Buket Erdem

Dr. Buket Erdem

Department of Orthodontics, Istanbul Health and Technology University, Istanbul, İstanbul, Turkey (Türkiye)
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
1 November 2018 in American Journal of Orthodontics and Dentofacial Orthopedics
Verified
Journal Article
Closed access
Buket ErdemBuket Erdem
Buket Erdem
NKNazan Küçükkeleş
Nazan Küçükkeleş

1 November 2020 in Journal of Stomatology Oral and Maxillofacial Surgery
Verified
Journal Article
Closed access
HYHanife Nuray Yilmaz
Hanife Nuray Yilmaz
SHSirin Hatipoglu
Sirin Hatipoglu
Buket ErdemBuket Erdem
Buket Erdem
BCBanu Can
Banu Can
TKTanju Kadir
Tanju Kadir

1 January 2026 in The Angle Orthodontist
Verified
Journal Article
Closed access
Buket ErdemBuket Erdem
Buket Erdem
MÖMustafa Özcan
Mustafa Özcan
ÇŞÇağla Şar
Çağla Şar
Objectives: To evaluate and compare the accuracy of four AI chatbots, ChatGPT-3.5, ChatGPT-4.0, Copilot, and Gemini, in response to orthodontic emergency scenarios. Materials and Methods: Forty frequently asked questions related to orthodontic emergencies were posed to the chatbots. These questions were categorized as fixed orthodontic treatment, clear aligner treatment, eating and oral hygiene, pain and discomfort, general concerns, retention, and sports and travel. The responses were evaluated by three orthodontic experts using a five-point Likert scale, and statistical analysis was conducted to assess variations in accuracy across chatbots. Results: Statistical analysis revealed significant differences among the chatbots. Gemini and ChatGPT-4.0 demonstrated the highest accuracy in response to orthodontic emergencies, followed by Copilot, whereas ChatGPT-3.5 had the lowest accuracy scores. Additionally, the “Fixed Orthodontic Treatment” category showed a statistically significant difference ( P = .043), with Gemini outperforming the other chatbots in this category. However, no statistically significant differences were found in other categories. Conclusions: AI chatbots show potential in providing immediate assistance for orthodontic emergencies, but their accuracy varies across different models and question categories.

25 November 2020 in Journal of Orofacial Orthopedics / Fortschritte der Kieferorthopädie
Verified
Journal Article
Closed access
PDF file
HYHanife Nuray Yilmaz
Hanife Nuray Yilmaz
EAEvin Alakus
Evin Alakus
Buket ErdemBuket Erdem
Buket Erdem
NKNazan Kucukkeles
Nazan Kucukkeles

9 January 2026 in Diagnostics
Verified
Journal Article
Open access
PDF file
NTNazlı TOKATLI
Nazlı TOKATLI
Buket ErdemBuket Erdem
Buket Erdem
MOMustafa Ozcan
Mustafa Ozcan
BMBegum Turan Mavis
Begum Turan Mavis
ÇŞÇaǧla Şar
Çaǧla Şar
FÖFulya Özdemir
Fulya Özdemir
Background/Objectives: The early and accurate identification of impacted teeth in the maxilla is critical for effective dental treatment planning. Traditional diagnostic methods relying on manual interpretation of radiographic images are often time-consuming and subject to variability. Methods: This study presents a deep learning-based approach for automated classification of impacted maxillary canines using panoramic radiographs. A comparative evaluation of four pre-trained convolutional neural network (CNN) architectures—ResNet50, Xception, InceptionV3, and VGG16—was conducted through transfer learning techniques. In this retrospective single-center study, the dataset comprised 694 annotated panoramic radiographs sourced from the archives of a university dental hospital, with a mildly imbalanced representation of impacted and non-impacted cases. Models were assessed using accuracy, precision, recall, specificity, and F1-score. Results: Among the tested architectures, VGG16 demonstrated superior performance, achieving an accuracy of 99.28% and an F1-score of 99.43%. Additionally, a prototype diagnostic interface was developed to demonstrate the potential for clinical application. Conclusions: The findings underscore the potential of deep learning models, particularly VGG16, in enhancing diagnostic workflows; however, further validation on diverse, multi-center datasets is required to confirm clinical generalizability.

8 February 2025 in Seminars in Orthodontics
Verified
Journal Article
Closed access
ÇŞÇağla Şar
Çağla Şar
Buket ErdemBuket Erdem
Buket Erdem
MEMerve Nur Eğlenen
Merve Nur Eğlenen
MKMurat Koçak
Murat Koçak
DGDerya Germeç-Çakan
Derya Germeç-Çakan