文献速递泌尿生殖技术与安全US

开发深度学习网络对下腔静脉塌陷进行分类以预测液体反应性

Development of a Deep Learning Network to Classify Inferior Vena Cava Collapse to Predict Fluid Responsiveness.
PubMed 文献 · J Ultrasound Med · 2020-10-10

本研究利用长短期记忆网络分析危重症患者下腔静脉超声视频,以预测液体反应性。在175例患者中,网络预测的AUC为0.70(95%CI 0.43-1.00),阳性似然比为无穷大,阴性似然比为0.3(95%CI 0.12-0.77),低于床旁超声专家的AUC 0.94(95%CI 0.83-0.99)。作者认为网络表现中等,需更大数据集进一步训练和测试。

要点

  • 长短期记忆网络可基于下腔静脉超声视频对塌陷进行分类以预测液体反应性。
  • 该网络预测液体反应性的AUC为0.70(95%CI 0.43-1.00),表现中等。
  • 床旁超声专家离线视频审阅并手动测量直径的AUC为0.94(95%CI 0.83-0.99),优于网络。

核心结论

  • 长短期记忆网络可利用下腔静脉超声视频分类塌陷以预测液体反应性,表现中等,但不如床旁超声专家;需更大数据集进一步训练和测试。

研究设计与样本

  • 研究论文;使用2项先前前瞻性研究中自主呼吸危重症患者行静脉液体复苏时的下腔静脉超声视频数据集;共分析175例患者的211段视频,随机选取90%训练、10%测试;液体反应性定义为500 mL液体负荷后心脏指数增加大于10%(生物电抗法测量)。

诊断标准与关键数值

  • 液体反应性定义为500 mL液体负荷后心脏指数增加大于10%(生物电抗法测量);长短期记忆网络预测液体反应性的AUC为0.70(95%CI 0.43-1.00),阳性似然比为无穷大,阴性似然比为0.3(95%CI 0.12-0.77);床旁超声专家离线视频审阅并手动测量直径的AUC为0.94(95%CI 0.83-0.99)。

局限性

  • 训练队列样本量小,网络表现中等。
  • 网络表现差于床旁超声专家。
  • 需用更大数据集进一步训练和测试该长短期记忆网络。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

OBJECTIVES: To create a deep learning algorithm capable of video classification, using a long short-term memory (LSTM) network, to analyze collapsibility of the inferior vena cava (IVC) to predict fluid responsiveness in critically ill patients.

METHODS: We used a data set of IVC ultrasound (US) videos to train the LSTM network. The data set was created from IVC US videos of spontaneously breathing critically ill patients undergoing intravenous fluid resuscitation as part of 2 prior prospective studies. We randomly selected 90% of the IVC videos to train the LSTM network and 10% of the videos to test the LSTM network's ability to predict fluid responsiveness. Fluid responsiveness was defined as a greater than 10% increase in the cardiac index after a 500-mL fluid bolus, as measured by bioreactance.

RESULTS: We analyzed 211 videos from 175 critically ill patients: 191 to train the LSTM network and 20 to test it. Using standard data augmentation techniques, we increased our sample size from 191 to 3820 videos. Of the 175 patients, 91 (52%) were fluid responders. The LSTM network was able to predict fluid responsiveness moderately well, with an area under the receiver operating characteristic curve of 0.70 (95% confidence interval [CI], 0.43-1.00), a positive likelihood ratio of infinity, and a negative likelihood ratio of 0.3 (95% CI, 0.12-0.77). In comparison, point-of-care US experts using video review offline and manual diameter measurement via software caliper tools achieved an area under the receiver operating characteristic curve of 0.94 (95% CI, 0.83-0.99).

CONCLUSIONS: We demonstrated that an LSTM network can be trained by using videos of IVC US to classify IVC collapse to predict fluid responsiveness. Our LSTM network performed moderately well given the small training cohort but worse than point-of-care US experts. Further training and testing of the LSTM network with a larger data sets is warranted.

来源:J Ultrasound Med,查看原文。版权归原作者所有。

引用

  1. Blaivas M, Blaivas L, Philips G, et al. Development of a Deep Learning Network to Classify Inferior Vena Cava Collapse to Predict Fluid Responsiveness. J Ultrasound Med. 2020. PMID: 33038035. doi:10.1002/jum.15527

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。