Bora Deniz Argon

Dr. Bora Deniz Argon

orcid

Research Focus & Metrics

Representative Publications

View All Publications
1 April 2024 in Japanese Journal of Ophthalmology
Verified
Journal Article
Closed access
PDF file
FSFidan Safalı
Fidan Safalı
SOSerap Yurttaşer Ocak
Serap Yurttaşer Ocak
BABora Deniz Argon
Bora Deniz Argon
GKGülderen Karaca
Gülderen Karaca
MEMustafa Nuri Elçioğlu
Mustafa Nuri Elçioğlu

17 June 2026 in Cornea
Verified
Journal Article
Closed access
BABora Deniz Argon
Bora Deniz Argon
ŞDŞule Vildan Durmuş
Şule Vildan Durmuş
Purpose: To compare the accuracy and safety of 4 large language models on cornea and external disease multiple-choice questions (MCQs). Methods: DeepSeek-V3.2, GPT-5.2 (via ChatGPT), Gemini 3 Pro, and Claude Opus 4.5 were tested on American Academy of Ophthalmology (AAO) Ophthalmic News and Education (ONE) Network Cornea/External MCQs (114 text-only) and AAO Basic and Clinical Science Course Cornea/External study questions (38 text-only). Each item was queried once per model using a standardized prompt for the primary analysis. In secondary analyses, each item was requeried 5 times per model in independent sessions. Accuracy was compared using Cochran Q and pairwise exact McNemar tests with Holm adjustment. Potentially harmful wrong answers (HarmfulWrong) were independently coded using a prespecified rubric. Results: In the AAO ONE dataset, accuracy was 65.8% for DeepSeek-V3.2, 93.0% for GPT-5.2, 93.9% for Gemini 3 Pro, and 92.1% for Claude Opus 4.5 (Cochran Q P < 0.001). DeepSeek-V3.2 was significantly less accurate than all other models; the other 3 did not differ significantly. In the Basic and Clinical Science Course dataset, accuracy was 57.9%, 76.3%, 94.7%, and 84.2%, respectively (Cochran Q P < 0.001); DeepSeek-V3.2 was significantly less accurate than Gemini 3 Pro and Claude Opus 4.5. Five-run retesting showed similar ranking but imperfect stability, particularly for DeepSeek-V3.2. HarmfulWrong responses were infrequent, and 2 cornea specialists achieved 98.0% and 97.4% overall accuracy without HarmfulWrong responses. Conclusions: GPT-5.2, Gemini 3 Pro, and Claude Opus 4.5 achieved similarly high accuracy on text-only cornea/external disease MCQs, whereas DeepSeek-V3.2 underperformed. Potentially harmful errors were uncommon but support continued clinician oversight.

27 January 2026 in International Ophthalmology
Verified
Journal Article
Closed access
BABora Deniz Argon
Bora Deniz Argon
ÖAÖzlem Avcı
Özlem Avcı

1 January 2021 in Beyoglu Eye Journal
Verified
Journal Article
Open access
GKGamze Karatas
Gamze Karatas
KAKarata
Karata
BEBurak Erden
Burak Erden
ACAkin Cakir
Akin Cakir
ERErden
Erden
MEMustafa Nuri Elcioglu
Mustafa Nuri Elcioglu
This is a retrospective, comparative evaluation of the short-term efficacy and safety of intravitreal ranibizumab (IVR) and IVR combined with posterior subtenon triamcinolone acetonide (STA) in the treatment of diabetic macular oedema (DME). A total of 79 pseudophakic eyes of 57 patients with DME who underwent IVR injection treatment were examined retrospectively. All of the patients were treatment-naive. In the study group (STA+IVR), consisting of 30 eyes of 39 patients, the STA and IVR were administered in the first treatment session simultaneously, followed by 2 consecutive monthly IVR injections. In the control group (IVR only) comprised 40 eyes of 27 patients, 3 consecutive monthly IVR injections were administered. Patients with serous retinal detachment (SRD) according to optical coherence tomography images were identified in both groups for subgroup analyses. The primary outcome measures were changes in central macular thickness (CMT), best corrected visual acuity (BCVA), and the intraocular pressure (IOP) at 1, 2, and 3 months post-injection. There was no statistically significant difference between the demographic characteristics of the patients' baseline BCVA and CMT measurements (p>0.05). For the IVR group, the mean pre-treatment CMT and BCVA was 421.20±89.10 μm and 0.42±0.24 logMAR, respectively. After the third injection, the mean was 308.12±59.07 μm and 0.20±0.12 logMAR, respectively. The combined treatment group baseline measurements were 454.50±122.52 μm and 0.54±0.29 logMAR, respectively. After the third injection, the mean was 294.22±50.33 μm and 0.27±0.21 logMAR, respectively. The decrease was statistically significant for both groups (p=0.001). Comparison of the CMT within groups revealed a statistically significant difference in favor of the combined group after the second injection (p=0.017). There was no statistically significant difference in the BCVA gains between groups (p>0.05). Patients with SRD were evaluated as a subgroup, and at the first month, the mean gain in CMT was -71.63±57.98 μm in the control group and -123.61±93.46 μm in the study group (p=0.048). The required anti-glaucomatous treatment was statistically significant in the combined group (p=0.008). Both treatments provided improvement in BCVA and CMT and can be considered functional and anatomically effective treatment options for DME.

12 June 2026 in Graefe's Archive for Clinical and Experimental Ophthalmology
Verified
Journal Article
Closed access
BABora Deniz Argon
Bora Deniz Argon
AÇAkın Çakır
Akın Çakır
SÇSezin Doğan Çakır
Sezin Doğan Çakır
FSFidan Safalı
Fidan Safalı
MEMustafa Nuri Elçioğlu
Mustafa Nuri Elçioğlu
MAMine Adaş
Mine Adaş

16 April 2026
Verified
Book
Open access
PDF file
DYDilan Yıldız
Dilan Yıldız
EÇElvin Halili Çelenk
Elvin Halili Çelenk
EÖEmine Betül Akbaş Özyürek
Emine Betül Akbaş Özyürek
TYTuğçe Dursun Yılmazşamlı
Tuğçe Dursun Yılmazşamlı
TUTahsin Uzundede
Tahsin Uzundede
BABora Deniz Argon
Bora Deniz Argon