S. Saeed Mohammadi

Dr. S. Saeed Mohammadi


Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 February 2024 in Ophthalmology Science
Verified
Journal Article
Open access
SMS. Saeed Mohammadi
S. Saeed Mohammadi
QNQuan Dong Nguyen
Quan Dong Nguyen
To assess the capabilities of Chat Generative Pre-trained Transformer (ChatGPT) and Vertex AI in executing code-free preprocessing, training machine learning (ML) models, and analyzing the data. Evaluation of diagnostic test or technology. ChatGPT and Vetrex AI as publicly available large language model and ML platform, respectively. ChatGPT was employed to improve the resolution of fundus photography images from the Methods to Evaluate Segmentation and Indexing Techniques in the field of Retinal Ophthalmology (Messidor-2) open-source dataset using the Contrast Limited Adaptive Histogram Equalization (CLAHE) technique by Fiji software. Subsequently, Vertex AI, an automated ML (AutoML) platform, was utilized to develop 2 classification models. The first model served as a binary classifier for detecting the presence of diabetic retinopathy (DR), while the second determined its severity. Finally, ChatGPT was used to provide scripts for R and Python programming languages for data analysis and was also directly employed in analyzing the data in a code-free method. Evaluating the utility of ChatGPT in generating scripts for preprocessing images using Fiji and analyzing data across Python and R and assessing its potential in analyzing data through a code-free method. Investigating the capabilities of Vertex AI to train image classification models for detection of DR and its severity. Two ML models were trained using 1740 images from the Messidor-2 database. The first model, designed to detect the severity of DR, achieved an area under the precision-recall curve (AUPRC) of 0.81, with a precision rate of 81.81% and recall of 72.83%. The second model, tailored for the detection of the presence of DR, recorded a precision and recall of 84.48% with an AUPRC of 0.90. ChatGPT and Vertex AI have the potential to enable physicians without coding expertise to preprocess images, analyze data, and train ML models. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

1 January 2022 in Middle East African Journal of Ophthalmology
Verified
Journal Article
Open access
MRMohammad T. Rajabi
Mohammad T. Rajabi
KSKianoosh Shahraki
Kianoosh Shahraki
ANAtefeh Nozare
Atefeh Nozare
ZMZahra Moravej
Zahra Moravej
STSepideh Tavakolizadeh
Sepideh Tavakolizadeh
KSKourosh Shahraki
Kourosh Shahraki
PURPOSE: The purpose of the study is to compare the surgical outcomes and success rates of external dacryocystorhinostomy (EX-DCR) versus endoscopic endonasal DCR (EN-DCR) for the treatment of primary acquired nasolacrimal duct obstruction (PANDO). METHODS: This retrospective nonrandomized study was conducted at Farabi Eye Hospital and Noor Eye Hospital, Iran. A review of electronic medical records of all patients with PANDO who underwent EX-DCR or EN-DCR between January 2016 and 2018 was carried out. RESULTS: A total of 803 patients underwent surgery, of which 618 patients (77%) were managed by EX-DCR and 185 patients (23%) by EN-DCR. The majority of cases (62%) were female. The mean age of the patients in EX-DCR and EN-DCR groups was 40.8 ± 14.2 and 34.3 ± 9.2 years, respectively. EX-DCR resulted in significantly less amount of pain compared to EN-DCR (P < 0.05). The success rate of surgery among EX-DCR and EN-DCR groups was 92.4% and 91.1%, respectively, and did not show statistically significant difference. A higher incidence of intraoperative hemorrhage requiring intervention was noted in the EN-DCR group (16.7% vs. 4.5%). Postoperative patient's satisfaction with EN-DCR and EX-DCR was 73% and 82%, respectively. CONCLUSION: Both EX-DXR and endoscopic DCR surgeries have high success rates and low incidence of failure. The choice of DCR technique should be based on the experience of the surgeon and patient's lacrimal and nasal anatomy and preferences.

22 October 2020 in Current Eye Research
Verified
Journal Article
Closed access
GLGolshan Latifi
Golshan Latifi
AAAli Banafshe Afshan
Ali Banafshe Afshan
ABAmir Houshang Beheshtnejad
Amir Houshang Beheshtnejad
MZMehran Zarei-Ghanavati
Mehran Zarei-Ghanavati
NMNeda Mohammadi
Neda Mohammadi
AKAhmad Kheirkhah
Ahmad Kheirkhah
To evaluate corneal subbasal nerve plexus by in vivo confocal microscopy (IVCM) following punctal occlusion in patients with moderate to severe dry eye disease (DED).Patients with grade 3 or 4 seve...

1 October 2017
Verified
Journal Article
Closed access
FHFarideh Hosseinzadeh
Farideh Hosseinzadeh
SMS. Saeed Mohammadi
S. Saeed Mohammadi
FNForoogh Nejatollahi
Foroogh Nejatollahi

30 January 2019 in Journal of Current Ophthalmology
Verified
Journal Article
Open access
MRMohammad Etezad Razavi
Mohammad Etezad Razavi
MRMohammad Taher Rajabi
Mohammad Taher Rajabi
NHNarges Reza Hassanpoor
Narges Reza Hassanpoor
SMS. Saeed Mohammadi
S. Saeed Mohammadi
To assess the efficacy of sclerotherapy with sodium tetradecyl sulfate (STS; Fibrovein 1%) in superficial periocular venous and lymphatic malformations. Eleven patients with low-flow venous and lymphatic malformations with extension predominantly to the eyelids, conjunctiva, and anterior orbit were selected. Sclerotherapy with STS was undertaken as an office-based procedure without any radiological guidance. Injections were repeated every 4 weeks until desired response occurred. Therapeutic effect was assessed objectively by change in the size of the lesions in serial photography. The lesions completely resolved in 4 cases with small eyelid and fornix lesions. In other 7 cases there was partial resolution to less than half of primary size. We did not have any significant complications. Sclerotherapy with STS is an easy and effective modality for treatment of venous-lymphatic malformations and can be undertaken as an office-based procedure in lesions which are limited to eyelids and anterior orbit.

15 September 2020 in Cornea
Verified
Journal Article
Closed access
GLGolshan Latifi
Golshan Latifi
SMS. Saeed Mohammadi
S. Saeed Mohammadi
MDMahmood Davoodabadi
Mahmood Davoodabadi
Purpose: Long-term evaluation of corneal epithelial thickness (ET) profile changes after photorefractive keratectomy (PRK) using Fourier-domain anterior segment optical coherence tomography. Methods: Three hundred twenty-six eyes of 163 patients were included in this prospective observational study. The corneal epithelial map was obtained across a 9-mm diameter area of the cornea before and up to 27 months after surgery. ET was assessed in 25 sectors and 4 annular zones (central 2 mm, paracentral 2–5 mm, midperipheral 5–7 mm, and peripheral 7–9 mm). Results: There was a significant reduction in mean ET in all zones 1 month after PRK. Subsequently, ET increased in all annular zones. The change in mean ET became stable in the midperipheral and peripheral zones at 3 to 6 months and in the central zone at 12 months, and it continued to increase in the paracentral zone even after 18 months after surgery. The ET was 3.40 μm and 4.05 μm in the central and paracentral zones at 6 months, respectively. Postoperative spherical equivalent changed significantly only from 1 to 3 months (P < 0.04). There was a significant correlation between postoperative spherical equivalent at month 1 and ET change in the paracentral and midperipheral zones (P < 0.027). Conclusions: There is a significant reduction in ET 1 month after myopic PRK with a gradual thickening thereafter until it reaches stability at 12 months in the central zone. However, it continues to change even after 18 months in the paracentral zone. The greatest thickening is in the paracentral zone, followed by the central zone.