首页|University of Health Sciences Reports Findings in Artificial Intelligence (The e fficacy of artificial intelligence in urology: a detailed analysis of kidney sto ne-related queries)
University of Health Sciences Reports Findings in Artificial Intelligence (The e fficacy of artificial intelligence in urology: a detailed analysis of kidney sto ne-related queries)
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 originating in Istanbu l, Turkey, by NewsRx journalists, research stated, "The study aimed to assess th e efficacy of OpenAI's advanced AI model, ChatGPT, in diagnosing urological cond itions, focusing on kidney stones. A set of 90 structured questions, compliant w ith EAU Guidelines 2023, was curated by seasoned urologists for this investigati on." Financial support for this research came from University of Health Sciences. The news reporters obtained a quote from the research from the University of Hea lth Sciences, "We evaluated ChatGPT's performance based on the accuracy and comp leteness of its responses to two types of questions [binary ( true/false) and descriptive (multiple-choice)], stratified in to difficulty levels: easy, moderate, and complex. Furthermore, we analyzed the model's learning and adaptability capacity by reassessing the initially incorrec t responses after a 2 week interval. The model demonstrated commendable accuracy , correctly answering 80% of binary questions (n:45) and 93.3% of descriptive questions (n:45). The model's performance showed no significant v ariation across different question difficulty levels, with p-values of 0.548 for accuracy and 0.417 for completeness, respectively. Upon reassessment of initial ly 12 incorrect responses (9 binary to 3 descriptive) after two weeks, ChatGPT's accuracy showed substantial improvement. The mean accuracy score significantly increased from 1.58 ? 0.51 to 2.83 ? 0.93 (p = 0.004), underlining the model's a bility to learn and adapt over time. These findings highlight the potential of C hatGPT in urological diagnostics, but also underscore areas requiring enhancemen t, especially in the completeness of responses to complex queries."
IstanbulTurkeyEurasiaArtificial In telligenceEmerging TechnologiesHealth and MedicineMachine LearningUrolog y
NETL
NSTL
