PurposeTo evaluate real-world agreement between a CE-marked OCT-based AI decision-support system and routine retreatment decisions for neovascular AMD within a teleophthalmology workflow.MethodsRetrospective clinical study including 429 OCT examinations from 247 patients (306 treated eyes) with neovascular AMD. Retinal specialists made routine retreatment decisions (“inject” vs “watch-and-wait”) using full clinical context. Independently, the AI system (deepeye® TPS, version 1.2) analyzed the current OCT volume only (no prior OCT, visual acuity, treatment interval, or clinical notes) and generated a Disease Activity Score (DAS; 0–100) used to derive an “inject” vs “watch-and-wait” recommendation. Discrepant cases were re-evaluated by senior graders to establish a double-senior-graded (DSG) reference standard. Implementation analyses assessed a deferral (“safety zone”) strategy. Main outcome measures included agreement/accuracy, sensitivity, and specificity versus real-world decisions and the double-senior-graded (DSG) reference standard, as well as decision coverage under deferral.ResultsAgreement between real-world decisions and AI recommendations was 83.2% (sensitivity 74.7%, specificity 88.0%). Against the double-senior-graded reference standard (DSG), accuracy in the full analysis set (FAS), analyzed at the examination level, was 85.5% (sensitivity 77.2%, specificity 90.4%). Using an empirically optimized DAS threshold, accuracy increased to 88.6% (sensitivity 78.5%, specificity 94.9%) in the eligible retreatment-decision set (ERDS). Application of a deferral policy (“safety zone”, DAS 33–64) resulted in automated recommendations for 78.4% of eligible examinations, while 21.6% were deferred due to intermediate DAS values; among examinations with an automated recommendation, accuracy was 92.3% (sensitivity 83.2%, specificity 97.5%). Most misclassifications involved subtle IRF/SRF and SHRM as identified by the reading center and tended to be underestimated by the AI.ConclusionThe evaluated OCT-only AI decision-support output showed substantial agreement with routine retinal-specialist retreatment decisions in a real-world teleophthalmology workflow, particularly when intermediate Disease Activity Scores were deferred to human review. However, false-negative cases and context-dependent discrepancies highlight that the system should support, not replace, clinician judgement. Prospective multicenter validation using longitudinal and multimodal input data is required before broader workflow integration can be recommended.
Purpose: Macular atrophy (MA) can develop during long-term anti-angiogenic therapy in neovascular AMD (nAMD). This study characterizes the development of MA, associated changes in macular neovascularization (MNV), and the functional consequences. Patients and methods: MNV and MA size were analyzed in 143 eyes from 94 patients with nAMD (31 male, 63 female; mean age: 75.9 ± 7.5 years; mean follow-up: 5.23 ± 2.34 years; mean 7.0 ± 2.3 injections/year). MNV and MA areas were delineated on optical coherence tomography (OCT) B-scans, transposed onto near-infrared images, and quantified at baseline and annually. Best-corrected visual acuity (BCVA) and additional features, including serous pigment epithelial detachment (PED) and subretinal drusenoid deposits (SDD), were also recorded. Results: MA was present at baseline in 10.5% of eyes and developed in an additional 54.7% during follow-up, with a mean onset at 2.44 ± 1.51 years. Larger MNV size (p = .001) and faster MNV growth (p = .03) were significantly associated with MA development, as well as the presence of SDD (p = .001) and PED (p = .02). MA was linked to significantly reduced BCVA (p = .0024) especially after subfoveal involvement. Conclusion: MA commonly emerges during long-term anti-angiogenic therapy in nAMD and is functionally relevant, especially when the fovea is involved. Its development appears primarily associated with MNV size and progression resulting from MNV transformation. These findings suggest that MA and MNV transformation (“fibrosis”) represent two facets of the same pathological process contributing to vision loss. Consequently, preventing MA in nAMD could become an important target for future therapeutic strategies.
Ob pachychorioidale Makulaerkrankungen ein echtes Kontinuum darstellen, ist weiterhin nicht geklärt. Für ein Spektrumsmodell sprechen gemeinsame chorioidale Merkmale wie Pachyvessels, chorioidale Hyperpermeabilität, venöse Abflussstörung und klinisch beschriebene Übergänge von der Chorioretinopathia centralis serosa (CCS) zur pachychorioidalen Neovasuklopathie (PNV) sowie von PNV zu polypoidalen chorioidalen Vakulopathie (PCV). Die Evidenz hierfür bleibt jedoch niedrig: Sie beruht überwiegend auf klinischen Beobachtungen, retrospektiven Kohorten und kleinen Fallserien mit uneinheitlichen Definitionen, selektierten Kollektiven und meist ohne unabhängige Reading-Center-Bewertung. Aktuelle Arbeiten schärfen die Gegenposition: Die Choroideadicke allein ist weder notwendig noch hinreichend, die PNV umfasst offenbar verschiedene Subtypen, und die PCV ist ätiologisch heterogen. Epidemiologische Unterschiede zwischen klassischer CCS und klassischer PCV sprechen zusätzlich gegen ein einfaches lineares Ein-Krankheits-Modell. Derzeit erscheint daher ein vorsichtiges, nichtlineares Spektrumsmodell mit möglichen, aber nicht obligaten Progressionspfaden angemessener als die Annahme einer einzigen Erkrankung in festen Stadien.
