Sürdürülebilir Kalkınma Amaçları
Yayınlar
- MakaleAçık Erişim2026Scopus SJRQ1Multidimensional Evaluation of AI-Generated Patient Information on Cone Beam–Computed Tomography
Öçbe, Melisa; Akçay, Hülya Çerçi; Sır, Eda; Taş, Çağan; Erbalta, Rana
This study aimed to conduct a multidimensional evaluation of artificial intelligence (AI) chatbot–generated patient information regarding cone beam–computed tomography (CBCT) in dentistry, with specific focus on readability, informational quality, reliability, and patient-centered suitability. Twenty frequently asked, patient-oriented questions related to CBCT were systematically identified from a public online forum. Each question was submitted to four large language model–based chatbots (ChatGPT-4o, Gemini Advanced, Claude Sonnet 4, and Microsoft Copilot) under standardized conditions. Generated responses were evaluated using validated instruments, including the DISCERN tool and Global Quality Scale (GQS) for information quality and reliability, as well as Flesch Reading Ease, Flesch–Kincaid Grade Level, and Gunning Fog Index for readability. Patient-centeredness was further assessed using PEMAT-Understandability and PEMAT-Actionability scores. Comparative analyses were performed using linear mixed-effects models. Significant differences were observed among chatbots across all evaluated domains (p < 0.05). While advanced models demonstrated higher informational quality and reliability, their responses frequently exceeded recommended health literacy thresholds. Readability, transparency, and actionability varied substantially between platforms. No chatbot consistently met all criteria for optimal patient-directed communication. AI chatbots can provide generally accurate information on CBCT; however, variability in readability, reliability, and educational suitability limits their standalone use for patient education. Careful integration with professional oversight is essential to ensure safe and accessible AI-supported communication in dentomaxillofacial radiology. This study provides the first multidimensional, comparative evaluation of leading AI chatbots in delivering patient-oriented information about cone beam–computed tomography. It shows critical gaps between informational accuracy and health literacy suitability. This study reveals the need for professional oversight when using AI for patient education in dentomaxillofacial radiology.
- MakaleYalnız künye2026Scopus SJRQ2Evaluating YouTube videos on oral potentially malignant disorders and oral cancer
Akçay, Hülya Çerçi; Kargu, Erdal Cem; Öçbe, Melisa
Background Oral potentially malignant disorders (OPMDs) are abnormalities with an elevated risk of transforming into oral squamous cell carcinoma (OSCC). Despite the visibility of early lesions, OSCC is frequently diagnosed at advanced stages due to low public awareness. YouTube offers potential for oral health education, but the reliability of OPMD-related content remains uncertain. Methods This study systematically assessed the content, reliability, and educational value of 100 English-language YouTube videos on OPMDs and oral cancer. Two independent evaluators analyzed videos using a 6-domain content rubric, JAMA benchmarks, DISCERN, and the Global Quality Scale (GQS). Inter-observer agreement was calculated. Results Of the 100 videos screened, 36 met inclusion criteria. The mean view count was 6,741.9 ± 14,315.5, with limited engagement (interaction index = 1.9 ± 2.3). The highest content scores were observed for Definition and Classification (4.47 ± 0.63) and Diagnostic Approaches (4.07 ± 1.05), while Patient Education ranked lowest (2.57 ± 1.09). Overall video quality was moderate (GQS = 2.94 ± 0.75; DISCERN = 47.29 ± 15.55; JAMA = 2.16 ± 0.67; VIQI = 14.13 ± 2.13). Strong correlations existed among quality indices (ρ = 0.70–0.75, P < .001), but engagement did not correlate with quality. Conclusions OPMD-related YouTube content frequently lacks comprehensive patient education, and credible sources are not always the most viewed. Developing accurate, accessible, and engaging educational videos remains essential.
AtıfScopus2WoS3OpenAlex2
İncele