首页|School of Dentistry Reports Findings in Artificial Intelligence (PAINe - An Arti ficial Intelligence Based Virtual Assistant to Aid in the Differentiation of Pai n of Odontogenic versus Temporomandibular Origin)
School of Dentistry Reports Findings in Artificial Intelligence (PAINe - An Arti ficial Intelligence Based Virtual Assistant to Aid in the Differentiation of Pai n of Odontogenic versus Temporomandibular Origin)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Artificial Intelligenc e is the subject of a report. According to news reporting out of Curitiba, Brazi l, by NewsRx editors, research stated, “Pain associated with temporomandibular d ysfunction (TMD) is often confused with odontogenic pain, which is a challenge i n endodontic diagnosis. Validated screening questionnaires can aid the identific ation and differentiation of the source of pain.” Our news journalists obtained a quote from the research from the School of Denti stry, “Therefore, this study aimed to develop a virtual assistant based on artif icial intelligence, using natural language processing techniques to automate the initial screening of patients with tooth pain. The PAINe chatbot was developed in Python language, using the PyCharm environment and the ‘openai’ library to in tegrate the ChatGPT 4 API, and the ‘streamlit’ library for interface constructio n. The validated TMD Pain Screener questionnaire and one question about the curr ent pain intensity was integrated into the chatbot to perform the differential d iagnosis of TMD in patients with tooth pain. The responses’ accuracy was evaluat ed in 50 random scenarios to compare the chatbot with the validated questionnair e. The Kappa coefficient was calculated to assess the agreement level between th e chatbot responses and the validated questionnaire. The chatbot achieved an acc uracy rate of 86% and a substantial level of agreement (Kappa = 0. 70). Most responses were clear and provided adequate information about the diagn osis. The implementation of a virtual assistant using natural language processin g, based on large language models, for initial differential diagnosis screening of patients with tooth pain, demonstrated substantial agreement between validate d questionnaires and the chatbot.”
CuritibaBrazilSouth AmericaArtific ial IntelligenceDentistryDiagnostics and ScreeningEmerging TechnologiesH ealth and MedicineMachine LearningNatural Language ProcessingTooth Pain
NETL
NSTL
