EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Suitability of machine learning for atrophy and fibrosis development in neovascular age‐related macular degeneration

Jesus de la Fuente iD, Sara Llorente-González iD, Patricia Fernandez-Robredo iD, María Hernandez, Alfredo García-Layana iD, Idoia Ochoa iD, Sergio Recalde iD, Spanish AMD group

Acta Ophthalmologica · 2024

DOI: 10.1111/aos.16616 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Acta Ophthalmologica, 2024. Verfasst von Jesus de la Fuente und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Electronics Engineering, School of Engineering (Tecnun), University of Navarra, Pamplona, Spain. Hauptthemen laut MEDLINE: Machine Learning, Angiogenesis Inhibitors, Wet Macular Degeneration, Fibrosis. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: ISCIII Thematic Network of Cooperative Health Research General Subdirection, Multiopticas Foundation, Spanish Ministry of Science and Innovation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To assess the suitability of machine learning (ML) techniques in predicting the development of fibrosis and atrophy in patients with neovascular age‐related macular degeneration (nAMD), receiving anti‐VEGF treatment over a 36‐month period.

Methods

An extensive analysis was conducted on the use of ML to predict fibrosis and atrophy development on nAMD patients at 36 months from start of anti‐VEGF treatment, using only data from the first 12 months. We use data collected according to real‐world practice, which includes clinical and genetic factors.

Results

The ML analysis consistently identified ETDRS as a relevant factor for predicting the development of atrophy and fibrosis, confirming previous statistical analyses. Also, it was shown that genetic variables did not demonstrate statistical relevance in the prediction. Despite the complexity of predicting macular degeneration, our model was able to obtain a balance accuracy of 63% and an AUC of 0.72 when predicting the development of atrophy or fibrosis at 36 months.

Conclusion

This study demonstrates the potential of ML techniques in predicting the development of fibrosis and atrophy in nAMD patients receiving long‐term anti‐VEGF treatment. The findings highlight the importance of clinical factors, particularly ETDRS (early treatment diabetic retinopathy study) visual acuity test, in predicting these outcomes. The lessons learned from this research can guide future ML‐based prediction tasks in the field of ophthalmology and contribute to the design of data collection processes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningAngiogenesis InhibitorsWet Macular DegenerationFibrosisVisual AcuityVascular Endothelial Growth Factor AIntravitreal InjectionsHumansMaleFemaleAgedTomography, Optical CoherenceAtrophyFollow-Up StudiesAged, 80 and overRetrospective StudiesRanibizumabFluorescein AngiographyFundus Oculi

Stichwörter der Autor:innen

atrophyextreme gradient boostingfibrosismachine learningnAMDrandom Forestsupport vector machine

Substanzen

Angiogenesis InhibitorsVascular Endothelial Growth Factor ARanibizumab

Autor:innen und Institutionen

  • Department of Electrical and Electronics Engineering, School of Engineering (Tecnun), University of Navarra, Pamplona, Spain.
  • Center for Data Science, New York University, New York City, New York, USA.
  • Retinal Pathologies and New Therapies Group, Experimental Ophthalmology Laboratory, Department of Ophthalmology, Clinica Universidad de Navarra, Pamplona, Spain.
  • Navarra Institute for Health Research, IdiSNA, Pamplona, Spain.
  • Thematic Network of Cooperative Health Research in Eye Diseases (Oftared), Health Institute Carlos III (ISCIII), Department of Ophthalmology, Clinica Universidad de Navarra, Pamplona, Spain.
  • Institute for Data Science and Artificial Intelligence (DATAI), University of Navarra, Pamplona, Spain.

ORCID-Profile: Jesus de la Fuente, Sara Llorente-González, Patricia Fernandez-Robredo, Alfredo García-Layana, Idoia Ochoa, Sergio Recalde

Förderung

  • ISCIII Thematic Network of Cooperative Health Research General Subdirection
  • Multiopticas Foundation
  • Spanish Ministry of Science and Innovation
  • Fulbright Association
  • Ramon y Cajal Grant from Spain
  • Thematic Network of Cooperative Health Research in Eye Diseases
  • FIS Project European Program FEDER
  • Gipuzkoa Fellows grant from the Basque Government

Zitieren

APA

de la Fuente, J., Llorente-González, S., Fernandez-Robredo, P., Hernandez, M., García-Layana, A., Ochoa, I., Recalde, S., & Spanish AMD group (2024). Suitability of machine learning for atrophy and fibrosis development in neovascular age‐related macular degeneration. Acta Ophthalmologica. https://doi.org/10.1111/aos.16616

Vancouver

de la Fuente J, Llorente-González S, Fernandez-Robredo P, Hernandez M, García-Layana A, Ochoa I, et al. Suitability of machine learning for atrophy and fibrosis development in neovascular age‐related macular degeneration. Acta Ophthalmologica. 2024. doi:10.1111/aos.16616

BibTeX
@article{delaFuente2024,
  author = {de la Fuente, Jesus and Llorente-González, Sara and Fernandez-Robredo, Patricia and Hernandez, María and García-Layana, Alfredo and Ochoa, Idoia and Recalde, Sergio and Spanish AMD group, Spanish AMD group},
  title = {Suitability of machine learning for atrophy and fibrosis development in neovascular age‐related macular degeneration},
  journal = {Acta Ophthalmologica},
  year = {2024},
  doi = {10.1111/aos.16616}
}
Kostenlos starten →