相关实验视频

Updated: Jan 14, 2026

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

大型语言模型在儿童肺炎的诊断中以随机水平进行,使用胸部X射线图

Justin Gillette¹, Michelle Lu², Thomas F Heston^3,4

¹Medical Education and Clinical Sciences, Elson S. Floyd College of Medicine, Washington State University, Spokane, USA.

|October 22, 2025

概括

一般用途的大型语言模型 (LLM) 在诊断儿科肺炎时显示出不可靠的性能,使用胸部X射线图 (CXR) 来诊断儿科肺炎. 这些人工智能工具,包括ChatGPT,Claude,Gemini和Grok,还不适合无监督的临床使用.

科学领域:

人工智能在医学中的应用
儿科放射学儿科放射学
医学诊断医学诊断医学诊断

背景情况:

肺炎是全球儿童健康的一个主要问题.
胸部放射 (CXR) 对于诊断儿科肺炎至关重要.
在CXRs上区分细菌和病毒性肺炎是具有挑战性的.

研究的目的:

评估通用大型语言模型 (LLM) 在CXRs上识别儿科肺炎的诊断性能.
评估LLM在区分细菌性肺炎,病毒性肺炎和正常CXRs方面的可靠性.
了解目前用于无监督医学图像解释的LLM的局限性.

主要方法:

四个公开的LLM (ChatGPT,Claude,Gemini,Grok) 在44个儿科CXR上进行了测试.
图像被分类为细菌性肺炎,病毒性肺炎或正常.
每个LLM对每个图像进行了两次解读;精度和内部一致性与人类专家的共识相比进行了测量.

主要成果:

所有LLM的平均诊断准确率为31%,相当于偶然.
病毒性肺炎 (54%) 的精度最高,正常CXRs (18%) 的精度最低.
内部一致性在46%至71%之间,表明性能不可靠;与专家一致性不超过49%.

结论:

目前,一般用途的LLM在CXR上诊断儿科肺炎时是不可靠的.
它们的准确性较低,特别是在排除疾病方面,并且缺乏内部一致性,这对无监督的临床部署构成风险.
未来的人工智能工具必须是专门构建的,在各种数据上进行训练,并与临床监督集成,以确保安全使用.

关键词:

在医学成像中使用AI.聊天聊天聊天胸部X射线图 - 胸部X射线图 AI的诊断准确性 AI的诊断准确性大型语言模型.儿科肺炎儿科肺炎

更多相关视频

Experimental Model to Evaluate Resolution of Pneumonia

Experimental Model to Evaluate Resolution of Pneumonia

Published on: February 17, 2023

Protocol and Guidelines for Point-of-Care Lung Ultrasound in Diagnosing Neonatal Pulmonary Diseases Based on International Expert Consensus

Protocol and Guidelines for Point-of-Care Lung Ultrasound in Diagnosing Neonatal Pulmonary Diseases Based on International Expert Consensus

Published on: March 6, 2019

相关概念视频

Pneumonia III: Complications and Assessment

Pneumonia III: Complications and Assessment

Pneumonia poses the potential for numerous complications that warrant consideration. These complications include the following:

Assessment of Respiration

Assessment of Respiration

The respiratory system's basic structures and primary functions lay the foundation for nurses' comprehensive respiratory assessments. This assessment includes subjective and objective data to gauge the patient's respiratory health.
Subjective Assessment: Nurses interview the patient to gather information directly during the subjective assessment. It includes questions about the individual's medical history, medications, and symptoms, focusing on past respiratory conditions like...

Respiratory System Abnormal Finding I: Inspection and Percussion

Respiratory System Abnormal Finding I: Inspection and Percussion

Respiratory system abnormalities are a significant concern in healthcare due to their potential to indicate underlying severe conditions like Chronic Obstructive Pulmonary Disease (COPD), asthma, and pneumonia. These abnormalities can often be detected through physical examination methods like inspection and percussion.
Inspection Findings
During an inspection, several findings may suggest the presence of respiratory distress or disease. Pursed-lip breathing, where exhalation is slowed by...