文献速递胸部心血管US

基于迁移学习的肺超声B线评估用于急性心力衰竭

Transfer Learning-Based B-Line Assessment of Lung Ultrasound for Acute Heart Failure.
PubMed 文献 · Ultrasound Med Biol · 2024-02-29

本研究利用观察性急性心衰肺超声研究中的标准化动态影像,基于30例患者的49952帧图像训练卷积神经网络在帧水平判读B线,并在60例患者476段独立视频上评估。多分类AI算法二分类检测病理状态的AUC为0.967(95%CI 0.965-0.970),0-4级多分类评分与专家盲法阅片者的线性加权kappa为0.839(95%CI 0.804-0.871)。作者认为该算法在二分类和有序多分类B线评估中表现稳健,有潜力整合入临床流程辅助用户进行定量客观的B线评估。

要点

  • 多分类AI算法二分类检测病理状态AUC为0.967(95%CI 0.965-0.970)。
  • 0-4级多分类AI评分与专家盲法阅片者的线性加权kappa为0.839(95%CI 0.804-0.871)。
  • 该算法有潜力辅助新手用户进行定量客观的B线评估。

核心结论

  • 多分类AI算法在二分类和有序多分类B线评估中表现稳健,AUC为0.967(95%CI 0.965-0.970),与专家盲法阅片的线性加权kappa为0.839(95%CI 0.804-0.871),有潜力整合入临床流程辅助用户进行定量客观的B线评估以评估急性心衰。

研究设计与样本

  • 基于观察性急性心衰肺超声研究提供的标准化动态视频片段,用于AI模型开发与评估。

诊断标准与关键数值

  • 多分类AI算法在独立评估集二分类水平检测病理状态AUC为0.967(95%CI 0.965-0.970)。
  • 0-4级多分类AI算法评分与专家盲法阅片者比较,线性加权kappa为0.839(95%CI 0.804-0.871)。

局限性

  • 原文未报告局限性。

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

OBJECTIVE: B-lines assessed by lung ultrasound (LUS) outperform physical exam, chest radiograph, and biomarkers for the associated diagnosis of acute heart failure (AHF) in the emergent setting. The use of LUS is however limited to trained professionals and suffers from interpretation variability. The objective was to utilize transfer learning to create an AI-enabled software that can aid novice users to automate LUS B-line interpretation.

METHODS: Data from an observational AHF LUS study provided standardized cine clips for AI model development and evaluation. A total of 49,952 LUS frames from 30 patients were hand scored and trained on a convolutional neural network (CNN) to interpret B-lines at the frame level. A random independent evaluation set of 476 LUS clips from 60 unique patients assessed model performance. The AI models scored the clips on both a binary and ordinal 0-4 multiclass assessment.

RESULTS: A multiclassification AI algorithm had the best performance at the binary level when applied to the independent evaluation set, AUC of 0.967 (95% CI 0.965-0.970) for detecting pathologic conditions. When compared to expert blinded reviewer, the 0-4 multiclassification AI algorithm scale had a reported linear weighted kappa of 0.839 (95% CI 0.804-0.871).

CONCLUSIONS: The multiclassification AI algorithm is a robust and well performing model at both binary and ordinal multiclass B-line evaluation. This algorithm has the potential to be integrated into clinical workflows to assist users with quantitative and objective B-line assessment for evaluation of AHF.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Pare JR, Gjesteby LA, Tonelli M, et al. Transfer Learning-Based B-Line Assessment of Lung Ultrasound for Acute Heart Failure. Ultrasound Med Biol. 2024. PMID: 38423896. doi:10.1016/j.ultrasmedbio.2024.02.004

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。