European journal of dental education : official journal of the Association for Dental Education in Europe · 2026
A Randomised Study of ChatGPT-4o vs. Written Materials for Teaching Periodontal-Systemic Relationships in Dental Education.
СтатьяНазвание 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.
Keles Mert
Аннотация
INTRODUCTION: The bidirectional relationship between periodontal and systemic diseases (particularly diabetes and cardiovascular diseases) is central to contemporary dental curricula. However, the effectiveness of Large Language Model (LLM) tools compared to traditional written materials remains unclear.
MATERIALS AND METHODS: In this study, 70 fourth-year dental students were divided into two equal groups: Group 1-Learning with written materials (n = 35) and Group 2-Learning supported by ChatGPT-4o (n = 35). Two 20-item tests (Test A pre-test; Test B post-test) developed from international consensus documents were administered to both groups. Prior to implementation, a pilot item analysis was conducted with 35 fifth-year students to assess the appropriateness of the A/B test questions. After the intervention, a 7-item, 5-point Likert questionnaire evaluated student perceptions. The primary outcome was the post-test total knowledge score (Test B), analysed between groups using ANCOVA with the pre-test total score (Test A) as a covariate. Appropriate parametric and nonparametric tests were applied for secondary analyses (α = 0.05).
RESULTS: Both groups showed pre-post improvement in knowledge scores. After adjustment for baseline knowledge using ANCOVA, there was no significant difference between the groups in the primary outcome (Test B total score). According to survey data, Group 2 scored higher in terms of accessibility/ease of information and motivation, while Group 1 reported better concentration/focus (p < 0.05); no significant between-group differences were observed for the other items.
CONCLUSION: ChatGPT-4o-supported interactive learning was comparable to written materials in terms of short-term knowledge acquisition for periodontal-systemic relationships. Both methods offered different advantages: ChatGPT-4o supported increased accessibility and motivation, while written notes supported sustained concentration. A blended approach integrating ChatGPT-4o with traditional resources may be pragmatic for teaching complex interdisciplinary topics.
MATERIALS AND METHODS: In this study, 70 fourth-year dental students were divided into two equal groups: Group 1-Learning with written materials (n = 35) and Group 2-Learning supported by ChatGPT-4o (n = 35). Two 20-item tests (Test A pre-test; Test B post-test) developed from international consensus documents were administered to both groups. Prior to implementation, a pilot item analysis was conducted with 35 fifth-year students to assess the appropriateness of the A/B test questions. After the intervention, a 7-item, 5-point Likert questionnaire evaluated student perceptions. The primary outcome was the post-test total knowledge score (Test B), analysed between groups using ANCOVA with the pre-test total score (Test A) as a covariate. Appropriate parametric and nonparametric tests were applied for secondary analyses (α = 0.05).
RESULTS: Both groups showed pre-post improvement in knowledge scores. After adjustment for baseline knowledge using ANCOVA, there was no significant difference between the groups in the primary outcome (Test B total score). According to survey data, Group 2 scored higher in terms of accessibility/ease of information and motivation, while Group 1 reported better concentration/focus (p < 0.05); no significant between-group differences were observed for the other items.
CONCLUSION: ChatGPT-4o-supported interactive learning was comparable to written materials in terms of short-term knowledge acquisition for periodontal-systemic relationships. Both methods offered different advantages: ChatGPT-4o supported increased accessibility and motivation, while written notes supported sustained concentration. A blended approach integrating ChatGPT-4o with traditional resources may be pragmatic for teaching complex interdisciplinary topics.