Utility of Artificial Intelligence for the Diagnosis, Prognosis, and Management of Central Serous Chorioretinopathy: a Narrative Review

UDC.coleccionInvestigación
UDC.departamentoCiencias da Computación e Tecnoloxías da Información
UDC.grupoInvGrupo de Visión Artificial e Recoñecemento de Patróns (VARPA)
UDC.institutoCentroINIBIC - Instituto de Investigacións Biomédicas de A Coruña
UDC.issue101
UDC.journalTitleInternational Journal of Retina and Vitreous
UDC.volume12
dc.contributor.authorFernández-Vigo, José Ignacio
dc.contributor.authorValverde-Megías, Alicia
dc.contributor.authorBurgos-Blasco, Bárbara
dc.contributor.authorMoura, Joaquim de
dc.contributor.authorLy-Yang, Fernando
dc.date.accessioned2026-09-02T10:26:01Z
dc.date.available2026-09-02T10:26:01Z
dc.date.issued2026
dc.description.abstract[Abstract]: Central serous chorioretinopathy (CSC) represents a significant cause of visual impairment, particularly in working-age individuals. Despite advances in multimodal imaging and evidence supporting photodynamic therapy (PDT) as the mainstay of chronic CSC, current clinical workflows are still affected by variability in image interpretation, manual quantification, and individualized treatment selection. This narrative review investigates the utility of Artificial Intelligence (AI) in improving the diagnosis, prognosis, and management of CSC. AI-based image analysis, including Optical Coherence Tomography (OCT), Optical Coherence Tomography Angiography (OCTA), and Fundus Fluorescein Angiography (FFA), has demonstrated high diagnostic accuracy across selected datasets and the ability to identify relevant biomarkers, thereby improving efficiency and consistency. Machine learning models demonstrate promising predictive power for subretinal fluid absorption, visual acuity outcomes, and disease recurrence, and identify critical prognostic factors. While emerging, AI-guided treatment strategies hold promise for personalized therapy, particularly for optimizing PDT, laser-based interventions, and follow-up strategies. The integration of AI into clinical decision-making workflows may elevate diagnostic capabilities, especially for non-specialists, and reduce clinical workload. However, the widespread implementation of AI in CSC faces notable challenges, including dataset bias, limited external validation, insufficient representation of differential diagnoses, regulatory complexities, and ethical considerations pertaining to transparency and equitable access. Future directions emphasize integrating multimodal data, fostering global collaborative efforts, and developing robust, generalizable AI models to fully realize AI’s potential to enhance patient care and optimize healthcare delivery for CSC.
dc.identifier.citationFernández-Vigo, J.I., Valverde-Megías, A., Burgos-Blasco, B. et al. Utility of artificial intelligence for the diagnosis, prognosis, and management of central serous chorioretinopathy: a narrative review. Int J Retin Vitr 12, 101 (2026). https://doi.org/10.1186/s40942-026-00867-6
dc.identifier.doi10.1186/s40942-026-00867-6
dc.identifier.issn2056-9920
dc.identifier.urihttps://hdl.handle.net/2183/49133
dc.language.isoeng
dc.publisherSpringer Nature
dc.relation.urihttps://doi.org/10.1186/s40942-026-00867-6
dc.rightsAttribution 4.0 Internationalen
dc.rights.accessRightsopen access
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectCentral serous chorioretinopathy
dc.subjectPachychoroid disease
dc.subjectArtificial intelligence
dc.subjectMachine learning
dc.subjectBiomarkers
dc.subjectTreatment strategies
dc.titleUtility of Artificial Intelligence for the Diagnosis, Prognosis, and Management of Central Serous Chorioretinopathy: a Narrative Review
dc.typejournal article
dc.type.hasVersionVoR
dspace.entity.typePublication
relation.isAuthorOfPublication028dac6b-dd82-408f-bc69-0a52e2340a54
relation.isAuthorOfPublication.latestForDiscovery028dac6b-dd82-408f-bc69-0a52e2340a54

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Moura_Joaquimde_2026_Utility_of_artificial_intelligence_for_the_diagnosis.pdf
Size:
1.55 MB
Format:
Adobe Portable Document Format