文献速递呼吸衰竭与机械通气重症综合管理与镇静镇痛

人工智能辅助胸片判读与阅片者表现及效率的关联

Association of Artificial Intelligence-Aided Chest Radiograph Interpretation With Reader Performance and Efficiency.
PubMed 文献 · JAMA Netw Open · 2022-08-01
一句话结论多中心交叉对照研究显示,人工智能辅助判读可提高放射科医生对胸片主要病变的敏感性且不降低特异性,并将报告时间缩短3.9秒。

该多中心队列研究于2021年4月至11月在波士顿两家四级学术医院开展,纳入6名放射科医生(2名主治、2名胸部放射学fellow、2名住院医),采用随机交叉设计,分别在有/无人工智能辅助下判读497张成人胸片(MIMIC-CXR 247张、MGH 250张),洗脱期4周。人工智能生成热图和图像水平病变概率。结果显示人工智能辅助下阅片者对肺炎、结节、气胸、胸腔积液的敏感性均显著提高,特异性未受影响,气胸和结节的AUROC显著改善;报告时间人工智能组较无人工智能组降低10%(40.8 vs 36.9秒,差3.9秒,95%CI 2.9-5.2,P<.001)。提示人工智能辅助可改善胸片判读表现与效率。

要点

  • 人工智能辅助使阅片者对气胸的敏感性从0.792(95%CI 0.756-0.827)提高至0.988(95%CI 0.932-1.000),对结节的敏感性从0.567(95%CI 0.524-0.611)提高至0.816(95%CI 0.732-0.882)。
  • 人工智能辅助使肺炎敏感性从0.673(95%CI 0.632-0.714)提高至0.887(95%CI 0.834-0.928),胸腔积液敏感性从0.889(95%CI 0.862-0.917)提高至0.872(95%CI 0.808-0.921)。
  • 人工智能辅助下阅片者对4种目标病变的AUROC均改善,其中气胸和结节的改善有统计学意义。
  • 人工智能辅助将每张胸片报告时间从40.8秒降至36.9秒(降低10%,差3.9秒,95%CI 2.9-5.2,P<.001)。

适用人群与场景

  • 成人患者胸片,包括有和无肺炎、结节、气胸、胸腔积液4种目标病变者;MIMIC-CXR数据集患者人口学数据不可用,MGH数据集平均(SD)年龄63(16)岁,男性133例(53.2%)。
  • 判读者为放射科医生,包括主治放射科医生、胸部放射学fellow和住院医。

研究设计与关键结果

  • 多中心队列研究,2021年4月至11月,纳入6名放射科医生(2名主治、2名胸部放射学fellow、2名住院医),采用随机交叉设计,有/无人工智能辅助两个判读 session,洗脱期4周,共497张成人胸片(MIMIC-CXR 247张,MGH 250张),351张存在目标病变。
  • 人工智能对全部病变的敏感性高于阅片者:结节0.816(95%CI 0.732-0.882) vs 0.567(95%CI 0.524-0.611);肺炎0.887(95%CI 0.834-0.928) vs 0.673(95%CI 0.632-0.714);胸腔积液0.872(95%CI 0.808-0.921) vs 0.889(95%CI 0.862-0.917);气胸0.988(95%CI 0.932-1.000) vs 0.792(95%CI 0.756-0.827)。
  • 人工智能辅助下阅片者对全部目标病变的敏感性显著提高,特异性未受负面影响。
  • 人工智能辅助下阅片者对4种目标病变的AUROC均改善,其中气胸和结节的改善有统计学意义。
  • 人工智能辅助组报告时间较无人工智能组降低10%(40.8 vs 36.9秒;差3.9秒;95%CI 2.9-5.2;P<.001)。

证据类型、等级与局限

  • 证据类型:多中心队列研究(观察性研究),采用随机交叉设计比较有/无人工智能辅助的判读表现。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,人工智能辅助判读与阅片者识别胸片主要病变的表现和效率改善相关。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「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

IMPORTANCE: The efficient and accurate interpretation of radiologic images is paramount.

OBJECTIVE: To evaluate whether a deep learning-based artificial intelligence (AI) engine used concurrently can improve reader performance and efficiency in interpreting chest radiograph abnormalities.

DESIGN, SETTING, AND PARTICIPANTS: This multicenter cohort study was conducted from April to November 2021 and involved radiologists, including attending radiologists, thoracic radiology fellows, and residents, who independently participated in 2 observer performance test sessions. The sessions included a reading session with AI and a session without AI, in a randomized crossover manner with a 4-week washout period in between. The AI produced a heat map and the image-level probability of the presence of the referrable lesion. The data used were collected at 2 quaternary academic hospitals in Boston, Massachusetts: Beth Israel Deaconess Medical Center (The Medical Information Mart for Intensive Care Chest X-Ray [MIMIC-CXR]) and Massachusetts General Hospital (MGH).

MAIN OUTCOMES AND MEASURES: The ground truths for the labels were created via consensual reading by 2 thoracic radiologists. Each reader documented their findings in a customized report template, in which the 4 target chest radiograph findings and the reader confidence of the presence of each finding was recorded. The time taken for reporting each chest radiograph was also recorded. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) were calculated for each target finding.

RESULTS: A total of 6 radiologists (2 attending radiologists, 2 thoracic radiology fellows, and 2 residents) participated in the study. The study involved a total of 497 frontal chest radiographs-247 from the MIMIC-CXR data set (demographic data for patients were not available) and 250 chest radiographs from MGH (mean [SD] age, 63 [16] years; 133 men [53.2%])-from adult patients with and without 4 target findings (pneumonia, nodule, pneumothorax, and pleural effusion). The target findings were found in 351 of 497 chest radiographs. The AI was associated with higher sensitivity for all findings compared with the readers (nodule, 0.816 [95% CI, 0.732-0.882] vs 0.567 [95% CI, 0.524-0.611]; pneumonia, 0.887 [95% CI, 0.834-0.928] vs 0.673 [95% CI, 0.632-0.714]; pleural effusion, 0.872 [95% CI, 0.808-0.921] vs 0.889 [95% CI, 0.862-0.917]; pneumothorax, 0.988 [95% CI, 0.932-1.000] vs 0.792 [95% CI, 0.756-0.827]). AI-aided interpretation was associated with significantly improved reader sensitivities for all target findings, without negative impacts on the specificity. Overall, the AUROCs of readers improved for all 4 target findings, with significant improvements in detection of pneumothorax and nodule. The reporting time with AI was 10% lower than without AI (40.8 vs 36.9 seconds; difference, 3.9 seconds; 95% CI, 2.9-5.2 seconds; P < .001).

CONCLUSIONS AND RELEVANCE: These findings suggest that AI-aided interpretation was associated with improved reader performance and efficiency for identifying major thoracic findings on a chest radiograph.

来源:JAMA Netw Open,查看原文。版权归原作者所有。

参考来源

  1. Ahn JS, Ebrahimian S, McDermott S, et al. Association of Artificial Intelligence-Aided Chest Radiograph Interpretation With Reader Performance and Efficiency. JAMA Netw Open. 2022. PMID: 36044215. doi:10.1001/jamanetworkopen.2022.29289

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。