文献速递肾血管病与高血压

利用机器学习从频谱多普勒波形中检测动脉粥样硬化性肾动脉狭窄的初步研究

Pilot Study of Using Machine Learning to Detect Atherosclerotic Renal Artery Stenosis From Spectral Doppler Waveforms.
PubMed 文献 · Kidney Int Rep · 2025-01-16

该研究回顾性纳入2000年1月至2022年1月期间经血管造影确诊的单侧动脉粥样硬化性肾动脉狭窄(ARAS)且需置入肾动脉支架的患者200例,以患肾为阳性病例、对侧正常肾为对照,将肾双功能超声的频谱波形重建为一维速度信号,训练一维卷积神经网络检测ARAS。最终198例患者的396条信号用于分析,模型总体准确率为0.95,精确率为0.94,受试者工作特征曲线下面积为0.97。

要点

  • 单侧ARAS患者的肾双功能超声频谱波形可重建为一维速度信号用于机器学习分析。
  • 一维卷积神经网络检测ARAS的总体准确率为0.95,精确率为0.94。
  • 受试者工作特征曲线下面积为0.97。

核心结论

  • 机器学习可利用肾双功能超声的动脉频谱多普勒波形成功检测动脉粥样硬化性肾动脉狭窄。

研究设计与样本

  • 回顾性识别2000年1月至2022年1月经血管造影确诊的单侧ARAS(对侧肾正常)且需置入肾动脉支架的患者。
  • 排除标准为缺术前肾双功能超声图像、合并纤维肌性发育不良、任一侧存在多于1条肾动脉或既往置入肾动脉支架后发生支架内再狭窄。
  • 选取200例患者,患肾作为阳性病例、对侧肾作为对照。
  • 使用WebPlotDigitizer手动描记外 envelope 重建频谱波形,将图形坐标转换为一维速度信号。
  • 信号标注为ARAS与正常后随机分为训练集(80%)与测试集(20%)。

主要发现

  • 排除2例因信号提取不充分后,最终198例患者的396条信号用于分析(中位年龄72岁,女性占51.0%)。
  • 训练后模型的总体准确率为0.95,精确率为0.94。
  • 受试者工作特征曲线下面积为0.97。

临床怎么用

  • 原文未据此给出推荐。

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)。

原文

INTRODUCTION: We investigated whether machine learning (ML) could be used to determine atherosclerotic renal artery stenosis (ARAS) using spectral Doppler waveforms in renal duplex ultrasound (DUS). METHODS: Patients with unilateral ARAS (contralateral normal kidney) confirmed by angiogram and requiring renal artery stent placement were retrospectively identified from January 2000 to January 2022. The exclusion criteria were unavailable preoperative renal DUS images, concomitant fibromuscular dysplasia, more than 1 renal artery on either side, or a previously placed renal artery stent with in-stent restenosis. Two hundred patients were selected; the affected kidney was used as the positive case and the contralateral kidney was used as the control. The spectral waveforms were reconstructed by manually tracing the outer envelope using WebPlot Digitizer. The graphical coordinates were then converted into 1-dimensional velocity signals. Signals were labeled as ARAS and normal and then randomly divided into training (80%) and testing (20%) datasets. A 1-dimensional convolutional neural network (CNN) was trained to classify the signals and detect ARAS. An Adam optimizer with a learning rate of 0.001 and a cross-entropy loss function were utilized. Five-fold cross-validation was applied, and the model was trained for 1000 epochs. RESULTS: A total of 396 signals were used from 198 patients after excluding 2 patients because of inadequate signal extraction (median age = 72 years, females = 51.0%). The overall accuracy of the trained model was 0.95 with a precision of 0.94. The area under the receiver operating characteristic curve was 0.97. CONCLUSION: ML has been successfully employed to detect ARAS using arterial spectral Doppler waveforms in DUS.

来源:Kidney Int Rep,查看原文。版权归原作者所有。

引用

  1. Mukhtar H, Rassoulinejad-Mousavi SM, Faghani S, et al. Pilot Study of Using Machine Learning to Detect Atherosclerotic Renal Artery Stenosis From Spectral Doppler Waveforms. Kidney Int Rep. 2025. PMID: 40303222. doi:10.1016/j.ekir.2025.01.012

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。