文献速递重症综合管理与镇静镇痛呼吸衰竭与机械通气

深度学习模型可基于胸部X线准确预测和量化肺水肿

A deep learning model enables accurate prediction and quantification of pulmonary edema from chest X-rays.
PubMed 文献 · Crit Care · 2023-05-26
一句话结论回顾性研究显示深度学习模型可从胸部X线高精度量化EVLWI,二分类模型准确率0.93、AUROC 0.98。

该研究回顾性纳入ICU内24小时内接受胸部X线和经肺热稀释(TPTD)测量的431例患者共471张X线片,以TPTD提取的血管外肺水指数(EVLWI)作为肺水肿的定量指标。采用深度学习方法,将数据按EVLWI分为二、三、四、五类,以提高X线预测EVLWI的分辨率。二分类模型(EVLWI<15、≥15)准确率0.93、AUROC 0.98、MCC 0.86;三个多分类模型准确率0.90~0.95、AUROC 0.97~0.99、MCC 0.86~0.92。结论认为深度学习能以高准确度量化EVLWI所反映的肺水肿。

要点

  • 二分类模型(EVLWI<15 vs ≥15)准确率0.93、AUROC 0.98、MCC 0.86。
  • 三个多分类模型准确率0.90~0.95、AUROC 0.97~0.99、MCC 0.86~0.92。
  • 研究纳入ICU内24小时内接受胸部X线和TPTD测量的431例患者共471张X线片,以EVLWI为定量参考。
  • 深度学习可将肺水肿按EVLWI分为二、三、四、五类进行量化预测,提高分辨率。
  • 结论认为深度学习能以高准确度量化EVLWI所反映的肺水肿。

适用人群与场景

  • 在重症监护病房内24小时内接受胸部X线和经肺热稀释(TPTD)测量的患者,共431例、471张X线片。

诊断标准与关键阈值

  • 以经肺热稀释(TPTD)提取的血管外肺水指数(EVLWI)作为肺水肿的定量参考指标。
  • 二分类模型以EVLWI<15和≥15为界值。

研究设计与关键结果

  • 研究为回顾性研究,纳入431例患者的471张胸部X线片,均在ICU内24小时内完成胸部X线和TPTD测量。
  • 以TPTD提取的EVLWI作为肺水肿的定量指标,采用深度学习方法将数据分为二、三、四、五类进行预测。
  • 二分类模型(EVLWI<15、≥15)的准确率为0.93、AUROC为0.98、MCC为0.86。
  • 三个多分类模型的准确率范围为0.90~0.95、AUROC范围为0.97~0.99、MCC范围为0.86~0.92。

证据类型、等级与局限

  • 证据类型:回顾性研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 原文结论认为深度学习能以高准确度量化EVLWI所反映的肺水肿。
  • 原文未据此给出推荐。

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: A quantitative assessment of pulmonary edema is important because the clinical severity can range from mild impairment to life threatening. A quantitative surrogate measure, although invasive, for pulmonary edema is the extravascular lung water index (EVLWI) extracted from the transpulmonary thermodilution (TPTD). Severity of edema from chest X-rays, to date is based on the subjective classification of radiologists. In this work, we use machine learning to quantitatively predict the severity of pulmonary edema from chest radiography.

METHODS: We retrospectively included 471 X-rays from 431 patients who underwent chest radiography and TPTD measurement within 24 h at our intensive care unit. The EVLWI extracted from the TPTD was used as a quantitative measure for pulmonary edema. We used a deep learning approach and binned the data into two, three, four and five classes increasing the resolution of the EVLWI prediction from the X-rays.

RESULTS: The accuracy, area under the receiver operating characteristic curve (AUROC) and Mathews correlation coefficient (MCC) in the binary classification models (EVLWI < 15, ≥ 15) were 0.93 (accuracy), 0.98 (AUROC) and 0.86(MCC). In the three multiclass models, the accuracy ranged between 0.90 and 0.95, the AUROC between 0.97 and 0.99 and the MCC between 0.86 and 0.92.

CONCLUSION: Deep learning can quantify pulmonary edema as measured by EVLWI with high accuracy.

来源:Crit Care,查看原文。版权归原作者所有。

参考来源

  1. Schulz D, Rasch S, Heilmaier M, et al. A deep learning model enables accurate prediction and quantification of pulmonary edema from chest X-rays. Crit Care. 2023. PMID: 37237287. doi:10.1186/s13054-023-04426-5

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。