ERDEM OZKAN

Dr. ERDEM OZKAN

Radiology, Kastamonu Training and Research Hospital, Kastamonu, Turkey (Türkiye)
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications

1 January 2024 in Revista da Associação Médica Brasileira
Verified
Journal Article
Open access
PDF file
MYMerve Yazla
Merve Yazla
BKBurcu Kadıoğlu
Burcu Kadıoğlu
HDHacer Demirdelen
Hacer Demirdelen
FAFatih Mehmet Aksoy
Fatih Mehmet Aksoy
EOERDEM OZKAN
ERDEM OZKAN
BKBurak Katipoglu
Burak Katipoglu
OBJECTIVE: Acute appendicitis is the most common cause of acute abdomen. It is important to differentiate between complicated and uncomplicated appendicitis before surgery in the emergency department. Recently, immature granulocytes have become one of the biomarkers used as predictors of inflammation. The aim of this study was to determine whether immature granulocyte levels are a biomarker that can predict whether acute appendicitis is complicated or not in patients admitted to the emergency department.

7 June 2022 in BMC Medical Imaging
Verified
Journal Article
Open access
PDF file
MGMutlu Gülbay
Mutlu Gülbay
ABAliye Bastug
Aliye Bastug
EOERDEM OZKAN
ERDEM OZKAN
BÖBüşra Yüce Öztürk
Büşra Yüce Öztürk
BMBökebatur Ahmet Raşit Mendi
Bökebatur Ahmet Raşit Mendi
HBHürrem Bodur
Hürrem Bodur
Background: The aim of the study was to predict the probability of intensive care unit (ICU) care for inpatient COVID-19 cases using clinical and artificial intelligence segmentation-based volumetric and CT-radiomics parameters on admission. Methods: Twenty-eight clinical/laboratory features, 21 volumetric parameters, and 74 radiomics parameters obtained by deep learning (DL)-based segmentations from CT examinations of 191 severe COVID-19 inpatients admitted between March 2020 and March 2021 were collected. Patients were divided into Group 1 (117 patients discharged from the inpatient service) and Group 2 (74 patients transferred to the ICU), and the differences between the groups were evaluated with the T-test and Mann–Whitney test. The sensitivities and specificities of significantly different parameters were evaluated by ROC analysis. Subsequently, 152 (79.5%) patients were assigned to the training/cross-validation set, and 39 (20.5%) patients were assigned to the test set. Clinical, radiological, and combined logit-fit models were generated by using the Bayesian information criterion from the training set and optimized via tenfold cross-validation. To simultaneously use all of the clinical, volumetric, and radiomics parameters, a random forest model was produced, and this model was trained by using a balanced training set created by adding synthetic data to the existing training/cross-validation set. The results of the models in predicting ICU patients were evaluated with the test set. Results: No parameter individually created a reliable classifier. When the test set was evaluated with the final models, the AUC values were 0.736, 0.708, and 0.794, the specificity values were 79.17%, 79.17%, and 87.50%, the sensitivity values were 66.67%, 60%, and 73.33%, and the F1 values were 0.67, 0.62, and 0.76 for the clinical, radiological, and combined logit-fit models, respectively. The random forest model that was trained with the balanced training/cross-validation set was the most successful model, achieving an AUC of 0.837, specificity of 87.50%, sensitivity of 80%, and F1 value of 0.80 in the test set. Conclusion: By using a machine learning algorithm that was composed of clinical and DL-segmentation-based radiological parameters and that was trained with a balanced data set, COVID-19 patients who may require intensive care could be successfully predicted.

24 January 2023 in Balkan Medical Journal
Verified
Journal Article
Open access
EEEda Elverici
Eda Elverici
AÖArzu Özsoy
Arzu Özsoy
BSBige Sayın
Bige Sayın
MGMuhammet Batuhan Gökhan
Muhammet Batuhan Gökhan
EOERDEM OZKAN
ERDEM OZKAN
Currently, unilateral clinical and subclinical axillary adenopathy cases associated with the Pfizer-BioNTech and Moderna vaccines are increasingly reported. However, only one study on axillary adenopathy due to the CoronaVac vaccine is published. To present the incidence, severity, and ultrasonographic findings of axillary adenopathy that developed in healthcare professionals in Turkey after they were vaccinated with CoronaVac against coronavirus disease-19. A prospective study. In Turkey, the first dose of the CoronaVac vaccine for coronavirus disease-19 was administered to healthcare professionals on January 14, 2021, and the second dose on February 11, 2021. This study covered the period from January 21, 2021 (1 week after the first dose), and April 15, 2021 (9 weeks after the second dose). Individuals who had a history of COVID-19 more than 3 weeks after vaccine doses, systemic disease, and diagnosis and treatment history of breast cancer were excluded. The axillary lymph nodes of the vaccinated and contralateral arms were evaluated in 101 volunteer healthcare professionals using axillary ultrasonography. A significant difference was found in the cortical thicknesses of the lymph nodes between the vaccinated and contralateral axilla after both the first (*p < 0.01) and second (*p < 0.01) doses. Accordingly, the rates of subclinical lymphatic hyperplasia on the vaccinated side were 25.7% (n = 26/101) after the first and 31.1% (n = 28/90) after the second dose. Lymph nodes with pathological appearance based on a reduced echogenic hilum with marked cortical thickening were found only in 2.2%. Among the 39 cases in which antibodies (immunoglobulin G and immunoglobulin M) were measured, the antibody level was classified as <10 and ≥10. No statistically significant difference was found in the cortical thickness of the axillary lymph nodes between patients with high antibody levels (≥10) and those with low antibody levels (<10) (p > 0.05). In this study, clinical signs of axillary lymph node hyperplasia were not detected after vaccination with CoronaVac. Mild and diffuse thickening of the CoronaVac vaccine-induced lymph nodes was more common than pathological and palpable lymph nodes.

5 February 2026 in Diagnostics
Verified
Journal Article
Open access
PDF file
EOERDEM OZKAN
ERDEM OZKAN
MKMustafa Koyun
Mustafa Koyun
Background/Objectives: Bone age assessment is critical in pediatric endocrinology and forensic medicine. Although recently developed multimodal large language models (LLMs) show potential in medical imaging, their diagnostic performance in bone age determination has not been sufficiently evaluated. This study evaluates the performance of four multimodal LLMs (ChatGPT-5, Gemini 2.5 Pro, Grok-3, and Claude 4 Sonnet) in bone age determination using the Gilsanz–Ratib (GR) atlas. Methods: This retrospective study included 245 pediatric patients (109 male, 136 female) under the age of 18 who underwent left wrist radiography. Each model estimated bone age using the patient’s radiograph and GR atlas as reference (atlas-assisted prompting). Bone age assessments made by an experienced radiologist using the GR atlas were evaluated as the reference standard. Performance was assessed using mean absolute error (MAE), intraclass correlation coefficient (ICC), and Bland–Altman analysis. Results: ChatGPT-5 demonstrated statistically superior performance, with an MAE of 1.46 years and ICC of 0.849, showing the highest alignment with the reference standard. Gemini 2.5 Pro showed moderate performance, with an MAE of 2.24 years; Grok-3 (MAE: 3.14 years) and Claude 4 Sonnet (MAE: 4.29 years) had error rates that were too high for clinical use. Conclusions: Significant performance differences exist among multimodal LLMs, despite atlas-supported prompting. Only ChatGPT-5 qualified as “clinically useful,” demonstrating potential as an auxiliary tool or educational support under expert supervision. Other models’ reliability remains insufficient.

13 August 2025 in Radiology: Artificial Intelligence
Verified
Journal Article
Closed access
UKURAL KOC
URAL KOC
MBMuhammed Said Beşler
Muhammed Said Beşler
ESEbru Akçapınar Sezer
Ebru Akçapınar Sezer
EKEmrah Karakaş
Emrah Karakaş
YÖYaşar Alper Özkaya
Yaşar Alper Özkaya
ŞBŞuayip Birinci
Şuayip Birinci
“Just Accepted” papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. The MammosighTR dataset, derived from Türkiye's national breast cancer screening mammography program, provides BI-RADS-labeled mammograms with detailed annotations on breast composition and lesion quadrant location, which may be useful for developing and testing AI models in breast cancer detection. ©RSNA, 2025