Park Jae Hyon, Yoon Jongjin, Park Insun, Sim Yongsik, Kim Soo Jin, Won Jong Yun, Han Kichang
Department of Radiology, Yonsei University College of Medicine, Seoul, Republic of Korea.
Department of Anesthesiology and Pain Medicine, Seoul National University Bundang Hospital, Seongnam, Republic of Korea.
Clin Kidney J. 2022 Dec 6;16(3):560-570. doi: 10.1093/ckj/sfac254. eCollection 2023 Mar.
A deep convolutional neural network (DCNN) model that predicts the degree of arteriovenous fistula (AVF) stenosis and 6-month primary patency (PP) based on AVF shunt sounds was developed, and was compared with various machine learning (ML) models trained on patients' clinical data.
Forty dysfunctional AVF patients were recruited prospectively, and AVF shunt sounds were recorded before and after percutaneous transluminal angioplasty using a wireless stethoscope. The audio files were converted to melspectrograms to predict the degree of AVF stenosis and 6-month PP. The diagnostic performance of the melspectrogram-based DCNN model (ResNet50) was compared with that of other ML models [i.e. logistic regression (LR), decision tree (DT) and support vector machine (SVM)], as well as the DCNN model (ResNet50) trained on patients' clinical data.
Melspectrograms qualitatively reflected the degree of AVF stenosis by exhibiting a greater amplitude at mid-to-high frequency in the systolic phase with a more severe degree of stenosis, corresponding to a high-pitched bruit. The proposed melspectrogram-based DCNN model successfully predicted the degree of AVF stenosis. In predicting the 6-month PP, the area under the receiver operating characteristic curve of the melspectrogram-based DCNN model (ResNet50) (≥0.870) outperformed that of various ML models based on clinical data (LR, 0.783; DT, 0.766; SVM, 0.733) and that of the spiral-matrix DCNN model (0.828).
The proposed melspectrogram-based DCNN model successfully predicted the degree of AVF stenosis and outperformed ML-based clinical models in predicting 6-month PP.
开发了一种基于动静脉内瘘（AVF）分流声音预测AVF狭窄程度和6个月主要通畅率（PP）的深度卷积神经网络（DCNN）模型，并将其与基于患者临床数据训练的各种机器学习（ML）模型进行比较。
前瞻性招募了40例功能失调的AVF患者，使用无线听诊器在经皮腔内血管成形术前后记录AVF分流声音。音频文件被转换为梅尔频谱图以预测AVF狭窄程度和6个月PP。将基于梅尔频谱图的DCNN模型（ResNet50）的诊断性能与其他ML模型[即逻辑回归（LR）、决策树（DT）和支持向量机（SVM）]以及基于患者临床数据训练的DCNN模型（ResNet50）进行比较。
梅尔频谱图通过在收缩期的中高频处表现出更大的振幅来定性地反映AVF狭窄程度，狭窄程度越严重，对应于高音调的杂音。所提出的基于梅尔频谱图的DCNN模型成功预测了AVF狭窄程度。在预测6个月PP时，基于梅尔频谱图的DCNN模型（ResNet50）（≥0.870）的受试者操作特征曲线下面积优于基于临床数据的各种ML模型（LR，0.783；DT，0.766；SVM，0.733）以及螺旋矩阵DCNN模型（0.828）。
所提出的基于梅尔频谱图的DCNN模型成功预测了AVF狭窄程度，并且在预测6个月PP方面优于基于ML的临床模型。
