Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy.
Institute for Applied Mathematics and Information Technology (IMATI), National Research Council of Italy (CNR), Milan, Italy.
J Vasc Access. 2024 Jul;25(4):1170-1179. doi: 10.1177/11297298221147968. Epub 2023 Feb 10.
Arteriovenous fistula (AVF) is the preferred vascular access (VA) for hemodialysis, but it is associated with high non-maturation and failure rates. Predicting patient-specific AVF maturation and postoperative changes in blood flow volumes (BFVs) and vessel diameters is of fundamental importance to support the choice of optimal AVF location and improve VA survival. The goal of this study was to employ machine learning (ML) in order to give physicians a fast and easy-to-use tool that provides accurate patient-specific predictions, useful to make AVF surgical planning decisions.
We applied a set of ML approaches on a dataset of 156 patients. Both parametric and non-parametric ML approaches, taking preoperative data as input, were exploited to predict maturation, postoperative BFVs, and diameters. The best approach associated with lowest cross-validation errors between predictions and real measurements was then chosen to provide estimates and quantify prediction errors.
The -NN was the best approach to predict brachial BFV, AVF maturation, and other VA variables, and it was also associated with the least computational effort. With this approach, the confusion matrices proved the high accuracy of the prediction for AVF maturation (96.8%) and the low absolute error distribution for the continuous BFV and diameter variables.
Our data-based approach provided accurate patient-specific predictions for different AVF configurations, requiring short computational time as compared to a physical model we previously developed. By supporting VA surgical planning, this fast computing approach could allow AVF surgical planning and help reducing the rate of non-maturation, which might ultimately have a broad impact on the management of hemodialysis patients.
动静脉瘘（AVF）是血液透析的首选血管通路，但它与高未成熟和失败率有关。预测患者特定的 AVF 成熟度以及术后血流量（BFVs）和血管直径的变化对于支持最佳 AVF 位置的选择和提高 VA 存活率至关重要。本研究的目的是应用机器学习（ML）为医生提供一个快速且易于使用的工具，提供准确的患者特异性预测，有助于做出 AVF 手术规划决策。
我们将一组 ML 方法应用于 156 名患者的数据集。利用术前数据作为输入，应用参数和非参数 ML 方法来预测成熟度、术后 BFVs 和直径。然后选择与预测与真实测量之间的交叉验证误差最低的最佳方法来提供估计并量化预测误差。
-NN 是预测肱动脉 BFV、AVF 成熟度和其他 VA 变量的最佳方法，它也与最低的计算工作量相关。通过这种方法，混淆矩阵证明了对 AVF 成熟度的预测具有很高的准确性（96.8%），并且连续 BFV 和直径变量的绝对误差分布较低。
我们基于数据的方法为不同的 AVF 配置提供了准确的患者特异性预测，与我们之前开发的物理模型相比，计算时间较短。通过支持 VA 手术规划，这种快速计算方法可以帮助 AVF 手术规划并有助于降低未成熟率，这可能最终对血液透析患者的管理产生广泛影响。
