Your browser doesn't support javascript.
loading
Suitability of machine learning for atrophy and fibrosis development in neovascular age-related macular degeneration.
de la Fuente, Jesus; Llorente-González, Sara; Fernandez-Robredo, Patricia; Hernandez, María; García-Layana, Alfredo; Ochoa, Idoia; Recalde, Sergio.
Afiliación
  • de la Fuente J; Department of Electrical and Electronics Engineering, School of Engineering (Tecnun), University of Navarra, Pamplona, Spain.
  • Llorente-González S; Center for Data Science, New York University, New York City, New York, USA.
  • Fernandez-Robredo P; Retinal Pathologies and New Therapies Group, Experimental Ophthalmology Laboratory, Department of Ophthalmology, Clinica Universidad de Navarra, Pamplona, Spain.
  • Hernandez M; Navarra Institute for Health Research, IdiSNA, Pamplona, Spain.
  • García-Layana A; Thematic Network of Cooperative Health Research in Eye Diseases (Oftared), Health Institute Carlos III (ISCIII), Department of Ophthalmology, Clinica Universidad de Navarra, Pamplona, Spain.
  • Ochoa I; Retinal Pathologies and New Therapies Group, Experimental Ophthalmology Laboratory, Department of Ophthalmology, Clinica Universidad de Navarra, Pamplona, Spain.
  • Recalde S; Navarra Institute for Health Research, IdiSNA, Pamplona, Spain.
Acta Ophthalmol ; 102(5): e831-e841, 2024 Aug.
Article en En | MEDLINE | ID: mdl-38131161
ABSTRACT

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.
Asunto(s)
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Fibrosis / Agudeza Visual / Inhibidores de la Angiogénesis / Factor A de Crecimiento Endotelial Vascular / Degeneración Macular Húmeda / Inyecciones Intravítreas / Aprendizaje Automático Límite: Aged / Aged80 / Female / Humans / Male Idioma: En Revista: Acta Ophthalmol Asunto de la revista: OFTALMOLOGIA Año: 2024 Tipo del documento: Article País de afiliación: España Pais de publicación: Reino Unido
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Fibrosis / Agudeza Visual / Inhibidores de la Angiogénesis / Factor A de Crecimiento Endotelial Vascular / Degeneración Macular Húmeda / Inyecciones Intravítreas / Aprendizaje Automático Límite: Aged / Aged80 / Female / Humans / Male Idioma: En Revista: Acta Ophthalmol Asunto de la revista: OFTALMOLOGIA Año: 2024 Tipo del documento: Article País de afiliación: España Pais de publicación: Reino Unido