Stavroula Antonopoulou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Stavroula Antonopoulou has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Cortino Sukotjo
Department of Prosthodontics, School of Dental Medicine University of Pittsburgh Pittsburgh Pennsylvania USA
6 shared publications - Alvin G. Wee
Department of Restorative Dentistry University of Washington School of Dentistry Seattle Washington USA
3 shared publications - Amanda Colebeck
Attending and Program Director, Department of Dentistry, Division of Oral Oncology and Maxillofacial Prosthetics, Erie County Medical Center, Buffalo, NY
3 shared publications Maribeth Krzesinski
Clinical Assistant Professor Prosthodontics, Department of Prosthodontics, School of Dental Medicine, University of Pittsburgh, Pittsburgh, PA
3 shared publicationsMerve Koseoglu
Associate Professor, Department of Prosthodontics, Faculty of Dentistry, University of Sakarya, Sakarya, Turkey
3 shared publicationsSoni Prasad
Adams School of Dentistry University of North Carolina Chappel Hill North Carolina USA
3 shared publications
Latest Publications
- 7 July 2026
- Published by Elsevier in The Journal of Prosthetic Dentistry
- Vol. 136 (4) , e145-e146
Response to the Letter to the Editor, “Comment on 'Readability and performance of AI chatbot responses to frequently asked questions in maxillofacial prosthodontics'”
- 7 July 2026
- Published by Elsevier in The Journal of Prosthetic Dentistry
- Vol. 136 (4) , e145-e146
Response to the Letter to the Editor, “Comment on 'Readability and performance of AI chatbot responses to frequently asked questions in maxillofacial prosthodontics'”
- Open Access
- 14 April 2026
- Published by Wiley in Journal of Prosthodontics
Assessing the ability of large language models to summarize and generate maxillofacial prosthetic treatment options
Purpose: The aim was to evaluate the ability of four large language models (LLMs) (OpenAI's ChatGPT‐3.5, Microsoft 365 Copilot, DeepSeek‐R1, and Google Gemini 2.5 Pro) to develop treatment options when presented with clinical cases published in the maxillofacial prosthodontics literature. Materials and Methods: Six maxillofacial case reports were fed to the LLMs following a prompt that requested prosthodontic treatment options from the perspective of a prosthodontist. Expert evaluators scored the relevance, clarity, depth, focus, and coherence of the responses. Statistical analyses, including descriptive statistics, two‐way analysis of variance (ANOVA), post hoc Tukey tests, Pearson correlation analyses, and intraclass correlation coefficients (ICCs), were performed ( α < 0.05). Results: There were significant differences among the total mean relevance ( p = 0.003), clarity ( p = 0.006), depth ( p < 0.001), focus ( p < 0.001), and coherence ( p < 0.001) scores of chatbots. Copilot consistently scored the lowest, and Gemini or DeepSeek scored the highest for all five factors. Depth ( p = 0.006), focus ( p = 0.024), and coherence ( p = 0.013) scores of senior prosthodontists were slightly higher than those of junior prosthodontists. Pearson correlation analysis revealed positive correlations between the total mean scores for all five factors ( p < 0.001). Conclusions: The study demonstrates the ability of LLMs to develop maxillofacial prosthetic treatment plans tailored to specific clinical scenarios. There were significant differences between the abilities of the LLMs evaluated in this study. Copilot scored the lowest for all factors evaluated, and Gemini and/or DeepSeek scored the highest.
- 14 April 2026
- Published by Wiley in Journal of Prosthodontics
Open AccessAssessing the ability of large language models to summarize and generate maxillofacial prosthetic treatment options
Purpose: The aim was to evaluate the ability of four large language models (LLMs) (OpenAI's ChatGPT‐3.5, Microsoft 365 Copilot, DeepSeek‐R1, and Google Gemini 2.5 Pro) to develop treatment options when presented with clinical cases published in the maxillofacial prosthodontics literature. Materials and Methods: Six maxillofacial case reports were fed to the LLMs following a prompt that requested prosthodontic treatment options from the perspective of a prosthodontist. Expert evaluators scored the relevance, clarity, depth, focus, and coherence of the responses. Statistical analyses, including descriptive statistics, two‐way analysis of variance (ANOVA), post hoc Tukey tests, Pearson correlation analyses, and intraclass correlation coefficients (ICCs), were performed ( α < 0.05). Results: There were significant differences among the total mean relevance ( p = 0.003), clarity ( p = 0.006), depth ( p < 0.001), focus ( p < 0.001), and coherence ( p < 0.001) scores of chatbots. Copilot consistently scored the lowest, and Gemini or DeepSeek scored the highest for all five factors. Depth ( p = 0.006), focus ( p = 0.024), and coherence ( p = 0.013) scores of senior prosthodontists were slightly higher than those of junior prosthodontists. Pearson correlation analysis revealed positive correlations between the total mean scores for all five factors ( p < 0.001). Conclusions: The study demonstrates the ability of LLMs to develop maxillofacial prosthetic treatment plans tailored to specific clinical scenarios. There were significant differences between the abilities of the LLMs evaluated in this study. Copilot scored the lowest for all factors evaluated, and Gemini and/or DeepSeek scored the highest.
- 10 December 2025
- Published by Wiley in Journal of Prosthodontics
- Vol. 35 (1) , 6-7
Response to the letter to the editor: “Beyond readability scores: Reconsidering the evaluation of large language models in prosthodontic patient education”
- 10 December 2025
- Published by Wiley in Journal of Prosthodontics
- Vol. 35 (1) , 6-7
Response to the letter to the editor: “Beyond readability scores: Reconsidering the evaluation of large language models in prosthodontic patient education”
- Open Access
- 27 September 2025
- Published by Elsevier in The Journal of Prosthetic Dentistry
- Vol. 135 (1) , 195.e1-195.e9
Readability and performance of AI chatbot responses to frequently asked questions in maxillofacial prosthodontics
- 27 September 2025
- Published by Elsevier in The Journal of Prosthetic Dentistry
- Vol. 135 (1) , 195.e1-195.e9
Open AccessReadability and performance of AI chatbot responses to frequently asked questions in maxillofacial prosthodontics
- Open Access
- 22 August 2025
- Published by Wiley in Journal of Prosthodontics
Assessing readability and accuracy of content produced by the American College of Prosthodontists and large language models for patient education in prosthodontics
Purpose: This study aims to evaluate the readability and accuracy of content produced by ChatGPT, Copilot, Gemini, and the American College of Prosthodontists (ACP) for patient education in prosthodontics.Materials and Methods: A series of 26 questions were selected from the ACP's list of questions (GoToAPro.org FAQs) and their published answers. Answers to the same questions were generated from ChatGPT‐3.5, Copilot, and Gemini. The word counts of responses from chatbots and the ACP were recorded. The readability was calculated using the Flesch Reading Ease Scale and Flesch–Kincaid Grade Level. The responses were also evaluated for accuracy, completeness, and overall quality. Descriptive statistics were used to calculate mean and standard deviations (SD). One‐way analysis of variance was performed, followed by the Tukey multiple comparisons to test differences across chatbots, ACP, and various selected topics. The Pearson correlation coefficient was used to examine the relationship between each variable. Significance was set at α < 0.05.Results: ChatGPT had a higher word count, while ACP had a lower word count (p < 0.001). The cumulative scores of the prosthodontist topic had the lowest Flesch Reading Ease Scale score, while brushing and flossing topics displayed the highest score (p < 0.001). Brushing and flossing topics also had the lowest Flesch–Kincaid Grade Level score, whereas the prosthodontist topic had the highest score (p < 0.001). Accuracy for denture topics was the lowest across the chatbots and ACP, and it was the highest for brushing and flossing topics (p = 0.006).Conclusions: This study highlights the potential for large language models to enhance patient's prosthodontic education. However, the variability in readability and accuracy across platforms underscores the need for dental professionals to critically evaluate the content generated by these tools before recommending them to patients.
- 22 August 2025
- Published by Wiley in Journal of Prosthodontics
Open AccessAssessing readability and accuracy of content produced by the American College of Prosthodontists and large language models for patient education in prosthodontics
Purpose: This study aims to evaluate the readability and accuracy of content produced by ChatGPT, Copilot, Gemini, and the American College of Prosthodontists (ACP) for patient education in prosthodontics.Materials and Methods: A series of 26 questions were selected from the ACP's list of questions (GoToAPro.org FAQs) and their published answers. Answers to the same questions were generated from ChatGPT‐3.5, Copilot, and Gemini. The word counts of responses from chatbots and the ACP were recorded. The readability was calculated using the Flesch Reading Ease Scale and Flesch–Kincaid Grade Level. The responses were also evaluated for accuracy, completeness, and overall quality. Descriptive statistics were used to calculate mean and standard deviations (SD). One‐way analysis of variance was performed, followed by the Tukey multiple comparisons to test differences across chatbots, ACP, and various selected topics. The Pearson correlation coefficient was used to examine the relationship between each variable. Significance was set at α < 0.05.Results: ChatGPT had a higher word count, while ACP had a lower word count (p < 0.001). The cumulative scores of the prosthodontist topic had the lowest Flesch Reading Ease Scale score, while brushing and flossing topics displayed the highest score (p < 0.001). Brushing and flossing topics also had the lowest Flesch–Kincaid Grade Level score, whereas the prosthodontist topic had the highest score (p < 0.001). Accuracy for denture topics was the lowest across the chatbots and ACP, and it was the highest for brushing and flossing topics (p = 0.006).Conclusions: This study highlights the potential for large language models to enhance patient's prosthodontic education. However, the variability in readability and accuracy across platforms underscores the need for dental professionals to critically evaluate the content generated by these tools before recommending them to patients.
- Open Access
- 8 May 2025
- Published by MDPI AG in Prosthesis
- Vol. 7 (3) , 47
The Effect of Extrinsic Staining on 3D Printed Provisional Crowns
Purpose: The aim of this study was to evaluate the color stability of 3D printed resin disks using spectral reflectance data obtained at different time periods after immersion in various staining solutions. The color stability of 3D-printed temporary crowns is clinically important, as it directly affects the esthetic outcome and patient satisfaction during the provisional phase of treatment. Materials and methods: Forty identical round disk specimens measuring 10 mm in diameter and 2 mm in thickness were fabricated using CAD/CAM 3D printing resin (shade B1). Half of the specimens (n = 20) were polished using an acrylic bur and medium pumice. The remaining specimens were unpolished (n = 20). Each group of disks was then immersed in one of the following immersion solutions: artificial saliva, black tea, carrot juice, and red wine. Color difference ΔE was evaluated using the spectrophotometer, a spectral reflectance instrument, at baseline, day 1, week 1, week 2 and week 3, against a white background. Comparisons between polished and unpolished disks at each time point were conducted using Mann–Whitney tests. Differences among the staining solutions at each time point for both polished and unpolished disks were analyzed using a one-way ANOVA with Tukey’s post hoc test. Results: Color difference ΔE was measured using the CIELAB formula. The mean ΔE values of each group were calculated. The greatest difference in color was observed in the unpolished and polished disks immersed in red wine. Polished disks showed less color difference when compared to unpolished disks. Significant differences in ΔE were detected between polished and unpolished disks immersed in red wine at week 1 (p = 0.0159), week 2 (p = 0.0079) and week 3 (p = 0.0079) and in carrot juice at week 3 (p = 0.0317). Conclusions: Immersion of 3D printed disks in different staining solutions caused detectable color difference in the tested materials, which was relative to the immersion duration and the staining solution used. The color of the 3D printed resins is influenced by the surface finishing, which may result in visually perceptible color differences. The color stability of 3D printied materials should be improved to provide long-term esthetics.
- 8 May 2025
- Published by MDPI AG in Prosthesis
- Vol. 7 (3) , 47
Open AccessThe Effect of Extrinsic Staining on 3D Printed Provisional Crowns
Purpose: The aim of this study was to evaluate the color stability of 3D printed resin disks using spectral reflectance data obtained at different time periods after immersion in various staining solutions. The color stability of 3D-printed temporary crowns is clinically important, as it directly affects the esthetic outcome and patient satisfaction during the provisional phase of treatment. Materials and methods: Forty identical round disk specimens measuring 10 mm in diameter and 2 mm in thickness were fabricated using CAD/CAM 3D printing resin (shade B1). Half of the specimens (n = 20) were polished using an acrylic bur and medium pumice. The remaining specimens were unpolished (n = 20). Each group of disks was then immersed in one of the following immersion solutions: artificial saliva, black tea, carrot juice, and red wine. Color difference ΔE was evaluated using the spectrophotometer, a spectral reflectance instrument, at baseline, day 1, week 1, week 2 and week 3, against a white background. Comparisons between polished and unpolished disks at each time point were conducted using Mann–Whitney tests. Differences among the staining solutions at each time point for both polished and unpolished disks were analyzed using a one-way ANOVA with Tukey’s post hoc test. Results: Color difference ΔE was measured using the CIELAB formula. The mean ΔE values of each group were calculated. The greatest difference in color was observed in the unpolished and polished disks immersed in red wine. Polished disks showed less color difference when compared to unpolished disks. Significant differences in ΔE were detected between polished and unpolished disks immersed in red wine at week 1 (p = 0.0159), week 2 (p = 0.0079) and week 3 (p = 0.0079) and in carrot juice at week 3 (p = 0.0317). Conclusions: Immersion of 3D printed disks in different staining solutions caused detectable color difference in the tested materials, which was relative to the immersion duration and the staining solution used. The color of the 3D printed resins is influenced by the surface finishing, which may result in visually perceptible color differences. The color stability of 3D printied materials should be improved to provide long-term esthetics.