vaginosis to determine population- specific microbial interactions
AU - Cameron G. Celeste
AU - Carleigh C. Sokolik
AU - Wambui Gachunga
AU - Ivana K. Parker
PY - 2026
DA - 2026/10/05
JO - PLOS Computational Biology
DO - 10.1371/journal.pcbi.1014767
UR - https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014767
AB - In this study we utilize machine learning techniques to create predictive models and determine key bacterial interactions for the diagnosis of Bacterial vaginosis. Bacterial vaginosis (BV) is a common vaginal syndrome affecting reproductive-age women globally. It is associated with various adverse obstetric and gynecological out-comes including increased risk of sexually transmitted infections, HIV, cervical cancer, and pre-term birth. While it is known that BV is caused by a shift in abundance between Lactobacilli and anaerobic bacteria, it is unknown how gradual shifts in that balance lead towards BV status. Here we perform a rigorous comparison of machine learning architectures and feature selection methods used to train models on 16s rRNA data of patients presenting with BV. Using the highest-performing models, we employ explainable AI methods to determine the most important bacteria for BV diagnosis. Furthermore, we implement Voronoi-based decision boundaries to show how the relative abundances between pairs of these bacteria results in BV positive or BV negative outcomes. Results: We find that support vector machine and random forest models in combination with feature selection predict BV diagnosis with the most balanced accuracy. Using those models, we identify four Lactobacilli spp and six anaerobes to be key in to be key to the diagnosis of BV. The determination of key bacteria can inform BV diagnostics and pathogenesis research to species that have previously eluded scientific focus. Additionally, decision boundary plots offer a diagnostic point of reference for how the relative abundances of key vaginal flora are indicative of BV outcomes. Author summary: Bacterial vaginosis (BV) is one of the most common vaginal syndromes among women of reproductive age. It impacts 23% to 29% of women globally and is linked to an increased risk of gynecological complications. Over the past decades research has yielded innovations in BV diagnosis and treatment, yet very little is known about how the microbial species interact with each other to progress into BV. Additionally, while evidence suggests that women have complex and diverse vaginal microbiomes that can vary in a population specific manner, many diagnostic methods and treatments ignore personalized factors. Here, we use machine learning models across populations to identify important microbes for BV diagnosis using machine learning. Furthermore, we characterize how abundances of these microbes determines BV. To do this, we identify the best models for each population among the 150 trained to determine BV in patients. We use these models to identify the bacteria that are most important in BV using feature importance. We highlight 10 bacteria that are important for BV determination, 3 of which have not previously been studied in the context of BV. We also use a novel method to create machine learning decision boundary plots to show how the abundance of bacterial pairings can be indicative of BV. With further accompanying research, these plots have the potential to be used as a diagnostic tool or screening reference.
SN - 1553-7358
ER -