Inteligência artificial aplicada à endometriose, diagnóstico pélvico e lacunas em fenótipos neurológicos e ósseos: Uma revisão integrativa

Laryssa Andrade da Luz Santos, Dilton Jacobina Mesquita Neto, Emanuelle da Silva Ferreira, Ana Luiza Monteiro de Sousa, Bruno Borges Pereira, Mayana de Mello Bastos Campos, Suallen Amaral Rocha Machado, Júlia Maia Medeiros, Stephanie Santana Saint Clair Cerqueira, Sarah Gabriela Vavrik de Mesquita
In: 0719-4706 · 2026 · W7219293603
OA: gold CC0
🔓 Open OA copy Full text JSON View on OpenAlex
⚙ AI-generated summary by qwen3.7-flash, 2026-10-26 ⓘ

This integrative review analyzed 24 studies demonstrating that artificial intelligence models using imaging and biomarkers achieve high diagnostic performance for pelvic endometriosis, while identifying a lack of research on AI applications for neurological or bone manifestations.

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

⚙ AI-generated deep summary by qwen3.7-flash, 2026-10-26 · read from full text ⓘ

This integrative review analyzed 24 studies published between 2021 and 2026 to evaluate the application of artificial intelligence in diagnosing endometriosis. The research focused on diagnostic capabilities related to the central nervous system and bone tissue, assessing models based on ultrasound, magnetic resonance imaging, radiomics, and microRNAs. Key findings indicated that these AI models demonstrated high diagnostic performance with areas under the curve exceeding 0.90 for various pelvic phenotypes. However, the authors explicitly noted a significant gap, as no applications were identified for diagnosing endometriosis manifestations in the central nervous system or bone tissue. This paper is centrally about endometriosis — specifically evaluating the current state and limitations of artificial intelligence tools for its diagnosis.

Read from the paper's body, not the abstract. Not a substitute for reading the paper. No clinical advice. How this works

Abstract

To analyze the application of artificial intelligence (AI) in the diagnosis of endometriosis, focusing on diagnostic possibilities related to the central nervous system (CNS) and bone tissue. An integrative review conducted according to PRISMA 2020. The search was performed in PubMed, including original studies published between 2021 and 2026 on AI, machine learning, deep learning, radiomics, and molecular biomarkers applied to endometriosis. Methodological quality was assessed using the QUADAS-2, STROBE, CARE Checklist, and ARRIVE Guidelines instruments. Of the 530 records identified, 24 studies comprised the final sample. Models based on ultrasonography, magnetic resonance imaging, radiomics, and microRNAs showed high diagnostic performance, with AUCs greater than 0.90 in several studies. No applications of AI aimed at diagnosing endometriosis in the CNS or bone tissue were identified. AI presents high diagnostic potential for pelvic phenotypes, yet gaps remain in the development of specific models for the neurological and bone manifestations of the disease.
Full text 2,202 characters · extracted from oa-html · click to expand
Inteligencia artificial aplicada a la endometriosis, diagnóstico pélvico y vacíos en fenotipos neurológicos y óseos Una revisión integradora DOI: https://doi.org/10.58210/rie3956Palabras clave: endometriosis, inteligencia artificial, aprendizaje automático, radiómica, sistema nervioso centralResumen Analizar la aplicación de la inteligencia artificial (IA) en el diagnóstico de la endometriosis, con foco en las posibilidades diagnósticas relacionadas con el sistema nervioso central (SNC) y el tejido óseo. Revisión integrativa conducida conforme al PRISMA 2020. La búsqueda se realizó en PubMed, incluyendo estudios originales publicados entre 2021 y 2026 sobre IA, aprendizaje automático, aprendizaje profundo, radiómica y biomarcadores moleculares aplicados a la endometriosis. La calidad metodológica se evaluó mediante los instrumentos QUADAS-2, STROBE, CARE Checklist y ARRIVE Guidelines. De los 530 registros identificados, 24 estudios conformaron la muestra final. Modelos basados en ultrasonografía, resonancia magnética, radiómica y microRNAs presentaron elevado rendimiento diagnóstico, con AUC superiores a 0,90 en diversos estudios. No se identificaron aplicaciones de IA orientadas al diagnóstico de la endometriosis en el SNC o el tejido óseo. La IA presenta elevado potencial diagnóstico para fenotipos pélvicos; sin embargo, persisten lagunas en el desarrollo de modelos específicos para las manifestaciones neurológicas y óseas de la enfermedad. Publicado Cómo citar Número Sección Licencia Derechos de autor 2026 Laryssa Andrade da Luz Santos, Dilton Jacobina Mesquita Neto, Emanuelle da Silva Ferreira, Ana Luiza Monteiro de Sousa, Bruno Borges Pereira, Mayana de Mello Bastos Campos, Suallen Amaral Rocha Machado, Júlia Maia Medeiros, Stephanie santana Saint clair Cerqueira, Sarah Gabriela Vavrik de Mesquita Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0. Los autores retienen los derechos de autor y otorgan a Revista Inclusiones el derecho de publicación bajo Creative Commons Attribution 4.0 International (CC BY 4.0). Esto permite el uso, distribución y reproducción en cualquier medio, siempre que se otorgue la debida atribución al autor.

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy is the canonical version.

My notes (saved in your browser only)

⚙ Ask this paper AI returns verbatim quotes from the full text · source: oa-html ⓘ

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2026) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

openalex
last seen: 2026-10-06T06:07:52.081803+00:00
License: CC0 · commercial use OK