Diagnostic pathology · 2026
Virtual assistants based on artificial intelligence for oral diagnosis: help for clinicians AI oral diagnosis helper.
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.
de Araújo Eduarda Gomes Onofre, de Medeiros Carvalho Livian Isabel, de de Souza Breno Estevam Silva, de Santana Ilan Hudson Gomes, Martins Hélder Domiciano Dantas, de Pontes Santos Hellen Bandeira, Mélo Cláudia Batista, Dos Reis Leonardo Amaral, Dias Lívia Máris Ribeiro Paranaíba, Batista Andre Ulisses Dantas, de Lucena Edson Hilan Gomes, Bonan Paulo Rogerio Ferreti
Аннотация
BACKGROUND: Oral cancer is one of the most aggressive malignancies in the head and neck region, with high potential for and a poor prognosis. Despite advancements in diagnostic methods, early detection remains a challenge owing to the lack of specific symptoms in the initial stages and socioeconomic barriers limiting access to health care. Artificial intelligence has emerged as a promising tool for improving diagnostic accuracy in various medical fields, including oral pathology. This study aimed to evaluate the performance of the AI Oral Diagnosis Helper (AODH), developed using ChatGPT™ (versions 4 and 4o), in the diagnosis and management of oral diseases. METHODS: Thirty clinical cases were evaluated by two specialists for oral diagnosis and AODH. Diagnosis and treatment suggestions were compared with those of a gold standard specialist. Agreement and accuracy rates were calculated via Fleiss’ generalized kappa coefficient with a 95% confidence interval via RStudio. RESULTS: AODH via ChatGPT™ 4 (AODH4) correctly identified 22 out of 30 cases (73.3%), whereas AODH via version 4° (AODH4°) correctly identified 24 cases (80%). Expert 1 and Expert 2 correctly diagnosed 27 (90%) and 26 (86.7%) cases, respectively. Fleiss’s kappa indicated substantial reliability among AODHs and experts (K = 0.79). The AODH4 recommended appropriate diagnostic tests in 21 cases (70%), whereas the AODH4o did so in 26 cases (86.7%). For biopsy recommendations, Specialist 1 was accurate in 27 cases (90%), Specialist 2 was accurate in 26 cases (86.7%), AODH4 was accurate in 17 cases (56.7%), and AODH4o was accurate in 26 cases (86.7%). CONCLUSION: AODH demonstrated high diagnostic accuracy comparable to that of human specialists and can assist in oral diagnosis, especially where access to specialists is limited. The performance of AODH4o was superior to that of AODH4. Further research is needed to define the role of AI in enhancing clinical decision-making.