基于四种机器学习模型预测慢性肾脏病患者全因死亡率。

Prediction of all-cause mortality for chronic kidney disease patients using four models of machine learning.

机构信息

UMR 5558 CNRS Lyon, Université Claude Bernard Lyon 1, Hospices Civils de Lyon, Hôpital Edouard Herriot, Service de Néphrologie, Lyon, France.

Université Claude Bernard Lyon 1, Carmen, Dept Nephrology, Nutrition and Dialysis, Hôpital Lyon Sud, Hospices Civils de Lyon, Pierre-Benite, France.

出版信息

Nephrol Dial Transplant. 2023 Jun 30;38(7):1691-1699. doi: 10.1093/ndt/gfac316.

DOI:10.1093/ndt/gfac316

PMID:36484698

Abstract

BACKGROUND

The prediction tools developed from general population data to predict all-cause mortality are not adapted to chronic kidney disease (CKD) patients, because this population displays a higher mortality risk. This study aimed to create a clinical prediction tool with good predictive performance to predict the 2-year all-cause mortality of stage 4 or stage 5 CKD patients.

METHODS

The performance of four different models (deep learning, random forest, Bayesian network, logistic regression) to create four prediction tools was compared using a 10-fold cross validation. The model that offered the best performance for predicting mortality in the Photo-Graphe 3 cohort was selected and then optimized using synthetic data and a selected number of explanatory variables. The performance of the optimized prediction tool to correctly predict the 2-year mortality of the patients included in the Photo-Graphe 3 database were then assessed.

RESULTS

Prediction tools developed using the Bayesian network and logistic regression tended to have the best performances. Although not significantly different from logistic regression, the prediction tool developed using the Bayesian network was chosen because of its advantages and then optimized. The optimized prediction tool that was developed using synthetic data and the seven variables with the best predictive value (age, erythropoietin-stimulating agent, cardiovascular history, smoking status, 25-hydroxy vitamin D, parathyroid hormone and ferritin levels) had satisfactory internal performance.

CONCLUSIONS

A Bayesian network was used to create a seven-variable prediction tool to predict the 2-year all-cause mortality in patients with stage 4-5 CKD. Prior to external validation, the proposed prediction tool can be used at: https://dev.hed.cc/?a=jpfauvel&n=2022-05%20Modele%20Bayesien%2020000%20Mortalite%207%20variables%20Naif%20Zou%20online(1).neta for research purposes.

摘要

背景

从一般人群数据中开发的预测工具并不适用于慢性肾脏病（CKD）患者，因为这类人群的死亡率风险更高。本研究旨在创建一种具有良好预测性能的临床预测工具，以预测 4 期或 5 期 CKD 患者的 2 年全因死亡率。

方法

使用 10 折交叉验证比较了四种不同模型（深度学习、随机森林、贝叶斯网络、逻辑回归）创建的四种预测工具的性能。选择在 Photo-Graphe 3 队列中预测死亡率表现最佳的模型，然后使用合成数据和选定的一些解释变量对其进行优化。然后评估优化后的预测工具对 Photo-Graphe 3 数据库中患者 2 年死亡率的正确预测能力。

结果

使用贝叶斯网络和逻辑回归开发的预测工具往往具有最佳性能。虽然与逻辑回归没有显著差异，但选择了使用贝叶斯网络开发的预测工具，因为它具有优势，然后对其进行了优化。使用合成数据和七个具有最佳预测值的变量（年龄、促红细胞生成素刺激剂、心血管病史、吸烟状况、25-羟维生素 D、甲状旁腺激素和铁蛋白水平）开发的优化预测工具具有令人满意的内部性能。