EÇEmine Dilara Çolpak

Emine Dilara Çolpak

*This is an algorithmically generated author record based on publicly available information.

Emine Dilara Çolpak has a total of 3 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Benchmarking Different Natural Language Processing Models for Their Responses to Queries on Toothsupported Fixed Dental Prostheses in Terms of Accuracy and Consistency

    by Emine Dilara Çolpak, Deniz Yılmaz

    Aim: This study aimed to evaluate the accuracy and repeatability of responses generated by four different software programs regarding tooth-supported fixed dental prostheses. Materials and Method: Twelve open-ended questions in Turkish were created and posed to four different NLPs according to the following models: OpenAI o3 (LRM-O), OpenAI GPT 4.5 (LLM-G), DeepSeek R1 (LRM-R), and DeepSeek V3 (LLM-V) with pre-prompts in the morning, afternoon, and evening. The responses were evaluated with a holistic rubric. For accuracy assessments, the Kruskal–Wallis H test was used. Consistency between the graders’ responses was assessed using the Brennan and Prediger coefficient and the Cohen kappa coefficient. Repeatability was assessed using the Fleiss kappa and Krippendorff alpha coefficients (p < 0.05). Results: There was no statistically significant difference in accuracy between the LRM-O, LLM-G, LRM-R, and LLM-V groups (p = 0.298). The respective accuracies of LRM-O, LLM-G, LRM-R, and LLM-V were 77.7%, 50%, 66.6%, and 77.7%. In addition, the repeatability of LLMs was found to be almost perfect, whereas that of LRMs was substantial. Conclusion: Within the limitations of the study, LRMs and LLMs exhibited similar accuracy. However, the repeatability of LLMs was higher than that of LRMs. Keywords: Artificial intelligence, Dental prostheses, Treatment protocols

  • Chatgpt Vs. Google Gemini: Assessment of Performance Regarding the Accuracy and Repeatability of Responses to Questions in Implant-Supported Prostheses

    by Deniz Yılmaz, Emine Dilara Çolpak

    Purpose: This study aimed to determine the accuracy and repeatability of the responses of different large language models to questions regarding implant-supported prostheses and assess the impact of pre-prompt utilization and the time of day. Materials & Methods: A total of 12 open-ended questions related to implant-supported prostheses were generated and the content validity of the questions was verified by a specialist. Following that, questions were posed to 2 different LLMs: ChatGPT-4.0 and Google Gemini (morning, afternoon, evening; with and without pre-prompt). The responses were evaluated by two expert prosthodontists with a holistic rubric; the concordance between the graders' responses and repeated responses by C and G software programs was calculated with the Brennan and Prediger coefficient, Cohen kappa coefficient, Fleiss kappa, and Krippendorff alpha coefficients. Kruskal-Wallis, Mann-Whitney U, independent t-test, and ANOVA analyses were used to compare the responses obtained in the implementations. Results: The results showed that the accuracy of ChatGPT and Google Gemini was 34.7% and 17.4%, respectively. The implementation of pre-prompt significantly increased accuracy in Gemini (p = 0.026). No significant difference was found according to the time of day (morning, afternoon, evening) or inter-week implementations. In addition, inter-rater reliability and repeatability showed high levels of consistency. Conclusion: The use of pre-prompt positively affected accuracy and repeatability in both ChatGPT and Google Gemini. However, LLMs can still produce hallucinations. Therefore, LLMs may assist clinicians but they should be aware of these limitations. Keywords: Chatbot, ChatGPT, Prostheses and Implant.


  • Open Access

    Renklenme ve Ağartma Prosedürleri Sonrası Farklı Universal Renkli Kompozit Rezinlerin Renk Stabilitesinin Karşılaştırılması

    by Deniz Yılmaz, Hatice Büyüközer Özkan, Emine Dilara Çolpak, Çilem Bulut

    Amaç: Bu çalışmanın amacı iki farklı universal renkli kompozit rezinin kahve solüsyonu ile renklenme miktarının belirlenmesi ve renklenmiş restorasyonlar üzerine % 40’lık H₂O₂ ağartma ajanı uygulanması sonrasındaki renk stabilitesinin belirlenerek bunların kompozit türlerine göre karşılaştırılmasıdır. Gereç ve Yöntemler: Çekilmiş 10 adet çürüksüz büyük azı dişlerinin bukkal ve lingual yüzeylerine 8 mm çapında 2 mm derinliğinde açılan kavitelere selektif asitleme ve universal adeziv kullanılarak Omnichroma (BO) ve Essentia Universal (LE) kompozit rezin materyalleriyle restorasyonları yapılmıştır. Başlangıç, kahve solüsyonunda 1., 6. ve 12. gün renk ölçümleri ve % 40 H₂O₂ ağartma sonrasında CIE L*, a*, b* değerleri spektrofotometre ile ölçülmüştür. CIEDE2000 formüllü kullanılarak ΔE00, ΔL′, ΔC′ ve ΔH′ değerleri hesaplanmıştır. Materyallere göre ΔE00, ΔL′, ΔC′ ve ΔH′ değerlerinin karşılaştırılmasında Mann-Whitney U testi, ΔE00 değerleri üzerinde ΔL′, ΔC′ ve ΔH′ değerlerinin etkisinin belirlenmesinde General Linear Model Variance Components testi kullanılmıştır (p0.05). Ağartma sonrası alınan Ta ölçümlerinde hem BO için hem de LE için ΔH′ etkisiz, ΔL′ ve ΔC′ etkili olmuştur. Sonuçlar: Bu çalışmanın limitasyonları dahilinde, BO ve LE materyallerinin klinik olarak kabul edilemez seviyelerde renklendiği ve ağartma prosedürlerinin her iki materyal üzerinde iyi etkinlik gösterdiği bulunmuştur. Anahtar Kelimeler: Ağartma ajanı, kompozit dental rezin, renk.