Text-to-image model for prostaglandin-associated periorbitopathy counseling: a proof-of-concept study
Bibliographic record
Abstract
To assess the feasibility and utility of a text-to-image artificial intelligence (AI) model in enhancing patient counseling on the cosmetic side effects of prostaglandin analogue (PGA) therapy. Cross-sectional study. Pre- and post-treatment periocular photographs of PGA-treated patients were collected. To simulate bilateral pre-treatment appearance, untreated eyes were mirrored. The Generative Fill feature powered by Adobe Firefly was applied to masked orbital regions, using descriptive text prompts to generate visualizations of prostaglandin-associated periorbitopathy (PAP), including upper eyelid ptosis, enophthalmos, and hypertrichosis. Prompts were iteratively refined to closely replicate known treatment-related changes. The AI model successfully produced visually realistic images within two minutes that closely resembled the actual post-treatment appearance of PAP. Key manifestations such as eyelash hypertrichosis, enophthalmos, deepened upper lid sulcus, and ptosis were effectively simulated using tailored prompts. This proof-of-concept study demonstrates that text-to-image AI may serve as a novel, rapid, and personalized tool for visualizing potential cosmetic side effects of PGA therapy. By enabling patients to preview changes on their own faces, this technology may enhance informed consent, set realistic expectations, and improve treatment adherence. Future research should evaluate patient perceptions, the accuracy of AI-generated outcomes, and integration into clinical workflows.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".