The involvement of clinicians in the most highly cited publications on artificial intelligence in ophthalmology indexed journals
Bibliographic record
Abstract
Significant advances in artificial intelligence (AI) have led to promising applications in ophthalmology. This study highlights the involvement of clinicians in the most cited ophthalmology publications on AI in ophthalmology journals indexed by Web of Science. Articles examining AI in ophthalmology journals were processed from Web of Science. After selecting relevant articles, we performed bibliometric analyses at the article and author levels as of March 2024. The primary outcome measure was the number of citations per article. Secondary outcomes included article measures (publication year, subspecialties, article type, databases, imaging) and author attributes (gender, academic metrics, location). The top 100 publications were cited between 58 and 734 times, with a median of 91 citations. Publication reprint addresses were mainly based in America (44) and in Europe (22). Common subspecialties were retina (60), glaucoma (44) and cornea (18). Most imaging modalities were fundus photography (47), optical coherence tomography (47) and visual fields (19). 76 studies were aimed at the development and evaluation of a diagnostic technology. Some private databases (44 %) and public databases (40 %) were specified. Among the 399 men and 163 women authors, 297 were physicians (52.9 %). Women and men had significantly different h-indexes (women: 23 [interquartile range (IQR): 13–46] vs. men: 38.5 [17–65]; P = 0.02) and number of published documents (women: 104 [32–277] vs. men: 188.5 [63.5–394]; P = 0.03). The most influential articles in AI and ophthalmology by number of citations predominantly used AI for image recognition and improving diagnostic technology in retina followed by glaucoma. Physicians had a predominant role in these, highlighting the continued importance of clinician involvement in this research.
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 | 0.008 | 0.081 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.019 | 0.031 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.006 | 0.003 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.009 | 0.003 |
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".