Post

New research · Ophthalmology
Indian journal of ophthalmology · 23h
AI / informaticsIndian journal of ophthalmology · 2026

The role of artificial intelligence in academic citation: A study on lens, cataract, and anterior segment research.

Mustafa Civelekler, Mehmet Çıtırık
Read paper
OphthalmologyAI / informatics

DeepSeek showed 52.5% accuracy in generating PubMed citations for ophthalmic literature.

The role of artificial intelligence in academic citation: A study on lens, cataract, and anterior segment research.

Mustafa Civelekler et al. · Indian journal of ophthalmology · 2026
Purpose

To evaluate the accuracy and reliability of four artificial intelligence (AI) models-ChatGPT, Copilot, DeepSeek, and Gemini-in generating PubMed citations for literature related to lens disease, cataracts, iris disorders, and anterior chamber pathology.

Methods

Comparative accuracy assessment study.

Results
DeepSeek accurately generated 52.5% of PubMed citations for ophthalmic literature.
More results

The citation accuracy varied significantly among the models.

DOI mismatches were the most common errors across all models.

Expert validation confirmed these findings, with DeepSeek producing the highest number of fully cited references.

Inter-rater agreement was substantial (Cohen's κ = 0.65).

“
Conclusion · 1 of 3

Domain-specific AI models, particularly DeepSeek, outperform general-purpose models in generating PubMed citations from ophthalmic literature.

Conclusion · 2 of 3

However, all the evaluated models exhibited citation errors, underscoring the necessity of human verification.

Conclusion · 3 of 3

AI tools may enhance academic workflows as assistive systems but should not be used autonomously for reference generation in medical research.

Read paper
0 comments

No comments yet. Be the first.

Related papers

LatestFoundational
AI / Informatics
difference, 0
AI and human experts had the same median quality scores for eye care questions
Case-control
0 of 28
distinct structural changes were absent in all 28 healthy control eyes
Cohort Study
RR, 0.91
Black patients were less likely to start medication for their eye condition
AI / Informatics
100% diagnostic sensitivity
ROFI correctly found every case of eye disease
AI / Informatics
10.50-point increase
students trained with digital patients had higher history-taking assessment scores
AI / Informatics
0.877
The o1 large language model correctly answered 87.7% of ophthalmology questions.
Cohort Study
HR 4.85
chronic pain conditions mean a nearly five times higher risk of developing dry eye disease
Cohort Study
12 per 10,000
a higher rate of eye infections after dexamethasone implant injections