支持清晰写作和检测瘤学随机对照试验中的旋转的大型语言模型:对GPT模型和提示的比较分析
Carole Koechli1,2, Fabio Dennstädt2, Christina Schröder1,2
1Department of Radiation Oncology, Kantonsspital Winterthur, Brauerstrasse 15, Winterthur, Switzerland, 41 52 266 26 53.
JMIR cancer
|January 21, 2026
概括
大型语言模型 (LLM) 可以检测瘤学随机对照试验 (RCT) 中的报告旋转. 通过将结论与完整摘要进行比较,LLM有助于识别误导性的疗效陈述,提高科学透明度.
科学领域:
- 在瘤学瘤学.
- 医疗信息学 医疗信息学
- 科学出版科学出版
背景情况:
- 随机对照试验 (RCT) 对于瘤学干预评估至关重要.
- 在RCT中报告"旋转"可能会误导读者关于真正的疗效,特别是在结论中.
研究的目的:
- 调查大语言模型 (LLM) 在瘤学RCT报告中检测旋转的能力.
- 评估LLM在识别旋转方面的表现,特别是在结论部分.
主要方法:
- 从主要医学期刊中随机抽取250个瘤学RCT.
- 三个商业LLM使用不同的文本输入 (结论仅限于完整摘要) 将试验分类为正/负.
- 用准确性,精确性,回忆力和F1分数对人类注释进行LLM绩效评估.
主要成果:
- 在所有输入条件中,GPT-o1模型实现了高F1得分,在提供方法,结果和结论时最高为0.98.
- 对错误分类的试验的分析揭示了旋转的标志性模式,例如缺少主终点结果或强调子组分析.
- 这些旋转模式在正确分类的负试验中很少存在.
结论:
- 通过识别结论和完整摘要之间的差异,LLM可以有效地检测瘤学RCT报告中的潜在旋转.
- 这种基于LLM的方法可以作为一个补充工具来提高科学报告的透明度.
- 需要进一步开发以解决更复杂的试验设计.
相关概念视频
Comparing the Survival Analysis of Two or More Groups
573
Survival analysis is a cornerstone of medical research, used to evaluate the time until an event of interest occurs, such as death, disease recurrence, or recovery. Unlike standard statistical methods, survival analysis is particularly adept at handling censored data—instances where the event has not occurred for some participants by the end of the study or remains unobserved. To address these unique challenges, specialized techniques like the Kaplan-Meier estimator, log-rank test, and...
573
Language
894
Language is a unique communication system that uses words and systematic rules to organize and transmit information. Unlike other forms of communication, which may involve postures, movements, odors, or vocalizations, language relies on symbols and grammar. This makes human communication distinct from that of other species, who also communicate but do not use language in the same way humans do.
Corballis and Suddendorf (2007) and Tomasello and Rakoczy (2003) highlight the role of language in...
Corballis and Suddendorf (2007) and Tomasello and Rakoczy (2003) highlight the role of language in...
894
Statistical Software for Data Analysis and Clinical Trials
1.4K
Statistical software is pivotal in data analysis and clinical trials by providing tools to analyze data, draw conclusions, and make predictions. These software packages range from simple data management applications to complex analytical platforms, supporting various statistical tests, models, and simulation techniques. Their significance lies in their ability to handle vast amounts of data with precision and efficiency, enabling researchers to validate hypotheses, identify trends, and make...
1.4K
Mechanistic Models: Compartment Models in Individual and Population Analysis
254
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
254
Guidelines for Writing Outcome
3.7K
When developing expected outcomes for a patient care plan, the nurse should adhere to the following recommendations:
Patient outcomes reflect the patient's response to the goal rather than what the nurse aims to achieve. Terminology should be observable and measurable to avoid the reader's interpretation. The desired outcome should be realistic and achievable in the designated care timeframe. Expected outcomes should align with adjunctive therapies. The outcome should enhance care...
Patient outcomes reflect the patient's response to the goal rather than what the nurse aims to achieve. Terminology should be observable and measurable to avoid the reader's interpretation. The desired outcome should be realistic and achievable in the designated care timeframe. Expected outcomes should align with adjunctive therapies. The outcome should enhance care...
3.7K
Spin–Spin Coupling Constant: Overview
1.5K
In bromoethane, the three methyl protons are coupled to the two methylene protons that are three bonds away. In accordance with the n+1 rule, the signal from the methyl protons is split into three peaks with 1:2:1 relative intensities. The methylene protons appear as a quartet, with the relative intensities of 1:3:3:1.
Qualitatively, any spin plus-half nucleus polarizes the spins of its electrons to the minus-half state. Consequently, the paired electron in the hydrogen–carbon bond must...
Qualitatively, any spin plus-half nucleus polarizes the spins of its electrons to the minus-half state. Consequently, the paired electron in the hydrogen–carbon bond must...
1.5K


