Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-2024
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-20T18:12:04.396182Z
status: published
lens: g_space
sector: health
headline: Artificial intelligence in ophthalmic optical coherence tomography angiography: a bibliometric analysis
dek: Aim To analyze research landscapes, hotspots, and trends in artificial intelligence (AI) applied to ophthalmic optical coherence tomography angiography (OCTA) from 2015 to 2024, aiming to reveal global collaborations and guide future research. Methods We retrieved publications from Web of Science Core Collection using AI and OCTA-related search terms. After screening, 237 articles were analyzed with CiteSpace (version 6.3.R1) for co-citation, collaboration, and keyword burst analysis. Results Annual publications…
gain_title: AI combined with OCTA research has advanced automated, quantitative analysis of retinal vascular imaging, showing potential for diagnosing retinal and choroidal diseases.
problem_title: (none)
trace_subject: (none)
gain_reading: AI combined with OCTA research has advanced automated, quantitative analysis of retinal vascular imaging, showing potential for diagnosing retinal and choroidal diseases.
gain_evidence: significantly advanced the automation and precise quantitative analysis of ophthalmic vascular imaging | substantial potential for diagnosing various retinal and choroidal diseases
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers searched the Web of Science Core Collection for work on artificial intelligence and optical coherence tomography angiography published between 2015 and 2024. They analyzed 237 articles with CiteSpace and found publication volume rose rapidly from 2017, with China and the US the most productive countries.

The findings matter because they show where AI-enabled eye imaging research is concentrating, notably on diagnosing conditions such as diabetic retinopathy and glaucoma. The review itself is a map of the literature, so it does not show that these tools improve care in routine practice, and the authors call for broader clinical validation.
limitation: The reviewed literature is limited by small sample sizes and limited algorithm generalizability, and the authors say large-scale multi-center clinical validation is still needed before routine adoption.
tag: Evidence-backed gain
key_points: The analysis covered 237 articles from 2015 to 2024, drawn from Web of Science Core Collection. | China contributed 94 publications and the US 86, making them the most productive and influential countries. | Main research themes were deep learning and vessel segmentation, diagnosis of diabetic retinopathy and glaucoma, and automated vascular quantification with multimodal imaging. | The authors recommend robust, interpretable models, multi-center validation, and standardized imaging and analysis protocols.
rundown: The study used CiteSpace version 6.3.R1 to run co-citation, collaboration, and keyword burst analyses. These methods were applied to reveal global collaboration patterns and research hotspots in AI-based OCTA.

Three research clusters emerged: deep learning algorithms for vessel segmentation, ocular disease diagnosis including diabetic retinopathy and glaucoma, and automated vascular quantification using multimodal imaging.

The authors say the goal is eventual widespread adoption of AI-OCTA in routine clinical practice. They say that requires large-scale multi-center clinical validation and standardized protocols.
sources:
- peer_reviewed | International Journal of Ophthalmology | https://doi.org/10.18240/ijo.2026.10.19 | 2026-10-18
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

47b504ba45a5849167b81c0e7ead4abdb2cecfe6645575908acb1e9c31a3a5ac

previous

0000000000000000000000000000000000000000000000000000000000000000