用于预测心脏手术后急性肾损伤发生的机器学习模型的开发、外部验证及可视化

Development, External Validation, and Visualization of Machine Learning Models for Predicting Occurrence of Acute Kidney Injury after Cardiac Surgery.

作者信息

Shao Jiakang, Liu Feng, Ji Shuaifei, Song Chao, Ma Yan, Shen Ming, Sun Yuntian, Zhu Siming, Guo Yilong, Liu Bing, Wu Yuanbin, Qin Handai, Lai Shengwei, Fan Yunlong

机构信息

Medical School of Chinese PLA, 100853 Beijing, China.

Department of Vascular and Endovascular Surgery, The First Medical Center of Chinese PLA General Hospital, 100853 Beijing, China.

出版信息

Rev Cardiovasc Med. 2023 Aug 9;24(8):229. doi: 10.31083/j.rcm2408229. eCollection 2023 Aug.

DOI:10.31083/j.rcm2408229

PMID:39076716

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11266781/

Abstract

BACKGROUND

Cardiac surgery-associated acute kidney injury (CSA-AKI) is a major complication that results in short- and long-term mortality among patients. Here, we adopted machine learning algorithms to build prediction models with the overarching goal of identifying patients who are at a high risk of such unfavorable kidney outcomes.

METHODS

A total of 1686 patients (development cohort) and 422 patients (validation cohort), with 126 pre- and intra-operative variables, were recruited from the First Medical Centre and the Sixth Medical Centre of Chinese PLA General Hospital in Beijing, China, respectively. Analyses were performed using six machine learning techniques, namely K-nearest neighbor, logistic regression, decision tree, random forest (RF), support vector machine, and neural network, and the APPROACH score, a previously established risk score for CSA-AKI. For model tuning, optimal hyperparameter was achieved by using GridSearch with 5-fold cross-validation from the scikit-learn library. Model performance was externally assessed via the receiver operating characteristic (ROC) and decision curve analysis (DCA). Explainable machine learning was performed using the Python SHapley Additive exPlanation (SHAP) package and Seaborn library, which allow the calculation of marginal contributory SHAP value.

RESULTS

637 patients (30.2%) developed CSA-AKI within seven days after surgery. In the external validation, the RF classifier exhibited the best performance among the six machine learning techniques, as shown by the ROC curve and DCA, while the traditional APPROACH risk score showed a relatively poor performance. Further analysis found no specific causative factor contributing to the development of CSA-AKI; rather, the development of CSA-AKI appeared to be a complex process resulting from a complex interplay of multiple risk factors. The SHAP summary plot illustrated the positive or negative contribution of RF-top 20 variables and extrapolated risk of developing CSA-AKI at individual levels. The Seaborn library showed the effect of each single feature on the model output of the RF prediction.

CONCLUSIONS

Efficient machine learning approaches were successfully established to predict patients with a high probability of developing acute kidney injury after cardiac surgery. These findings are expected to help clinicians to optimize treatment strategies and minimize postoperative complications.

CLINICAL TRIAL REGISTRATION

The study protocol was registered at the ClinicalTrials Registration System (https://www.clinicaltrials.gov/, #NCT04966598) on July 26, 2021.

摘要

背景

心脏手术相关急性肾损伤（CSA-AKI）是一种主要并发症，会导致患者出现短期和长期死亡率。在此，我们采用机器学习算法构建预测模型，其总体目标是识别出发生此类不良肾脏结局风险较高的患者。

方法

分别从中国人民解放军总医院第一医学中心和第六医学中心招募了总共1686例患者（开发队列）和422例患者（验证队列），这些患者有126个术前和术中变量。使用六种机器学习技术进行分析，即K近邻、逻辑回归、决策树、随机森林（RF）、支持向量机和神经网络，以及APPROACH评分（一种先前建立的CSA-AKI风险评分）。为了进行模型调整，通过使用来自scikit-learn库的5折交叉验证的GridSearch获得了最佳超参数。通过受试者操作特征（ROC）和决策曲线分析（DCA）对模型性能进行外部评估。使用Python的Shapley加性解释（SHAP）包和Seaborn库进行可解释机器学习，这允许计算边际贡献SHAP值。

结果

637例患者（30.2%）在术后7天内发生了CSA-AKI。在外部验证中，如ROC曲线和DCA所示，RF分类器在六种机器学习技术中表现最佳，而传统的APPROACH风险评分表现相对较差。进一步分析发现没有导致CSA-AKI发生的特定致病因素；相反，CSA-AKI的发生似乎是一个由多种风险因素复杂相互作用导致的复杂过程。SHAP汇总图说明了RF排名前20的变量的正向或负向贡献，并推断了个体层面发生CSA-AKI的风险。Seaborn库展示了每个单一特征对RF预测模型输出的影响。