人工智能评估创伤重点超声检查
本研究从一家年接诊超过3500例成人创伤评估的四级医疗一级创伤中心,获取2015至2022年创伤激活患者的FAST图像,由外科医生或放射科医生判读,阳性定义为肝肾隐窝或脾肾隐窝存在液体,合格性定义为右/左上腹切面同时显示肝与肾或脾与肾。共纳入109例的6608张图像,评估DenseNet121、InceptionV3、ResNet50、Vgg11bn四种卷积神经网络模型。合格性队列准确率88.7%、敏感度83.3%、特异度93.6%;阳性队列准确率98.0%、敏感度89.6%、特异度100.0%,数据增强后阳性模型准确率95.1%、敏感度94.0%;DenseNet121在各任务中准确率最佳。作者认为人工智能是改善图像判读准确性的可行方式,应作为床旁临床决策工具继续推进。
要点
- 阳性队列:准确率98.0%、敏感度89.6%、特异度100.0%,基于109例的6608张FAST图像。
- 合格性队列:准确率88.7%、敏感度83.3%、特异度93.6%,判读切面是否同时显示目标脏器。
- 数据增强后阳性模型准确率95.1%、敏感度94.0%。
- 四种卷积神经网络中DenseNet121在各任务中准确率最佳。
- 结论称人工智能检测FAST阳性与合格性准确率分别为94%与97%,作者认为可作为床旁决策工具。
适用人群与场景
- 创伤激活患者的FAST检查图像,来自一家四级医疗一级创伤中心,该中心每年完成超过3500例成人创伤评估。
- 图像为2015至2022年采集,涉及右 upper quadrant 与左 upper quadrant 切面。
诊断标准与关键阈值
- 阳性定义:肝肾隐窝或脾肾隐窝存在液体。
- 合格性定义:右 upper quadrant 切面同时显示肝与肾,左 upper quadrant 切面同时显示脾与肾。
研究设计与关键结果
- 研究类型为诊断准确性研究,共纳入109例的6608张图像,图像由外科医生或放射科医生判读,评估DenseNet121、InceptionV3、ResNet50、Vgg11bn四种卷积神经网络架构。
- 合格性测试队列:准确率88.7%、敏感度83.3%、特异度93.6%。
- 阳性队列:准确率98.0%、敏感度89.6%、特异度100.0%。
- 数据增强后阳性模型准确率提升至95.1%、敏感度提升至94.0%。
- DenseNet121在各任务中准确率最佳。
- 结论:人工智能检测FAST阳性与合格性的准确率分别为94%与97%。
证据类型、等级与局限
- 证据类型:诊断试验/标准研究,证据等级Level III。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为人工智能可辅助FAST阳性与切面合格性的标准化判读,所需专家临床投入极少。
- 作者认为人工智能是改善患者图像判读准确性的可行方式,应作为床旁临床决策工具继续推进。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「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
BACKGROUND: The focused assessment with sonography in trauma (FAST) is a widely used imaging modality to identify the location of life-threatening hemorrhage in a hemodynamically unstable trauma patient. This study evaluates the role of artificial intelligence in interpretation of the FAST examination abdominal views, as it pertains to adequacy of the view and accuracy of fluid survey positivity.
METHODS: Focused assessment with sonography for trauma examination images from 2015 to 2022, from trauma activations, were acquired from a quaternary care level 1 trauma center with more than 3,500 adult trauma evaluations, annually. Images pertaining to the right upper quadrant and left upper quadrant views were obtained and read by a surgeon or radiologist. Positivity was defined as fluid present in the hepatorenal or splenorenal fossa, while adequacy was defined by the presence of both the liver and kidney or the spleen and kidney for the right upper quadrant or left upper quadrant views, respectively. Four convolutional neural network architecture models (DenseNet121, InceptionV3, ResNet50, Vgg11bn) were evaluated.
RESULTS: A total of 6,608 images, representing 109 cases were included for analysis within the "adequate" and "positive" data sets. The models relayed 88.7% accuracy, 83.3% sensitivity, and 93.6% specificity for the adequate test cohort, while the positive cohort conferred 98.0% accuracy, 89.6% sensitivity, and 100.0% specificity against similar models. Augmentation improved the accuracy and sensitivity of the positive models to 95.1% accurate and 94.0% sensitive. DenseNet121 demonstrated the best accuracy across tasks.
CONCLUSION: Artificial intelligence can detect positivity and adequacy of FAST examinations with 94% and 97% accuracy, aiding in the standardization of care delivery with minimal expert clinician input. Artificial intelligence is a feasible modality to improve patient care imaging interpretation accuracy and should be pursued as a point-of-care clinical decision-making tool.
LEVEL OF EVIDENCE: Diagnostic Test/Criteria; Level III.
参考来源
- Levy BE, Castle JT, Virodov A, et al. Artificial intelligence evaluation of focused assessment with sonography in trauma. J Trauma Acute Care Surg. 2023. PMID: 37165477. doi:10.1097/TA.0000000000004021
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。