Bridging the Diagnostic Gap: Reviewing Current Endometriosis Screening Tools and Models

Abstract

Background: Endometriosis affects 10% of reproductive-aged women globally and is one of the major causes of infertility. It is a debilitating, chronic condition with an average diagnostic delay of up to 10 years. This is partly due to the lack of noninvasive tools to diagnose the disease, leading to disease progression and poor health-related outcomes. Aim: The purpose of this scoping review was to synthesize the available literature on the existing tools, their use and applicability, and identify current gaps in the field. Method: A comprehensive search was conducted to identify applicable studies using the Preferred Reporting Items for Systematic Reviews and Meta-Analysis extension for Scoping Reviews guidelines. Results: Eighteen studies were included in the review, with screening tools classified into four categories: questionnaire-based, app-based, machine learning and artificial intelligence (AI)–driven, and subtype-focused models. Among the included study tools, 14 reported on psychometric parameters with area under the receiver operating characteristic curve values ranging from 0.77 to 0.95, with machine learning and AI-driven models reporting the highest accuracy metrics. Conclusion: Significant gaps were noted across identified tools, particularly in external validation, comprehensive psychometric evaluation, and cultural adaptation.