Article Text

Download PDFPDF
Artificial intelligence-based fluid quantification and associated visual outcomes in a real-world, multicentre neovascular age-related macular degeneration national database
  1. Ruben Martin-Pinardel1,2,
  2. Jordi Izquierdo-Serra1,3,
  3. Sandro De Zanet4,
  4. Alba Parrado-Carrillo1,3,
  5. Gonzaga Garay-Aramburu5,
  6. Martin Puzo6,
  7. Carolina Arruabarrena7,
  8. Laura Sararols8,
  9. Maximino Abraldes9,
  10. Laura Broc10,
  11. Jose Juan Escobar-Barranco11,
  12. Marta Figueroa12,
  13. Miguel Angel Zapata13,
  14. José M Ruiz-Moreno14,
  15. Aina Moll-Udina1,3,
  16. Carolina Bernal-Morales1,3,
  17. Socorro Alforja1,3,
  18. Marc Figueras-Roca1,3,
  19. Laia Gómez-Baldó15,
  20. Carlos Ciller4,
  21. Stefanos Apostolopoulos4,
  22. Agata Mosinska4,
  23. Ricardo P Casaroli Marano1,2,3,
  24. Javier Zarranz-Ventura1,2,3
  25. from the FRB SPAIN-IMAGE Project Investigators
    1. 1 IDIBAPS, Barcelona, Spain
    2. 2 School of Medicine, University of Barcelona, Barcelona, Spain
    3. 3 Hospital Clinic de Barcelona, Barcelona, Spain
    4. 4 RetinAI, Bern, Switzerland
    5. 5 Ophthalmology, OSI Vitoria-Gasteiz, Vitoria, Spain
    6. 6 Miguel Servet Ophthalmology Research Group (GIMSO), Miguel Servet University Hospital, Zaragoza, Spain
    7. 7 Retina Section, Hospital Príncipe de Asturias, Alcalá de Henares, Spain
    8. 8 Fundació Privada Hospital Asil Granollers, Granollers, Spain
    9. 9 Hospital de Conxo, Santiago de Compostela, Spain
    10. 10 Hospital Universitari Germans Trias i Pujol, Badalona, Spain
    11. 11 Hospital Dos de Maig, Barcelona, Spain
    12. 12 Hospital Universitario Ramón y Cajal, Madrid, Spain
    13. 13 Hospital Vall d'Hebron, Barcelona, Spain
    14. 14 Hospital Universitario Puerta del Hierro, Madrid, Spain
    15. 15 Medical Department, Novartis Farmacéutica SA, Barcelona, Spain
    1. Correspondence to Dr Javier Zarranz-Ventura, Institut Clínic de Oftalmologia (ICOF), Hospital Clinic de Barcelona, Barcelona, Spain; jzarranz{at}


    Aim To explore associations between artificial intelligence (AI)-based fluid compartment quantifications and 12 months visual outcomes in OCT images from a real-world, multicentre, national cohort of naïve neovascular age-related macular degeneration (nAMD) treated eyes.

    Methods Demographics, visual acuity (VA), drug and number of injections data were collected using a validated web-based tool. Fluid compartment quantifications including intraretinal fluid (IRF), subretinal fluid (SRF) and pigment epithelial detachment (PED) in the fovea (1 mm), parafovea (3 mm) and perifovea (6 mm) were measured in nanoliters (nL) using a validated AI-tool.

    Results 452 naïve nAMD eyes presented a mean VA gain of +5.5 letters with a median of 7 injections over 12 months. Baseline foveal IRF associated poorer baseline (44.7 vs 63.4 letters) and final VA (52.1 vs 69.1), SRF better final VA (67.1 vs 59.0) and greater VA gains (+7.1 vs +1.9), and PED poorer baseline (48.8 vs 57.3) and final VA (55.1 vs 64.1). Predicted VA gains were greater for foveal SRF (+6.2 vs +0.6), parafoveal SRF (+6.9 vs +1.3), perifoveal SRF (+6.2 vs −0.1) and parafoveal IRF (+7.4 vs +3.6, all p<0.05). Fluid dynamics analysis revealed the greatest relative volume reduction for foveal SRF (−16.4 nL, −86.8%), followed by IRF (−17.2 nL, −84.7%) and PED (−19.1 nL, −28.6%). Subgroup analysis showed greater reductions in eyes with higher number of injections.

    Conclusion This real-world study describes an AI-based analysis of fluid dynamics and defines baseline OCT-based patient profiles that associate 12-month visual outcomes in a large cohort of treated naïve nAMD eyes nationwide.

    Data availability statement

    De-identified data are publicly available in a public, open access repository (Dryad Digital Repository).

    Statistics from

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    Data availability statement

    De-identified data are publicly available in a public, open access repository (Dryad Digital Repository).

    View Full Text


    • Twitter @GONZAGAGARAYARAMBURU, @DrMAZapata, @@carlos_ciller, @JavierZarranz

    • Collaborators FRB SPAIN-IMAGE Project Investigators: Fundació Privada Hospital Asil Granollers, Granollers: Gabriel Londoño, Maximiliano Olivera, Karim Bañon, Cynthia Rethati; Miguel Servet Ophthalmology Research Group (GIMSO), Miguel Servet University Hospital, Aragón Institute for Health Research (IIS-Aragón), Zaragoza, Spain: Pilar Calvo, Jorge Sánchez, Oscar Ruiz-Moreno; OSI Araba, Vitoria: Arantza Larrauri-Arana, Angela Gómez-Moreno, David Rodríguez-Feijoo, Enrique Diaz-de-Durana-Santa-Coloma, Maialen Aldazabal-Echeveste, Zuriñe del-Barrio-Lopez-de-Ipiña, Irene Herrero-Díaz; Hospital Universitario Vall de Hebrón, Barcelona: Helena Brosa, Laura Sánchez-Vela, José García-Arumí; Hospital Universitario Príncipe de Asturias, Madrid: Rafael Montejano-Milner, Fernando de Aragón; Hospital de Conxo, Santiago de Compostela: María Lidia Gómez Conde, María José Rodríguez-Cid, María Isabel Fernández Rodríguez, Pablo Almuiña Varela; Hospital Universitario Puerta del Hierro, Madrid: Rocío Vega-González, María García Zamora, Ignacio Flores-Moreno; Hospital Universitari Germans Trias i Pujol, Badalona: Xavier Valldeperas, Ferran Vilaplana Mira, Sandra Gómez Sánchez, Pamela Campos Figueroa; Hospital Dos de Maig, Barcelona: Jose Juan Escobar-Barranco, Manel Fernandez-Bonet, Begoña Pina-Marín; Hospital Universitario Ramón y Cajal, Madrid: Esther Ciancas, María Rios, Inma Dominguez, Paula Hernandez, Julio José Gonzalez-López.

    • Contributors Conception and design, obtained funding, overall responsibility and guarantor: JZ-V; data collection: JI-S, AP-C, GG-A, MP, CA, LS, MA, LB, JJE-B, MF, MAZ, JMR-M, AM-U, CB-M, SoA, MF-R, RPCM and JZ-V; analysis, interpretation and writing: RM-P, JI-S, SDZ, CC, SApostolopoulos, AM, RPCM and JZ-V; manuscript revision: RM-P, JI-S, SDZ, AP-C, GG-A, MP, CA, LS, MA, LB, JJE-B, MF, MAZ, JMR-M, AM-U, CB-M, SA, MF-R, LG-B, CC, StA, AM, RPCM and JZ-V.

    • Funding This work was supported in part by a research collaboration from Novartis Pharmaceuticals (FCRB code number: CP042794).

    • Competing interests JZ-V is a grant holder for Novartis Pharmaceuticals, Bayer and Allergan, and a consultant for Novartis Pharmaceuticals, Bayer, Allergan, Alcon, Alimera Sciences, Bausch and Lomb, Brill Pharma, DORC, Preceyes, Roche, Topcon, and Zeiss. Laia Gomez-Baldo is an employee of Novartis. SDZ, CC, SApostolopoulos and AM are employees of RetinAI.

    • Provenance and peer review Not commissioned; externally peer reviewed.

    • Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.

    Linked Articles

    • Highlights from this issue
      Frank Larkin