文献速递呼吸衰竭与机械通气重症综合管理与镇静镇痛

人工智能辅助图像解读对临床医生在平片胸片上识别气胸诊断性能的影响评估:多病例多阅片者研究

Evaluation of the impact of artificial intelligence-assisted image interpretation on the diagnostic performance of clinicians in identifying pneumothoraces on plain chest X-ray: a multi-case multi-reader study.
PubMed 文献 · Emerg Med J · 2024-09-25
一句话结论多中心多阅片者研究显示,AI辅助使前线急诊临床医生识别气胸的总体敏感度从66.8%升至78.1%(提高11.4%,95%CI 4.8-18.0,p=0.002),低年资医生获益最大。

该多中心盲法多病例多阅片者研究于2021年10月至2022年1月在线开展,纳入四家英格兰医院的18名不同专科、不同年资临床读者,判读395张平片胸片(气胸阳性189张、阴性206张),参考标准为两名胸部放射科医生的共识意见(第三名仲裁)。GEHC CCS气胸算法对最终数据集整体AUROC为0.939。读者先无AI辅助判读,经洗脱期后借助AI输出重复判读。结果显示总体敏感度由66.8%升至78.1%(提高11.4%,95%CI 4.8-18.0,p=0.002),特异度由93.9%升至95.8%(p=0.247),低年资读者亚组敏感度提高21.7%(95%CI 10.9-32.6)。总体判读时间未变,AI提高了诊断信心和敏感度,作者认为AI有潜力在急诊环境中支持技能较弱的临床医生。

要点

  • AI辅助使前线临床医生识别气胸的总体敏感度从66.8%(95%CI 57.3-76.2)升至78.1%(95%CI 72.2-84.0),提高11.4%(95%CI 4.8-18.0,p=0.002)。
  • 低年资读者亚组敏感度提高21.7%(95%CI 10.9-32.6),从56.0%(95%CI 37.7-74.3)升至77.7%(95%CI 65.8-89.7,p<0.01),为获益最大亚组。
  • 特异度从93.9%(95%CI 90.9-97.0)升至95.8%(95%CI 93.7-97.9),差异未达统计学显著(p=0.247)。
  • GEHC CCS气胸算法在该数据集检测或排除气胸的整体AUROC为0.939。
  • 总体判读时间未变,AI提高了诊断信心,尤其在低年资临床医生中。

适用人群与场景

  • 四家英格兰医院、六个临床专科、不同年资的18名临床读者,在线判读395张平片胸片(气胸阳性189张、阴性206张)。

诊断标准与关键阈值

  • 参考标准为两名胸部放射科医生的共识意见,第三名放射科医生担任仲裁。

处置流程与药物剂量

  • 读者先无AI辅助独立判读数据集,记录气胸有无及信心评级;经洗脱期后,借助GEHC CCS气胸算法输出重复同一判读流程。

研究设计与关键结果

  • 多中心盲法多病例多阅片者研究,18名读者、395张平片胸片(阳性189张、阴性206张),GEHC CCS气胸算法整体AUROC为0.939。
  • 总体敏感度无AI辅助66.8%(95%CI 57.3-76.2)vs AI辅助78.1%(95%CI 72.2-84.0),提高11.4%(95%CI 4.8-18.0,p=0.002)。
  • 总体特异度无AI辅助93.9%(95%CI 90.9-97.0)vs AI辅助95.8%(95%CI 93.7-97.9),p=0.247。
  • 低年资读者亚组敏感度无AI辅助56.0%(95%CI 37.7-74.3)vs AI辅助77.7%(95%CI 65.8-89.7),提高21.7%(95%CI 10.9-32.6,p<0.01)。
  • 总体判读时间未变,AI提高了诊断信心,尤其在低年资临床医生中。

证据类型、等级与局限

  • 证据类型:多中心盲法多病例多阅片者研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,AI辅助图像解读可显著提高临床医生检测气胸的诊断准确性,尤其使经验较少的从业者获益。
  • 作者认为,这些发现凸显了AI在急诊环境中支持技能较弱临床医生的潜力。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开

BACKGROUND: Artificial intelligence (AI)-assisted image interpretation is a fast-developing area of clinical innovation. Most research to date has focused on the performance of AI-assisted algorithms in comparison with that of radiologists rather than evaluating the algorithms' impact on the clinicians who often undertake initial image interpretation in routine clinical practice. This study assessed the impact of AI-assisted image interpretation on the diagnostic performance of frontline acute care clinicians for the detection of pneumothoraces (PTX).

METHODS: A multicentre blinded multi-case multi-reader study was conducted between October 2021 and January 2022. The online study recruited 18 clinician readers from six different clinical specialties, with differing levels of seniority, across four English hospitals. The study included 395 plain CXR images, 189 positive for PTX and 206 negative. The reference standard was the consensus opinion of two thoracic radiologists with a third acting as arbitrator. General Electric Healthcare Critical Care Suite (GEHC CCS) PTX algorithm was applied to the final dataset. Readers individually interpreted the dataset without AI assistance, recording the presence or absence of a PTX and a confidence rating. Following a 'washout' period, this process was repeated including the AI output.

RESULTS: Analysis of the performance of the algorithm for detecting or ruling out a PTX revealed an overall AUROC of 0.939. Overall reader sensitivity increased by 11.4% (95% CI 4.8, 18.0, p=0.002) from 66.8% (95% CI 57.3, 76.2) unaided to 78.1% aided (95% CI 72.2, 84.0, p=0.002), specificity 93.9% (95% CI 90.9, 97.0) without AI to 95.8% (95% CI 93.7, 97.9, p=0.247). The junior reader subgroup showed the largest improvement at 21.7% (95% CI 10.9, 32.6), increasing from 56.0% (95% CI 37.7, 74.3) to 77.7% (95% CI 65.8, 89.7, p<0.01).

CONCLUSION: The study indicates that AI-assisted image interpretation significantly enhances the diagnostic accuracy of clinicians in detecting PTX, particularly benefiting less experienced practitioners. While overall interpretation time remained unchanged, the use of AI improved diagnostic confidence and sensitivity, especially among junior clinicians. These findings underscore the potential of AI to support less skilled clinicians in acute care settings.

来源:Emerg Med J,查看原文。版权归原作者所有。

参考来源

  1. Novak A, Ather S, Gill A, et al. Evaluation of the impact of artificial intelligence-assisted image interpretation on the diagnostic performance of clinicians in identifying pneumothoraces on plain chest X-ray: a multi-case multi-reader study. Emerg Med J. 2024. PMID: 39009424. doi:10.1136/emermed-2023-213620

供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。