文献速递胸部技术与安全CTMRPETDR

胸部放射学中人机交互效果的决定因素

Determinants of Reader-LLM Interaction in Thoracic Radiology: Impact of Model Confidence and Reader Expertise.
PubMed 文献 · Radiology · 2026-01-01

本研究回顾性纳入100例胸部影像病例,10名阅片者在无辅助及大语言模型辅助两种模式下评估。结果显示模型置信度与阅片者专业水平独立影响恰当交互,而理由质量虽促进采纳正确建议,但也增加对错误建议的过度依赖。

要点

  • 高模型置信度与阅片者专业水平促进恰当采纳建议
  • 理由质量高会降低拒绝正确建议,但增加接受错误建议风险
  • 高年资与高自信阅片者更不易接受错误大模型建议

核心结论

  • 成功的人机协作与模型置信度和阅片者专业水平独立相关
  • 理由质量促进正确建议被采纳,但也增加对错误建议的过度依赖

研究设计与样本

  • 回顾性研究,纳入100例胸部影像病例,来自韩国胸部放射学会Weekly Case平台
  • 10名阅片者参与,先无辅助评估,后随机分组接受高准确率GPT-5或低准确率GPT-4o辅助
  • 参考标准由病例作者建立,采用多变量广义估计方程分析

关键影像表现/征象

  • 研究病例涵盖X线摄影、CT、MRI及PET胸部影像

诊断标准与关键数值

  • 高准确率模型为76%(379/500),低准确率模型为27%(133/500)

临床应用与阅片要点

  • 应用大模型辅助诊断时需综合评估模型置信度与自身判断,避免因理由表述质量高而盲从
  • 低年资阅片者更应警惕对大模型错误建议的过度依赖

局限性

  • 回顾性研究设计
  • 病例来源为单一平台,可能影响结果普适性

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

Background Large language models (LLMs) provide diagnostic suggestions and rationales, but determinants of successful reader-LLM interaction remain unclear. Purpose To determine how LLM attributes and reader expertise independently and jointly influence the selective integration of diagnostic advice in human-LLM collaboration. Materials and Methods In this retrospective study, 10 readers evaluated 100 chest imaging cases (radiography, CT, MRI, or PET) from the Korean Society of Thoracic Radiology Weekly Case platform (January 2018 to December 2020), unaided (session 1) and randomized to LLM-assisted setups (session 2) at the reader-case level: high accuracy (76% [379 of 500 reader-case pairs]) using OpenAI's GPT-5 or low accuracy (27% [133 of 500]) using OpenAI's GPT-4o (August 2025), providing ranked diagnostic options with rationales against a reference standard established by the case author. The primary outcome was adequate interaction (accepting correct or rejecting incorrect suggestions). Data were analyzed using multivariable generalized estimating equations, adjusted for reader expertise, diagnostic correctness and reader confidence (session 1), model confidence (score assigned to the correct diagnosis), and reference panel-assessed rationale quality. Results A total of 100 patients were included (mean age, 50.0 years ± 16.3 [SD]; 59 male). After multivariable adjustment, model confidence (odds ratio [OR], 3.82 [95% CI: 1.58, 9.25]; P = .003) and reader expertise (OR, 2.06 [95% CI: 1.38, 3.07]; P < .001) were independently associated with adequate interaction, with a weaker effect of confidence among experts (OR, 0.79 [95% CI: 0.67, 0.94]; P = .008). Higher rationale quality reduced rejection of correct suggestions (OR, 0.79 [95% CI: 0.67, 0.93]; P = .005) but increased acceptance of incorrect suggestions (OR, 1.71 [95% CI: 1.47, 1.99]; P < .001). Higher reader expertise (OR, 0.54 [95% CI: 0.41, 0.70]; P < .001) and reader confidence (OR, 0.80 [95% CI: 0.67, 0.94]; P = .007) were protective, reducing acceptance of incorrect suggestions. Conclusion Successful reader-LLM collaboration is associated with model confidence and reader expertise, with rationale quality facilitating correct advice uptake but increasing overreliance on incorrect suggestions. © RSNA, 2026 Supplemental material is available for this article.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Song, Jeong, Han, et al. Determinants of Reader-LLM Interaction in Thoracic Radiology: Impact of Model Confidence and Reader Expertise. Radiology. 2026. PMID: 42578783. doi:10.1148/radiol.253397

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。