AI-Driven OCT Biomarkers for Choroidal Neovascularization Assessment in Punctate Inner Choroidopathy and Multifocal Choroiditis.
Bibliographic record
Abstract
Purpose To assess potential optical coherence tomography (OCT) biomarkers associated with the presence and future development of secondary choroidal neovascularization (CNV) in inflammatory lesions using artificial intelligence (AI)-based segmentation in patients with punctate inner choroidopathy (PIC) and multifocal choroiditis (MFC). Design Multicenter, retrospective cross-sectional and cohort study. Subjects The study included 208 eyes from 156 patients, comprising 112 patients with PIC (143 eyes) and 44 patients with MFC (65 eyes). Methods Sequential OCT scans from patients with MFC and PIC were analyzed using an AI software tool (Discovery® OCT Biomarker Detector, RetinAI AG, Switzerland). The software evaluated morphological biomarkers, fluid and lesion compartment volumes, and retinal layer thickness. Manual corrections were performed on AI-based segmentations when necessary. Data were compared between MFC and PIC, and between eyes with and without CNV presence and development. Linear mixed-effects modeling was employed to identify predictive biomarkers for CNV development. Main Outcome Measures The primary outcomes were baseline lesion volume and presence of CNV and the secondary outcome was best-corrected visual acuity (BCVA). Results At baseline, CNV was present in 72.6% of the eyes (75.5% in PIC and 66.1% in MFC). During follow-up, 20 eyes developed CNV from inflammatory lesions (16 with PIC and 4 with MFC). CNV-positive eyes had significantly lower BCVA at baseline (0.28 ± 0.26 LogMAR vs. 0.14 ± 0.21 LogMAR; p < 0.0001). Baseline lesion volume was significantly greater in CNV-positive eyes (33.80 nL ± 63.71) compared to CNV-negative eyes (5.44 nL ± 12.44; p < 0.0001). Larger lesion volume (β = 24.29, 95% CI: 9.77-38.80; p = 0.001) and longer disease duration (β = 0.17, 95% CI: 0.07-0.27; p = 0.001) were associated with CNV presence. Conclusions Larger baseline lesion volume and longer disease duration are associated with secondary CNV in PIC and MFC patients. AI-driven OCT analysis has potential to identify key biomarkers, supporting personalized treatment strategies and improving patient outcomes.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".