相关实验视频

Updated: Jan 28, 2026

Evaluation of the Cognitive Performance of Hypertensive Patients with Silent Cerebrovascular Lesions

Evaluation of the Cognitive Performance of Hypertensive Patients with Silent Cerebrovascular Lesions

Published on: April 23, 2021

大型语言模型在NEJM图像挑战中的诊断性能:与人类评估人员进行的比较研究以及快速工程的影响

Yuchen Zhou^1,2, Weiping Wang¹, Peng Wang¹

¹Department of Radiation Oncology, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, China.

Frontiers in medicine

|January 26, 2026

概括

领先的多式联络大型语言模型 (LLM) 显示出高诊断准确度,在标准化医疗图像挑战中表现优于人类医生. 快速工程可以减轻LLM逻辑错误,增强其在教育和诊断方面的潜力.

科学领域:

人工智能在医学中的应用
医学诊断医学诊断医学诊断
临床决策支持临床决策支持

背景情况:

多模式大语言模型 (LLM) 正在成为潜在的临床决策支持工具.
它们的准确性和与标准化病例上的人类表现的比较仍然不清楚.

研究的目的:

严格评估四个领先的LLM在NEJM形象挑战中的表现.
为了对表现最好的LLM与医学学生和主治医生进行比较.
描述LLM错误类型和测试提示工程策略.

主要方法:

在200项NEJM图像挑战赛中评估了OpenAI o4-mini-high,Claude 4 Opus,Gemini 2.5 Pro和Qwen 3. 在200项NEJM图像挑战赛中进行评估.
与三名医学学生和一名内科主治医生对比,比较了顶尖的LLM.
分析了OpenAI o4-mini-high的主导错误类型,并测试了提示工程技术.

主要成果:

开放AI o4-mini-high实现了94%的准确性,超过了人类参与者 (38.5%-70.5%).
在轻松,中度和困难的病例中,表现一致.
83.3%的OpenAI o4-mini-high的错误源于诊断逻辑缺陷,而不是输入处理.
提示技术纠正了超过一半的初始错误.

结论:

一个领先的多式联络法学士 (LLM) 证明了高诊断准确度,在标准化环境中超过同行模型和人类.
结果表明模式识别能力,而不是类似人类的临床理解.
在教育和标准化环境中,LLM显示出潜力,由于快速的工程和人与人工智能的交互,错误在一定程度上得到了缓解.

关键词:

在NEJM的形象挑战中.医学中的人工智能临床决策支持临床决策支持医学教育医学教育多模式的大型语言模型

更多相关视频

Author Spotlight: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication

Author Spotlight: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication

Published on: January 26, 2024

Fast Imaging Technique to Study Drop Impact Dynamics of Non-Newtonian Fluids

Fast Imaging Technique to Study Drop Impact Dynamics of Non-Newtonian Fluids

Published on: March 5, 2014

相关概念视频

Language

Language

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...

Appendicitis-II: Diagnostic Studies and Management

Appendicitis-II: Diagnostic Studies and Management

Diagnosing and managing appendicitis requires a structured and comprehensive approach that spans from initial assessment to postoperative care. Here is an overview of the process:
Diagnosing Appendicitis
It requires a multifaceted approach, starting with a detailed physical examination to pinpoint the location and nature of the pain and identify any associated symptoms. Laboratory tests play a crucial role. A complete Blood Count (CBC) typically reveals leukocytosis (an increased number of...

Heart Failure IV: Classification and Diagnostic Evaluation

Heart Failure IV: Classification and Diagnostic Evaluation

Heart failure can be classified in various ways, with the most common classifications based on physical activity limitations, disease progression, severity, and treatment strategies.The Functional Classification of Heart Failure divides patients into four categories based on physical activity limitation due to symptom burden.Class I: Patients in this class have cardiac disease but no physical activity limitations. Ordinary activities like walking, climbing stairs, or routine tasks do not cause...

Aneurysm II: Clinical Manifestations and Diagnostic Studies

Aneurysm II: Clinical Manifestations and Diagnostic Studies

Thoracic, aortic arch and abdominal aneurysms are significant vascular conditions that can present with various clinical manifestations and lead to serious complications. Understanding these manifestations and the appropriate diagnostic studies is essential for effective management and treatment.Thoracic Aortic AneurysmsThoracic aortic aneurysms often remain asymptomatic until they reach a size that impinges on adjacent structures. They typically cause deep, diffuse chest pain that radiates to...

Components of Language

Components of Language

Language, whether spoken, signed, or written, consists of specific components: lexicon and grammar. The lexicon is the vocabulary of a language, comprising its words. Grammar is the set of rules used to convey meaning through the lexicon. For example, English grammar adds “-ed” to most verbs to indicate past tense. Words are formed by combining phonemes, which are the basic sound units of a language. Different languages have different sets of phonemes (e.g., “ah” vs.

Language Development

Language Development

Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...