Endometriosis Screening Using Machine Learning And Microbiome Analysis

Aruzhan Bolatova, Mai Oudah
In: Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics · 2026 · pp. 1–6 · doi:10.1145/3807503.3819437 · W7171489216
OA: gold CC0
🔓 Open OA copy View on OpenAlex View at publisher
⚙ AI-generated summary by gemini-2.5-flash-lite, 2026-08-05 ⓘ

This study developed a machine learning framework using gut, vaginal, and endometrial microbiomes to screen for endometriosis, achieving up to 93.8% accuracy, with the vaginal microbiome being the most discriminative.

One-sentence paraphrase of the abstract; not a substitute for reading it. No clinical advice. How this works

Abstract

Endometriosis is a chronic inflammatory disease with no known cure yet affecting at least 10% of women of reproductive age globally. It suffers from a 6-year median diagnostic delay due to reliance on invasive surgical confirmation, which means years of suffering prior to a confirmation of diagnosis. Microbial dysbiosis of the gut, vaginal and endometrial environments has been implicated in disease progression, suggesting that microbiome profiling might support a non‑invasive way of screening that could be used a prior step to assist decision making of the following steps. This study presents a comprehensive machine learning (ML) framework to classify endometriosis across three anatomical niches: gut, vaginal, and endometrial microbiomes. Combinations of ML algorithms and feature selection methods are evaluated to tackle the curse of dimensionality and find and optimal setting for Endometriosis screening. We also identify informative microbial taxa associated with endometriosis across body sites. Experimental results show that feature selection significantly enhances predictive performance, yielding accuracies up to 93.8% (with AUC of 1.00). The vaginal microbiome emerged as the most discriminative environment, followed by the endometrial and gut niches, respectively. We have identified a set of microbial biomarkers, including the enrichment of Anaerococcus, Staphylococcus, and Bradyrhizobium, and the depletion of Lactobacillus.

My notes (saved in your browser only)

Citation neighborhood (2-hop)

Papers in the corpus that this work cites (lower rings, blue) and that cite this one (upper rings, green). Dot size scales with the paper's in-corpus citation count — bigger dot = more influential within the endo/adeno field. Click a dot to open that paper. Outer rings show 2-hop neighbours — papers reached through the immediate citers/citees. [ collapse to 1-hop ]

References (37)

Source provenance

openalex
last seen: 2026-09-29T06:08:52.043707+00:00
License: CC0 · commercial use OK