EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

Rendimiento Diagnóstico de la Inteligencia Artificial en la Identificación de Lesiones del Manguito Rotador Mediante Resonancia Magnética: Revisión Sistemática

Maira Lorena Ibarra Guaman, María Rebeca Arizaga Ramírez, José Patricio Beltrán Carreño

Ibero Ciencias - Revista Científica y Académica - ISSN 3072-7197 · 23.04.2026 · 5 (2) · 697-712

DOI: 10.63371/ic.v5.n2.a1004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Ibero Ciencias - Revista Científica y Académica - ISSN 3072-7197, online erschienen am 23.04.2026. Verfasst von Maira Lorena Ibarra Guaman und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rotator cuff injuries are a common cause of shoulder pain and functional limitation, with a significant clinical and socioeconomic impact. Magnetic resonance imaging (MRI) is the reference imaging modality for their evaluation; however, its interpretation is subject to interobserver variability and depends on the radiologist’s level of experience. In this context, artificial intelligence (AI), particularly deep learning–based models, has emerged as a promising tool to support imaging-based diagnosis. The objective of this systematic review was to evaluate the available scientific evidence on the diagnostic accuracy of artificial intelligence applied to magnetic resonance imaging for the detection and characterization of rotator cuff injuries. A systematic review of diagnostic accuracy studies was conducted in accordance with PRISMA 2020 recommendations, using a structured search of PubMed/MEDLINE, Embase, Scopus, Web of Science, the Cochrane Library, and IEEE Xplore, including studies published between 2020 and 2025 in English or Spanish. Study selection and data extraction were performed independently by two reviewers, and the risk of bias was assessed using the QUADAS-2 tool. After the selection process, 30 studies were included, with results demonstrating sensitivities and specificities generally exceeding 85%, areas under the ROC curve greater than 0.90 in most cases, and diagnostic performance comparable to that of expert radiologists. In conclusion, artificial intelligence applied to shoulder MRI shows high potential as a diagnostic support tool; however, methodological heterogeneity and limited external validation indicate the need for prospective, multicenter studies before widespread clinical implementation

Zitieren

APA

Guaman, M. L. I., Ramírez, M. R. A., & Carreño, J. P. B. (2026). Rendimiento Diagnóstico de la Inteligencia Artificial en la Identificación de Lesiones del Manguito Rotador Mediante Resonancia Magnética: Revisión Sistemática. Ibero Ciencias - Revista Científica y Académica - ISSN 3072-7197, 5(2), 697-712. https://doi.org/10.63371/ic.v5.n2.a1004

Vancouver

Guaman MLI, Ramírez MRA, Carreño JPB. Rendimiento Diagnóstico de la Inteligencia Artificial en la Identificación de Lesiones del Manguito Rotador Mediante Resonancia Magnética: Revisión Sistemática. Ibero Ciencias - Revista Científica y Académica - ISSN 3072-7197. 2026;5(2):697-712. doi:10.63371/ic.v5.n2.a1004

BibTeX
@article{Guaman2026,
  author = {Guaman, Maira Lorena Ibarra and Ramírez, María Rebeca Arizaga and Carreño, José Patricio Beltrán},
  title = {Rendimiento Diagnóstico de la Inteligencia Artificial en la Identificación de Lesiones del Manguito Rotador Mediante Resonancia Magnética: Revisión Sistemática},
  journal = {Ibero Ciencias - Revista Científica y Académica - ISSN 3072-7197},
  year = {2026},
  volume = {5},
  number = {2},
  pages = {697--712},
  doi = {10.63371/ic.v5.n2.a1004}
}
Kostenlos starten →