From the Department of Surgery (B.E.L., J.T.C., W.S.W., E.M.), Institute for Biomedical Informatics (A.V.), Department of Pathology (C.B.), and Department of Radiology (T.B.), University of Kentucky, Lexington, Kentucky; Division of Trauma, Emergency Surgery, and Surgical Critical Care, Department of Surgery (M.S., K.I.), University of Southern California, Los Angeles, California; and Division of Trauma Critical Care and Acute Care Surgery, Department of Surgery (Z.D.W.), University of Kentucky, Lexington, Kentucky.
J Trauma Acute Care Surg. 2023 Nov 1;95(5):706-712. doi: 10.1097/TA.0000000000004021. Epub 2023 May 11.
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.
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.
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.
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.
Diagnostic Test/Criteria; Level III.
创伤重点超声评估（FAST）是一种广泛使用的影像学方法，用于确定血流动力学不稳定的创伤患者生命威胁性出血的位置。本研究评估了人工智能在解释 FAST 腹部检查视图中的作用，因为它涉及到视图的充分性和液体探查阳性的准确性。
从一家每年有超过 3500 例成人创伤评估的四级护理 1 级创伤中心获取 2015 年至 2022 年创伤激活的创伤重点超声检查图像。获得右上象限和左上象限视图的图像，并由外科医生或放射科医生进行阅读。阳性定义为肝肾窝或脾肾窝中有液体，而充分性则定义为右上象限或左上象限视图分别存在肝脏和肾脏或脾脏和肾脏。评估了四个卷积神经网络架构模型（DenseNet121、InceptionV3、ResNet50、Vgg11bn）。
共有 6608 张图像，代表 109 例，纳入“充分”和“阳性”数据集进行分析。在充分测试队列中，模型的准确率为 88.7%，灵敏度为 83.3%，特异性为 93.6%，而阳性队列的准确率为 98.0%，灵敏度为 89.6%，特异性为 100.0%。增强后，阳性模型的准确性和灵敏度提高到 95.1%和 94.0%。DenseNet121 在所有任务中表现出最佳的准确性。
人工智能可以检测 FAST 检查的阳性和充分性，准确率为 94%和 97%，有助于在最小的专家临床医生输入下实现护理交付的标准化。人工智能是提高患者护理成像解释准确性的可行方式，应作为一种床边临床决策工具进行探索。
诊断性测试/标准；III 级。
