Artificial intelligence versus ophthalmology experts: Comparative analysis of responses to blepharitis patient queries
Bibliographic record
Abstract
Objective To assess the accuracy and clinical education value of responses from AI models (GPT-3.5, GPT-4o, Gemini, Gemini Advanced) compared to expert ophthalmologists’ answers to common patient questions about blepharitis, and evaluate their potential for patient education and clinical use. Methods Thirteen frequently asked questions about blepharitis were selected. Responses were generated by AI models and compared to expert answers. A panel of ophthalmologists rated each response for correctness and clinical education value using a 7-point Likert scale. The Friedman test with post hoc comparisons was used to identify performance differences. Results Expert responses had the highest correctness (6.3) and clinical education value (6.4) scores, especially in complex, context-driven questions. Significant differences were found between expert and AI responses ( P < 0.05). Among AI models, GPT-3.5 performed best in simple definitions (correctness: 6.4) but dropped to 5.5 in nuanced cases. GPT-4o followed (5.4), while Gemini and Gemini Advanced scored lower (5.0 and 4.9), especially in diagnostic and treatment contexts. Conclusions AI models can support patient education by effectively answering basic factual questions about blepharitis. However, their limitations in complex clinical scenarios highlight the continued need for expert input. While promising as educational tools, AI should complement—not replace—clinician guidance in patient care.
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 | 0.015 | 0.112 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".