# Diagnostic accuracy of machine learning for endometriosis: a systematic review and meta-analysis

## TL;DR

This study reviews how well machine learning models can diagnose endometriosis, finding that models using genetic and imaging data are highly accurate.

## Contribution

The paper provides the first systematic review and meta-analysis of machine learning diagnostic accuracy for endometriosis.

## Key findings

- Machine learning models using genetic data showed high accuracy with an AUC of 0.982 in training sets.
- Imaging-based models also performed well, with an AUC of 0.979 in training and 0.983 in validation sets.
- Models based on clinical features had moderate accuracy with an AUC of 0.810 in training sets.

## Abstract

Researchers have explored machine learning (ML) in diagnosing endometriosis. However, systematic evidence on its diagnostic accuracy for endometriosis remains scarce.

To systematically review the performance of machine learning for the diagnosis of endometriosis.

PubMed, Embase, Cochrane Library, and Web of Science were systematically searched up to October 11, 2024.

Studies that constructed machine learning models to diagnose endometriosis.

Two reviewers independently screened studies, extracted data, and assessed study quality. The risk of bias of the included studies was assessed using the Prediction Model Bias Risk Assessment Tool.

A total of 45 publications were included. Participant numbers ranged from 39 to 612,777. A meta-analysis showed that the area under the curve (AUC), sensitivity, and specificity of models based on clinical features were 0.810 (95% confidence interval [CI]: 0.786–0.835), 0.81 (95% CI: 0.77–0.84), and 0.76 (95% CI: 0.73–0.79) in the training sets, and 0.796 (95% CI: 0.770–0.822), 0.80 (95% CI: 0.75–0.84), and 0.76 (95% CI: 0.72–0.80) in the validation sets. The AUC, sensitivity, and specificity of models based on genetic information were 0.982 (95% CI: 0.975–0.990), 0.94 (95% CI: 0.90–0.97), and 0.99 (95% CI: 0.94–1.00) in the training sets. For the validation sets, these metrics were 0.865 (95% CI: 0.701–1.000), 0.83, and 0.59–0.96. Models based on imaging features exhibited an AUC of 0.979 (95% CI: 0.959–0.999) and 0.983 (0.971–0.995) in the training and validation sets, respectively.

ML models, particularly those based on genetic information and imaging, possess substantial accuracy for detecting endometriosis.

https://www.crd.york.ac.uk/prospero/, identifier CRD42024605113.