Department of Emergency Medicine, Yale University School of Medicine, New Haven, CT, USA.
Philips Research North America, Cambridge, MA, USA.
Ultrasound Med Biol. 2023 Sep;49(9):2095-2102. doi: 10.1016/j.ultrasmedbio.2023.05.016. Epub 2023 Jun 24.
B-lines are a ring-down artifact of lung ultrasound that arise with increased alveolar water in conditions such as pulmonary edema and infectious pneumonitis. Confluent B-line presence may signify a different level of pathology compared with single B-lines. Existing algorithms aimed at B-line counting do not distinguish between single and confluent B-lines. The objective of this study was to test a machine learning algorithm for confluent B-line identification.
This study used a subset of 416 clips from 157 subjects, previously acquired in a prospective study enrolling adults with shortness of breath at two academic medical centers, using a hand-held tablet and a 14-zone protocol. After exclusions, random sampling generated a total of 416 clips (146 curvilinear, 150 sector and 120 linear) for review. A group of five experts in point-of-care ultrasound blindly evaluated the clips for presence/absence of confluent B-lines. Ground truth was defined as majority agreement among the experts and used for comparison with the algorithm.
Confluent B-lines were present in 206 of 416 clips (49.5%). Sensitivity and specificity of confluent B-line detection by algorithm compared with expert determination were 83% (95% confidence interval [CI]: 0.77-0.88) and 92% (95% CI: 0.88-0.96). Sensitivity and specificity did not statistically differ between transducers. Agreement between algorithm and expert for confluent B-lines measured by unweighted κ was 0.75 (95% CI: 0.69-0.81) for the overall set.
The confluent B-line detection algorithm had high sensitivity and specificity for detection of confluent B-lines in lung ultrasound point-of-care clips, compared with expert determination.
B 线是肺超声的一种振铃伪像，在肺水肿和感染性肺炎等肺泡水增加的情况下出现。与单个 B 线相比，融合 B 线的存在可能表示不同程度的病理学。现有的 B 线计数算法无法区分单个和融合 B 线。本研究旨在测试一种用于融合 B 线识别的机器学习算法。
本研究使用了来自两个学术医疗中心的 157 名呼吸困难成年患者前瞻性研究中采集的 416 个片段的子集，使用手持平板电脑和 14 区方案。排除后，随机抽样生成了总共 416 个片段（146 个曲线形、150 个扇形和 120 个线性）进行回顾。五名床边超声专家对这些片段进行融合 B 线的存在/不存在进行了盲法评估。将多数专家的意见定义为ground truth，并将其与算法进行比较。
在 416 个片段中有 206 个（49.5%）存在融合 B 线。算法检测融合 B 线的敏感性和特异性与专家确定的结果相比分别为 83%（95%置信区间 [CI]：0.77-0.88）和 92%（95% CI：0.88-0.96）。两种探头之间的敏感性和特异性没有统计学差异。算法与专家对融合 B 线的评估之间的一致性，以未加权 κ 表示，在总体数据集为 0.75（95% CI：0.69-0.81）。
与专家判断相比，融合 B 线检测算法在床边超声点检测中对融合 B 线的检测具有较高的敏感性和特异性。
