why choose us

300×250 Ad Slot

Research Article: Real-world evaluation of an OCT-based AI decision-support system for neovascular AMD activity triage in teleophthalmology

Date Published: 2026-07-01

Abstract:
To 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. Retrospective 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. Agreement 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. The 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.

Introduction:
Neovascular age-related macular degeneration (nAMD) is a leading cause of visual impairment among the elderly population in industrialized nations. With increasing life expectancy, its global prevalence and healthcare burden are expected to rise substantially ( 1 ). Although timely detection and anti-VEGF therapy can preserve vision, adherence to monitoring and treatment schedules remains suboptimal in real-world practice ( 2 ), particularly in decentralized regions with limited access to retinal specialists ( 3…

Read more

300×250 Ad Slot