BMC oral health · 2026
Evaluation of the approaches of different specialties and artificial intelligence systems on traumatic dental injuries.
СтатьяСравнительное исследованиеНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Şahin Gonca Zelal, Eymirli Ayhan
Аннотация
AIM: This study aimed to evaluate and compare the knowledge of three artificial intelligence (AI) systems and three dental specialist groups regarding the management of traumatic dental injuries (TDIs).
METHODOLOGY: An online survey consisting of three sections was administered: (1) an information sheet with electronic informed consent, (2) five sociodemographic questions, and (3) thirty multiple-choice questions assessing TDI knowledge based on the International Association of Dental Traumatology (IADT) guidelines and current literature. The survey was distributed via e-mail to specialists in endodontics, pediatric dentistry, and oral and maxillofacial surgery through the Turkish Dental Association database. For the AI systems (ChatGPT-4o, Gemini Advanced, and DeepSeek-V3), the 30-item questionnaire was administered under a standardized prompt three times per day over 10 consecutive days, and all responses were recorded. Internal consistency and reliability were assessed using Cronbach's alpha and intraclass correlation coefficients (ICC). Statistical analyses were performed using one-way ANOVA and independent-samples t-tests (p < 0.05).
RESULTS: A total of 95 specialists participated in the study (64 females, 31 males). Female participants demonstrated significantly higher correct-response rates than males. Participants classified as having very good knowledge achieved significantly higher scores than those with acceptable or low knowledge levels. No statistically significant differences were observed according to professional experience or workplace setting. Significant differences were found among specialist groups, with pediatric dentistry specialists achieving the highest correct-response rate. The overall mean accuracy among all specialists was 70.98% (SD = 15.6). AI systems performed as follows: ChatGPT-4o, 86% (SD = 3.2); Gemini Advanced, 79.33% (SD = 3.75); and DeepSeek-V3, 72.67% (SD = 4.32).
CONCLUSIONS: AI systems demonstrated higher overall accuracy than human participants; however, certain items resulted in misleading responses, highlighting the importance of case-specific interpretation. AI tools may serve as supportive adjuncts in clinical decision-making, but further rigorously designed studies are required to clarify their optimal role and limitations in TDI management.
METHODOLOGY: An online survey consisting of three sections was administered: (1) an information sheet with electronic informed consent, (2) five sociodemographic questions, and (3) thirty multiple-choice questions assessing TDI knowledge based on the International Association of Dental Traumatology (IADT) guidelines and current literature. The survey was distributed via e-mail to specialists in endodontics, pediatric dentistry, and oral and maxillofacial surgery through the Turkish Dental Association database. For the AI systems (ChatGPT-4o, Gemini Advanced, and DeepSeek-V3), the 30-item questionnaire was administered under a standardized prompt three times per day over 10 consecutive days, and all responses were recorded. Internal consistency and reliability were assessed using Cronbach's alpha and intraclass correlation coefficients (ICC). Statistical analyses were performed using one-way ANOVA and independent-samples t-tests (p < 0.05).
RESULTS: A total of 95 specialists participated in the study (64 females, 31 males). Female participants demonstrated significantly higher correct-response rates than males. Participants classified as having very good knowledge achieved significantly higher scores than those with acceptable or low knowledge levels. No statistically significant differences were observed according to professional experience or workplace setting. Significant differences were found among specialist groups, with pediatric dentistry specialists achieving the highest correct-response rate. The overall mean accuracy among all specialists was 70.98% (SD = 15.6). AI systems performed as follows: ChatGPT-4o, 86% (SD = 3.2); Gemini Advanced, 79.33% (SD = 3.75); and DeepSeek-V3, 72.67% (SD = 4.32).
CONCLUSIONS: AI systems demonstrated higher overall accuracy than human participants; however, certain items resulted in misleading responses, highlighting the importance of case-specific interpretation. AI tools may serve as supportive adjuncts in clinical decision-making, but further rigorously designed studies are required to clarify their optimal role and limitations in TDI management.