首页|University Hospital Bern Reports Findings in Artificial Intelligence (Artificial intelligence derived large language model in decisionmaking process in uveitis )
University Hospital Bern Reports Findings in Artificial Intelligence (Artificial intelligence derived large language model in decisionmaking process in uveitis )
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 from Bern, Switzerland , by NewsRx journalists, research stated, “Uveitis is the ophthalmic subfield de aling with a broad range of intraocular inflammatory diseases. With the raising importance of LLM such as ChatGPT and their potential use in the medical field, this research explores the strengths and weaknesses of its applicability in the subfield of uveitis.” The news correspondents obtained a quote from the research from University Hospi tal Bern, “A series of highly clinically relevant questions were asked three con secutive times (attempts 1, 2 and 3) of the LLM regarding current uveitis cases. The answers were classified on whether they were accurate and sufficient, parti ally accurate and sufficient or inaccurate and insufficient. Statistical analysi s included descriptive analysis, normality distribution, non-parametric test and reliability tests. References were checked for their correctness in different m edical databases. The data showed non-normal distribution. Data between subgroup s (attempts 1, 2 and 3) was comparable (Kruskal-Wallis H test, p-value = 0.7338) . There was a moderate agreement between attempt 1 and attempt 2 (Cohen’s kappa, q = 0.5172) as well as between attempt 2 and attempt 3 (Cohen’s kappa, q = 0.49 13). There was a fair agreement between attempt 1 and attempt 3 (Cohen’s kappa, q = 0.3647). The average agreement was moderate (Cohen’s kappa, q = 0.4577). Bet ween the three attempts together, there was a moderate agreement (Fleiss’ kappa, q = 0.4534). A total of 52 references were generated by the LLM. 22 references (42.3%) were found to be accurate and correctly cited. Another 22 r eferences (42.3%) could not be located in any of the searched datab ases. The remaining 8 references (15.4%) were found to exist, but w ere either misinterpreted or incorrectly cited by the LLM. Our results demonstra te the significant potential of LLMs in uveitis. However, their implementation r equires rigorous training and comprehensive testing for specific medical tasks. We also found out that the references made by ChatGPT 4.o were in most cases inc orrect.”
BernSwitzerlandEuropeArtificial In telligenceEmerging TechnologiesEye Diseases and ConditionsHealth and Medic ineMachine LearningOphthalmologyUveal Diseases and ConditionsUveitis
NETL
NSTL
